---
name: trekexecute
description: Disciplined plan executor — single-session, or multi-session through session orders the user starts, with failure recovery
argument-hint: "[--project <dir>] [--fg | --resume | --dry-run | --validate | --step N | --session N] [plan.md]"
allowed-tools: Read, Write, Edit, Bash, Glob, Grep, AskUserQuestion, Agent, Skill
disallowed-tools: TeamCreate
---

# Ultraexecute Local

Disciplined executor for trekplan plans. Reads a plan file, detects if it has
an Execution Strategy (multi-session), and either executes directly or
prepares one session order per session, wave by wave — all to realize one plan.

Each plan step is built by **one fresh helper** (`voyage:step-implementer`)
and judged by **one controller** that reads the step's diff. The executor
itself writes no product code: it records the start point, launches the
helper, runs the mechanical checks (proof of red, the floor guard, the
manifest, the step check, the regression, the done line), and decides from
exit codes and the controller's verdicts (Phase 6).

It starts only on a plan the operator approved as it is now (Phase 1, K2), and
it ends with a review it starts by itself (Phase 7.2): `/simplify`, then
`/trekreview`, then the verdict gate (K7). A BLOCK keeps the merge into main
closed (Phase 8). The guard asks the one question before a merge; the executor
never asks it again (operator decision 2026-10-08).

Voyage never starts a Claude Code session. Work that needs another session
becomes an order plus a starter line the user gives a session they open
themselves (Phase 2.6). Helpers inside this session are subagents, and helpers
never start helpers.

## Phase 1 — Parse mode and validate input

Parse `$ARGUMENTS` for mode flags:

1. If arguments contain `--project <dir>`: extract the directory path.
   - Resolve `{dir}` (trim trailing slash).
   - Set **project_dir = {dir}**.
   - Derive implicit file path: `{dir}/plan.md`.
   - If `{dir}` does not exist or `{dir}/plan.md` is missing:
     ```
     Error: project directory missing plan.md: {dir}
     Run /trekplan --project {dir} to produce it.
     ```
   - If no explicit `<plan.md>` argument is provided after flag parsing,
     use the derived `{dir}/plan.md`. If a `<plan.md>` argument IS provided,
     use that path but keep `project_dir` set (user may be pointing at a
     recovery session spec inside the project).
   - Continue parsing remaining flags (they combine with `--project`).
2. If arguments contain `--fg`: extract the file path. Set **mode = foreground**.
3. If arguments contain `--resume`: extract the file path. Set **mode = resume**.
4. If arguments contain `--dry-run`: extract the file path. Set **mode = dry-run**.
5. If arguments contain `--validate`: extract the file path. Set **mode = validate**.
6. If arguments contain `--step N` (N is a positive integer): extract N and the file path.
   Set **mode = step**, **target-step = N**.
7. If arguments contain `--session N` (N is a positive integer): extract N and the file path.
   Set **mode = session**, **target-session = N**.
8. If arguments contain `--gates`: set `gates_mode = true`. Default
   `gates_mode = false`. The flag is consumed by the autonomy-gate state
   machine via the CLI shim:
   `node ${CLAUDE_PLUGIN_ROOT}/lib/util/autonomy-gate.mjs --state X --event Y --gates {true|false}`.
   It no longer adds a question of the executor's own before a merge. The
   wave merge-back (Phase 2.6 Step 3) and the merge into main (Phase 8) are
   asked by the guard, which asks before every merge into main and every push,
   in auto mode too, and the executor never asks the same thing again
   (operator decision 2026-10-08: two questions for one merge became one). The
   MAIN_MERGE_GATE in Phase 8 is always on, regardless of `gates_mode`: it is
   a lock, and the guard's question is the one question.
9. Otherwise: the entire argument string is the file path. Set **mode = execute**.

If no path is provided (and `--project` was not used to derive one), output
usage and stop:

```
Usage: /trekexecute <plan.md>
       /trekexecute --project <dir>
       /trekexecute --fg <plan.md>
       /trekexecute --resume <plan.md>
       /trekexecute --dry-run <plan.md>
       /trekexecute --validate <plan.md>
       /trekexecute --step N <plan.md>
       /trekexecute --session N <plan.md>
       /trekexecute --project <dir> --resume
       /trekexecute --project <dir> --session N

Modes:
  (default)      Auto — multi-session if plan has Execution Strategy, else foreground
  --project      Resolve plan.md inside an trekbrief project folder; progress.json
                 is written there too
  --fg           Force foreground — all steps sequentially, ignore Execution Strategy
  --resume       Resume from last progress checkpoint
  --dry-run      Validate plan and show execution strategy without running
  --validate     Schema-only check — parse steps + manifests, no security scan, no execution
  --step N       Execute only step N (foreground)
  --session N    Execute only session N from the plan's Execution Strategy

Examples:
  /trekexecute .claude/plans/trekplan-2026-04-06-auth-refactor.md
  /trekexecute --project .claude/projects/2026-04-18-jwt-auth
  /trekexecute --project .claude/projects/2026-04-18-jwt-auth --resume
  /trekexecute --fg .claude/plans/trekplan-2026-04-06-auth-refactor.md
  /trekexecute --session 2 .claude/plans/trekplan-2026-04-06-auth-refactor.md
  /trekexecute --dry-run .claude/plans/trekplan-2026-04-06-auth-refactor.md
  /trekexecute --validate .claude/plans/trekplan-2026-04-06-auth-refactor.md
```

If the file does not exist, report and stop:
```
Error: file not found: {path}
```

Report detected mode:
```
Mode: {execute | resume | dry-run | step N | session N}
Project: {project_dir or "-"}
File: {path}
```

### Plan approval gate (K2)

**Runs in every mode that executes** (execute, resume, step N, session N).
Dry-run and validate execute nothing and skip it. Before anything is parsed
for execution, check that the operator approved THIS plan as it is now.
`/trekplan` logs the approval bound to the plan file's sha256 (its Phase 11:
`approval-log.mjs append --kind plan --sha256-of`), so an edit after the
approval makes it stale. Nothing reads the log file directly (K2); the log's
own CLI answers:

```bash
node ${CLAUDE_PLUGIN_ROOT}/lib/util/approval-log.mjs verify --json --kind plan --subject "{plan_path}" --sha256-of "{plan_path}"
```

`{plan_path}` is the file resolved above. Exit 0 (`approved`) → continue and
record `plan_approval = "approved"`; if `uncommitted` is above 0, say in one
line that N approvals are in the log but not committed yet. Exit 1 → **halt**:
no step, no helper, no progress file. Print `status` and `detail`:

| `status` | Meaning | What the operator does |
|----------|---------|------------------------|
| `not-logged` | The plan was never approved, or was approved before the log existed | `/trekplan --project {dir}` and answer "Approve" at its plan approval |
| `mismatch` | The plan changed after its approval (the approval covers other content) | Same: approve the plan as it is now, or restore the approved text. A review loop interrupted between adding its steps and the approval left the approved text in `{report dir}/plan-approved-round-{R}.md` (Phase 7.2): copy it back |
| `expired` | The approval carried an expiry that has passed | Same |
| `broken` | A record in `.claude/voyage/approvals.jsonl` was edited, removed or reordered | Restore the log from git (`git checkout -- .claude/voyage/approvals.jsonl`), then re-run |
| `diverged` | Committed approvals were rewritten | Same: restore from git |

Exit 2, or no JSON at all → **halt** and show the raw error: an approval check
that could not run is never a pass.

**Not checked:** a session spec or a recovery spec (a file with
`## Scope Fence`, Phase 2). Voyage writes those from an approved plan (the
session decomposer, Phase 7.6), and they carry no approval of their own.
Record `plan_approval = "not-checked"` and say "plan approval: not checked
(session spec)" in the final report, never "approved". A `--session N` run of
a trekplan's Execution Strategy executes the plan itself, so it IS checked:
the log is committed, and Phase 2.55 Check 2 brings the plan into the worktree.

The remediation steps of the review loop (Phase 7.2) change the plan, so the
loop asks for the plan's approval again before it builds them. Nothing else
in this command edits the plan.

Borrowed: the form of `lib/validators/intent-approval.mjs` and the `/trekplan`
intent gate (an approval bound to the approved content's hash, checked before
the work starts); the log is ai-native-sdlc's gate ledger (MIT), with its two
flaws corrected (header of `lib/util/approval-log.mjs`).

## Phase 2 — Detect file type and parse structure

Read the file. Determine whether it is an **trekplan** or a **session spec**:

- **Session spec**: contains `## Dependencies` with `Entry condition:` AND `## Scope Fence`
  AND `## Exit Condition` sections.
- **Voyage**: contains `## Implementation Plan` with numbered `### Step N:` headings
  but no `## Scope Fence`.

If neither structure is detected, report and stop:
```
Error: unrecognized file format. Expected an trekplan or session spec.
```

### Parse steps

Extract every `### Step N: {description}` heading (in order). For each step, extract:
- **Files** — file paths to create or modify
- **Changes** — what to modify
- **Reuses** — existing code to leverage (informational)
- **Test first** — the test the step writes before it builds: its `File:`
  (existing | new), what it `Verifies:`, an optional `Pattern:` (required from
  plan_version ≥ 1.8, see below)
- **Verify** — command to run after implementation: the first backticked
  span of the field. It is also the step's **test command**: proof of red
  (Sub-step B) and the done line (Sub-step G) run it, so it must be one
  test-runner invocation
- **On failure** — recovery action: the field starts with one of the words
  `revert`, `retry`, `skip`, `escalate` (K11; the plan validator warns
  otherwise), and the rest is the clause's detail
- **Regression** — optional (K10): ONE command from the criteria runner's
  allowlist, without pipes or `&&`: the frozen regression suite the step must
  keep green. Sub-step D4 runs it before the checkpoint; a step without the
  field runs as before. The plan validator rejects a `Regression:` that cannot
  run once K10 is in it (wave 2, order 9); for a plan validated before that,
  Sub-step D4 is where an unrunnable one is caught, never read as green
- **Checkpoint** — git commit command after success
- **Manifest** — YAML block following Checkpoint (v1.7+)
- **Interface in** / **Interface out** / **Review focus** — optional (K4):
  what the step consumes and produces, and what its controller must look at
  hardest. Read when present and passed to the helper and the controller;
  never required, and the executor tolerates their absence in every plan
  version.

If a step is missing `On failure`, default to `escalate` and record a parse warning.
If a step is missing `Verify`, record a parse warning.

**`Test first:` is required from plan_version ≥ 1.8.** A ≥ 1.8 step without a
`Test first:` field (or whose `File:` is missing) is not executable: STOP with
```
Error: plan_version={v} but step {N} has no Test first: field.
Re-run /trekplan - from plan_version 1.8 every step proves red before it builds.
```
For plans below 1.8 the field stays optional: a step without it runs, its
`red_proof` is recorded as `"not-run"`, and the final report counts it among
the steps without proof of red (never hidden, never called proven).

### Parse the Manifest block (v1.7+)

Read the plan header for a `plan_version` marker. Treat ≥ `1.7` as strict
mode; absence or <1.7 as legacy mode.

**Strict mode (plan_version ≥ 1.7):**
- Every step MUST have a `Manifest:` block with a YAML fenced payload.
- Parse the YAML. Required keys: `expected_paths` (list), `min_file_count`
  (integer), `commit_message_pattern` (string), `bash_syntax_check` (list),
  `forbidden_paths` (list), `must_contain` (list of `{path, pattern}` dicts).
- Validate each `commit_message_pattern` compiles as a regex (use a tolerant
  parser — do not execute untrusted input against shell).
- If any step is missing its Manifest, or YAML is malformed, STOP with:
  ```
  Error: plan_version=1.7 but step {N} has invalid/missing Manifest.
  Re-run planning-orchestrator — plan is not executable.
  ```

**Legacy mode (no plan_version, or < 1.7):**
- Synthesize a minimal manifest per step:
  - `expected_paths` ← step's `Files:` list
  - `min_file_count` ← `len(expected_paths)`
  - `commit_message_pattern` ← regex-escape first 3 words of Checkpoint msg
  - `bash_syntax_check` ← auto-detect `.sh` in Files
  - `forbidden_paths` ← []
  - `must_contain` ← []
- Record `legacy_plan: true` in the progress file.
- Emit warning: `Legacy plan (v1.6 or earlier) — manifests synthesized with
  reduced audit precision.`

### Parse Session Manifest (session specs only)

If the file is a session spec (v1.7+), parse the `## Session Manifest` block
into a YAML dict. Preserve `session_manifest.*` fields for Phase 7.5 audit.
If missing and `plan_version ≥ 1.7`, record a parse warning but continue —
the per-step manifests are still available for audit.

### Parse session spec fields (if applicable)

- **Entry condition** from `## Dependencies`
- **Touch list** and **Never-touch list** from `## Scope Fence`
- **Exit condition** checklist from `## Exit Condition`

### Parse Execution Strategy (if present)

If the plan contains an `## Execution Strategy` section, extract:
- Each `### Session N: {title}` with its Steps, Wave, Depends on, and Scope fence
- The `### Execution Order` with wave definitions

Set **has_execution_strategy = true**.

Report:
```
Type: {plan | session-spec}
Steps: {N}
{if has_execution_strategy}: Execution Strategy: {S} sessions across {W} waves
{if session spec}: Entry condition: {text}
{if session spec}: Scope fence: {N} touch, {N} never-touch
{if warnings}: Warnings: {list}
```

## Phase 2.3 — Validate-only mode exit (if mode = validate)

**If mode = validate, stop after Phase 2 parsing** and emit a schema-only
report. Do NOT run security scan, do NOT touch progress files, do NOT
execute any steps. This gives the user a fast sanity-check of plan
schema compliance without side effects.

**Preferred path (since v3.1.0):** invoke the plan validator directly. It
returns the same diagnostic info Phase 2 derives in prose, with stable
error codes for downstream tooling:

```bash
node ${CLAUDE_PLUGIN_ROOT}/lib/validators/plan-validator.mjs --strict --json "{path}"

# When --project is in scope and progress.json exists, also validate it:
[ -f "{project_dir}/progress.json" ] && \
  node ${CLAUDE_PLUGIN_ROOT}/lib/validators/progress-validator.mjs --json "{project_dir}/progress.json"
```

Map the validator's `code` field to the error templates below (e.g.
`PLAN_FORBIDDEN_HEADING` → "Detected heading format" branch). When both
calls exit 0, render the READY report. Otherwise render FAIL with the
validator's first error code + message.

If Phase 2 parsing succeeded (no fatal errors, every step has a valid
Manifest block in strict mode, or synthesized manifests in legacy mode):

```
=== Schema Validation: READY ===
File: {path}
Type: {plan | session-spec}
plan_version: {1.7 | legacy}
Steps: {N}
Manifests: {N valid | N synthesized (legacy)}
Warnings: {count}
{if warnings}: - {each warning on own line}

Plan is schema-compliant. Safe to run:
  /trekexecute {path}
```

If Phase 2 parsing failed (unrecognized format, missing Manifest in strict
mode, malformed YAML, invalid regex):

```
=== Schema Validation: FAIL ===
File: {path}
Reason: {specific error from Phase 2}

{if format not recognized}:
  Detected heading format: {e.g. "### Fase 1:", "## Phase 1"}
  Expected: "### Step N: <description>"
  Fix: re-run /trekplan — planning-orchestrator must emit v1.7 format

{if missing manifest}:
  Step {N} has no Manifest block (plan_version=1.7 requires one per step)
  Fix: re-run /trekplan — planning-orchestrator must include manifest YAML

{if malformed YAML or invalid regex}:
  Step {N}: {specific YAML/regex error}
  Fix: edit the plan manually or re-run /trekplan
```

Exit after emitting the report. Do not continue to Phase 2.4 or later.

## Phase 2.4 — Pre-execution security scan

**Runs for all modes except dry-run and validate** (those modes exit earlier or have their own report format).

Scan every `Verify:` and `Checkpoint:` command in the parsed plan against the
executor security denylist. This catches dangerous commands before execution begins.

### Extract commands

For each step in the plan, extract the command string from:
- `Verify:` field (the shell command after the backtick-quoted command)
- `Checkpoint:` field (the git commit command)

Also extract Exit Condition commands if present.

### Check against denylist

For each extracted command, check against these patterns:

**BLOCK patterns (stop execution immediately):**

| Pattern | Threat |
|---------|--------|
| `rm` with both `-r` and `-f` flags (any order) | Recursive force delete |
| `chmod 777` or `chmod -R 777` | World-writable permissions |
| `curl`/`wget` piped to `bash`/`sh`/`zsh` | Remote code execution |
| `eval` with `$`, backtick, or `$(` | Code injection via eval |
| `mkfs` or `dd` writing to `/dev/sd*`, `/dev/nvme*`, `/dev/hd*` | Disk destruction |
| `shutdown`, `reboot`, `halt`, `poweroff` | System shutdown |
| `:(){ :\|:& };:` pattern | Fork bomb |
| `base64` piped to `bash`/`sh` | Obfuscated code execution |
| `crontab -e` or writing to `/etc/cron*` | Persistence via cron |
| `kill -9 -1` or `pkill -9 -1` | Kill all user processes |
| `history -c` or truncating `~/.bash_history` | Evidence destruction |

**WARN patterns (report but continue):**

| Pattern | Concern |
|---------|---------|
| `npm install --save`, `pip install`, `cargo add` | Dependency changes during execution |
| `git push --force` | History rewrite |
| `git reset --hard` | Discard uncommitted changes |

### Scan output

For each match:
```
Security scan: Step {N} — {description}
  Command: {command}
  {BLOCKED | WARNING}: {pattern name}
```

**If ANY BLOCK pattern is found:**

```
SECURITY SCAN FAILED: {count} dangerous command(s) found in plan.

Blocked commands:
  Step {N}: {command} → {reason}

This plan contains commands blocked by the executor security policy.
The plan may have been tampered with or contain hallucinated dangerous commands.

Options:
  1. Review and fix the plan file: {path}
  2. Use --dry-run to inspect all commands without executing
  3. Use --fg for interactive execution (hooks provide additional protection)
```

Stop execution. Do NOT continue to Phase 2.5.

**If only WARN patterns found:** Continue execution but include warnings in the
pre-execution summary. Report them in the final output under "Security advisories."

**If clean:** Report `Security scan: PASS ({N} commands checked)` and continue.

## Phase 2.5 — Execution strategy decision

Determine how to execute this plan:

**Run as single session (foreground)** when ANY of these are true:
- `--fg` flag is set
- `--step N` mode
- `--resume` mode
- `--session N` mode (runs only that session's steps, foreground)
- Plan has no `## Execution Strategy` section
- Plan has Execution Strategy with only 1 session

**Run as multi-session (parallel orchestration)** when ALL of these are true:
- mode = `execute` (default, no --fg)
- Plan has `## Execution Strategy` with 2+ sessions
- At least one wave has 2+ sessions (parallelism possible)

**Run as multi-session (sequential orchestration)** when:
- mode = `execute` (default, no --fg)
- Plan has `## Execution Strategy` with 2+ sessions
- All sessions are in different waves (no parallelism, but still separate sessions)

For single-session (including every `--session N` run inside a session's
worktree): continue to Phase 3.
For multi-session, first locate the main checkout and the wave marker:

```bash
GIT_DIR_ABS="$(cd "$(git rev-parse --git-dir)" && pwd -P)"
GIT_COMMON_ABS="$(cd "$(git rev-parse --git-common-dir)" && pwd -P)"
MAIN_ROOT="$(git worktree list --porcelain | sed -n '1s/^worktree //p')"
if [ "$GIT_DIR_ABS" != "$GIT_COMMON_ABS" ]; then
  echo "Error: this is a linked worktree. Run this from the main checkout $MAIN_ROOT." >&2
  exit 1
fi
if [ -f "$MAIN_ROOT/.claude/trekplan-sessions/{slug}/orders/wave.json" ]; then echo "WAVE_IN_FLIGHT"; else echo "NO_WAVE"; fi
```

Exit 1 means this is a session's (or another) linked worktree: stop and report
the message — the multi-session path runs only from the main checkout, whose
root the first entry of `git worktree list` names (`--show-toplevel` would name
the linked worktree and miss the wave). `WAVE_IN_FLIGHT`: a wave is awaiting
its sessions — skip Phase 2.55 (its clean-tree and stale-worktree checks would
touch the live worktrees) and jump to Phase 2.6, which collects the wave.
`NO_WAVE`: run Phase 2.55, then Phase 2.6.

Report:
```
Strategy: {single session | N sessions (M parallel, K sequential)}
```

## Phase 2.55 — Pre-flight safety checks

**Only runs for multi-session parallel execution.** These checks prevent the
catastrophic data loss that occurs when parallel sessions share a working directory.

### Check 1 — Clean working tree

Run `git status --porcelain -- ':(top,exclude).claude/trekplan-sessions/'`
(the whole repo, from any subdirectory, minus Voyage's own session state: orders,
archived progress and kept session worktrees are never merged, and counting them
would stop every re-run after a failed wave). If there are ANY uncommitted or
untracked changes:

```
Error: working tree is not clean. Parallel execution requires a clean git state.
Uncommitted changes are invisible to worktrees and will be lost during merge.

Untracked/modified files:
{output of git status --porcelain}

Commit or stash your changes, then re-run.
To run sequentially instead: /trekexecute --fg {plan-path}
```

Stop execution. Update progress with `status: "stopped"`.

**Also write `.session-state.local.json`** (Handover 7) — this surfaces the
stopped state to `/trekcontinue` so the next session can prompt the user to
clean the working tree before resuming. Write atomically alongside `progress.json`:

```json
{
  "schema_version": 1,
  "project": "{project_dir}",
  "next_session_brief_path": "{project_dir}/brief.md",
  "next_session_label": "{current session label, or 'Continue'}",
  "status": "stopped",
  "updated_at": "{ISO-8601 now}"
}
```

Verify with `node ${CLAUDE_PLUGIN_ROOT}/lib/validators/session-state-validator.mjs --json
{project_dir}/.session-state.local.json`. On validator failure, emit a warning
to stderr but do NOT block the stop; `progress.json` is still authoritative.

**Also write sibling `NEXT-SESSION-PROMPT.local.md`** with frontmatter
(`produced_by: trekexecute`, `produced_at: <ISO-8601>`,
`status: stopped`) so the next-session producer-mismatch check has both
candidates available. Use the same combined ESM block pattern as Phase 8.

### Check 2 — Plan file reaches every worktree

Worktrees are created from HEAD, so tracking the plan file is the cheapest way
to make it visible in each one. But the project directory may be **gitignored**
— `.claude/projects/` is tool-managed and local-only, and a repo that ignores it
is normal, not exotic. `git add -f` is **not** the answer there: it would push
operator-local artifacts into history, and into whatever remote the repo
publishes to. When the plan file is ignored, Phase 2.6 Step 2a' (which copies
brief/plan/research into each worktree) is the delivery path, and this check
must step aside instead of failing.

```bash
PLAN_PATH="{plan-path}"
if git ls-files --error-unmatch "$PLAN_PATH" >/dev/null 2>&1; then
  PLAN_TRACKING="tracked"
else
  git check-ignore -q "$PLAN_PATH"
  case "$?" in
    0) PLAN_TRACKING="ignored" ;;
    1) PLAN_TRACKING="untracked" ;;
    *) echo "Error: git check-ignore failed on $PLAN_PATH - a fatal probe is not an answer about ignore status." >&2
       exit 1 ;;
  esac
fi
if [ "$PLAN_TRACKING" = "untracked" ]; then
  git add "$PLAN_PATH"
  git commit -m "chore: track plan file for parallel execution"
fi
```

Report by outcome:

| `PLAN_TRACKING` | Report |
|---|---|
| `tracked` | `Plan file already tracked.` |
| `untracked` | `Plan file committed for worktree visibility.` |
| `ignored` | `Plan file is gitignored — not forced into history. Step 2a' copies it into each worktree.` |

Any other `git check-ignore` exit code is fatal and stops execution: a probe
that failed is not a probe that answered "not ignored".

### Check 3 — Scope fence overlap validation

For each wave that has 2+ sessions, validate that no file appears in the Touch
list of two different sessions in the same wave:

1. For each session in the wave, extract the "Touch" list from the Execution Strategy.
2. For each pair of sessions (A, B) in the same wave, compute the intersection
   of their Touch lists.
3. If any intersection is non-empty:

```
Error: scope fence overlap detected in Wave {W}.
Sessions {A} and {B} both touch: {overlapping files}
These sessions cannot safely run in parallel.

Fix the Execution Strategy in the plan, or use --fg for sequential execution.
```

Stop execution. This is a defense-in-depth check — the planning-orchestrator
should have prevented this, but verifying at execution time catches plans
that were manually edited or have bugs.

### Check 4 — Stale worktree cleanup

Clean up what an earlier run of this plan left under
`trekplan-sessions/{slug}/` — never with force. It refuses from a linked
worktree and while a wave is awaiting its sessions (those worktrees and branches
are live or finished session work, not stale). `git worktree remove` without
force refuses a worktree with modified or untracked files, and `git branch -d`
refuses an unmerged branch: both are kept, reported, and never retried with
force.

```bash
# zsh (the Bash tool runs the user's shell): an unmatched glob stays literal, as in bash.
[ -n "${ZSH_VERSION:-}" ] && setopt nonomatch
GIT_DIR_ABS="$(cd "$(git rev-parse --git-dir)" && pwd -P)"
GIT_COMMON_ABS="$(cd "$(git rev-parse --git-common-dir)" && pwd -P)"
MAIN_ROOT="$(git worktree list --porcelain | sed -n '1s/^worktree //p')"
if [ "$GIT_DIR_ABS" != "$GIT_COMMON_ABS" ]; then
  echo "Error: this is a linked worktree. Run this from the main checkout $MAIN_ROOT." >&2
  exit 1
fi
SESSIONS="$MAIN_ROOT/.claude/trekplan-sessions/{slug}"
if [ -f "$SESSIONS/orders/wave.json" ]; then
  echo "Error: $SESSIONS/orders/wave.json exists - a wave is awaiting its sessions. Stale-worktree cleanup refused." >&2
  exit 1
fi
cd "$MAIN_ROOT" || exit 1
for wt in "$SESSIONS/worktrees"/session-*; do
  [ -d "$wt" ] || continue
  GIT_OPTIONAL_LOCKS=0 git worktree remove "$wt" 2>/dev/null || echo "KEPT worktree $wt"
done
GIT_OPTIONAL_LOCKS=0 git worktree prune
git for-each-ref --format='%(refname:short)' "refs/heads/trek/{slug}/" | while read -r b; do
  GIT_OPTIONAL_LOCKS=0 git branch -d "$b" >/dev/null 2>&1 || echo "KEPT branch $b"
done
KEPT="$(ls -d "$SESSIONS/worktrees"/session-* 2>/dev/null; git for-each-ref --format='%(refname:short)' "refs/heads/trek/{slug}/")"
if [ -n "$KEPT" ]; then
  echo "Earlier session work kept (changes or unmerged commits):" >&2
  echo "$KEPT" >&2
  exit 1
fi
```

Exit 0: report `Cleaned stale worktrees and merged branches from a previous run.`
Exit 1: stop and report its message. For every kept item say what the user can
do: a worktree — inspect it (`git -C <path> status --short`), commit or move
what matters, then `git worktree remove <path>`; a branch — inspect it
(`git log HEAD..<branch>`), merge it by hand, or delete it themselves once its
commits are not needed. Then re-run.

After all 4 checks pass:
```
Pre-flight: PASS (clean tree, plan reaches worktrees, no overlaps, no stale worktrees)
```

## Phase 2.6 — Multi-session orchestration (worktree-isolated, session orders)

**Only runs for multi-session execution.** Voyage never starts a Claude Code
session. This phase prepares ONE wave at a time: it creates an isolated git
worktree for each session in the wave, writes a **session order** for each
(the worktree, the steps, the done-condition) plus a one-line **starter**, and
stops. The user opens each session themselves, in the directory the order
names, and gives it the starter. Running the same `/trekexecute` command again
in the main checkout collects the wave: it reads every session's progress file,
merges the session branches back sequentially, cleans up, and prepares the next
wave. After the last wave, jump to Phase 8 (final report).

**CRITICAL SAFETY RULE:** Every session MUST run in its own git worktree. Never
run two sessions in the same working directory. This rule exists because
parallel git operations in a shared worktree cause index corruption, race
conditions, and repository destruction. Each order names its own worktree.

### Step 0 — Resolve paths and detect a wave in flight

```bash
# The MAIN checkout, never a linked worktree (Phase 2.5): in a session's
# worktree --show-toplevel names that worktree.
GIT_DIR_ABS="$(cd "$(git rev-parse --git-dir)" && pwd -P)"
GIT_COMMON_ABS="$(cd "$(git rev-parse --git-common-dir)" && pwd -P)"
REPO_ROOT="$(git worktree list --porcelain | sed -n '1s/^worktree //p')"
if [ "$GIT_DIR_ABS" != "$GIT_COMMON_ABS" ]; then
  echo "Error: this is a linked worktree. Run this from the main checkout $REPO_ROOT." >&2
  exit 1
fi
# The plan path relative to the main checkout: every session-orders.mjs call
# runs from $REPO_ROOT with it, and each session finds the plan there in its
# own worktree.
PLAN_REL="$(python3 -c 'import os.path,sys; print(os.path.relpath(os.path.realpath(sys.argv[1]), os.path.realpath(sys.argv[2])))' "{plan-path}" "$REPO_ROOT")"
case "$PLAN_REL" in
  ""|..*)
    echo "Error: the plan {plan-path} is not inside the main checkout $REPO_ROOT." >&2
    exit 1 ;;
esac
SESSION_DIR="$REPO_ROOT/.claude/trekplan-sessions/{slug}"
WORKTREE_DIR="$SESSION_DIR/worktrees"
ORDERS_DIR="$SESSION_DIR/orders"
ORIGINAL_BRANCH="$(git rev-parse --abbrev-ref HEAD)"
# Resolve the plugin root ONCE (same reason as Phase 7: the variable is
# substituted in this command's text but EMPTY in the Bash tool's env).
# Only the literal form is substituted (a `:-` default is never replaced); the
# fallback takes the highest installed version under cache/<market>/voyage/.
VOYAGE_ROOT="${CLAUDE_PLUGIN_ROOT}"
case "$VOYAGE_ROOT" in
  /*) ;;
  *) VOYAGE_ROOT="$(ls -d "$HOME"/.claude/plugins/cache/*/voyage/[0-9]*/ 2>/dev/null \
       | awk -F/ '{ split($(NF-1), v, "."); printf "%09d%09d%09d %s\n", v[1], v[2], v[3], $(0) }' \
       | sort | tail -1 | cut -d' ' -f2-)"
     VOYAGE_ROOT="${VOYAGE_ROOT%/}" ;;
esac
if [ ! -f "$VOYAGE_ROOT/lib/util/session-orders.mjs" ]; then
  echo "[voyage] session orders cannot be written - plugin root unresolved." >&2
  exit 2
fi
if [ -f "$ORDERS_DIR/wave.json" ]; then echo "WAVE_IN_FLIGHT"; else echo "NO_WAVE"; fi
```

Record `REPO_ROOT`, `PLAN_REL`, `SESSION_DIR`, `WORKTREE_DIR`, `ORDERS_DIR`,
`VOYAGE_ROOT` and `ORIGINAL_BRANCH` for the later steps. All paths except
`PLAN_REL` must be absolute.

- `WAVE_IN_FLIGHT` → read the wave number `W` from `$ORDERS_DIR/wave.json` and
  jump to **Step 3** (collect). Phase 2.55 was skipped for this run (Phase 2.5).
- `NO_WAVE` → prepare the lowest wave not yet merged:
  ```bash
  (cd "$REPO_ROOT" && node "$VOYAGE_ROOT/lib/util/session-orders.mjs" next-wave --plan "$PLAN_REL" --session-dir "$SESSION_DIR")
  ```
  A number is `W`: continue to Step 1. `none` means earlier runs merged every
  wave: go to Step 4. The record it reads, `$ORDERS_DIR/merged-waves.json`
  (plan path + sha256 of the plan's content), is written by Step 3 after each
  merged wave, survives Step 5, and is cleared only on confirm at Phase 8's
  main-merge gate, when every wave is merged and Step 4 passed, so a re-run
  after a later wave failed (or after a declined gate) never prepares an
  already-merged wave again.
  If `next-wave` exits 1, the record belongs to another plan or another version
  of this one (`{slug}` is the plan's file name, so plans can share
  `$SESSION_DIR`). Stop, touch nothing, and tell the user exactly what its
  message says: an unfinished multi-session run of that plan holds
  `$ORDERS_DIR`. Finish that run (re-run it with its own plan), or clear it and
  re-run this one:
  `(cd "$REPO_ROOT" && node "$VOYAGE_ROOT/lib/util/session-orders.mjs" clear --session-dir "$SESSION_DIR")`.

### Step 1 — Create worktrees for wave W

```bash
mkdir -p "$WORKTREE_DIR" "$ORDERS_DIR"
# The run's start point, written once (wave 1): Step 6's whole-run checks and
# the review (Phase 7.2) read it. Phase 8's clear removes it with the orders.
[ -f "$ORDERS_DIR/run-base.sha" ] || git rev-parse HEAD > "$ORDERS_DIR/run-base.sha"
```

**2a. Create worktrees for this wave's sessions:**

First make sure no session of this wave left a branch or a worktree behind in
an earlier attempt — it may hold that session's work, so it is neither reused
nor deleted:
```bash
EXISTING=""
for N in {wave W session numbers}; do
  if git rev-parse -q --verify "refs/heads/trek/{slug}/session-$N" >/dev/null || [ -e "$WORKTREE_DIR/session-$N" ]; then
    EXISTING="$EXISTING trek/{slug}/session-$N"
  fi
done
if [ -n "$EXISTING" ]; then
  echo "Error: left by an earlier attempt:$EXISTING (branch or $WORKTREE_DIR/session-N)." >&2
  exit 1
fi
```

If it exits 1, stop and report (no Step 5, no Phase 8; nothing was created or
deleted): name each branch and worktree, and what the user can do — inspect it
(`git log HEAD..<branch>`, `git -C <worktree> status --short`), merge it by
hand, or delete it themselves once its work is not needed — then re-run.

Then, for each session N in this wave:
```bash
BRANCH_NAME="trek/{slug}/session-{N}"
WORKTREE_PATH="$WORKTREE_DIR/session-{N}"
GIT_OPTIONAL_LOCKS=0 git worktree add -b "$BRANCH_NAME" "$WORKTREE_PATH" HEAD
```

`GIT_OPTIONAL_LOCKS=0` disables `.git/index.lock` background polling races
during parallel worktree operations (research/02 R2; GH #47721).

If `git worktree add` fails, report its error and stop the wave: never delete a
branch to make room. Jump to Step 5 (it removes the worktrees this wave just
created, without force), then Phase 8.

Report:
```
Worktree created: session-{N} → {WORKTREE_PATH} (branch: {BRANCH_NAME})
```

**2a'. Copy gitignored project artifacts into each worktree (addresses
plugin-in-monorepo + gitignored-state topology):**

`git worktree add` clones HEAD only. The plugin's `.gitignore` excludes
`.claude/projects/`, so the project directory (brief.md, plan.md, research/)
is missing in the freshly-created worktree. Each session needs to read
`brief.md`, `plan.md`, and `research/*` from `${PROJECT_DIR}` to do real work.

Insert this block AFTER the worktree-creation loop and BEFORE the orders are
written (Step 2):

```bash
# zsh (the Bash tool runs the user's shell): an unmatched glob stays literal, as in bash.
[ -n "${ZSH_VERSION:-}" ] && setopt nonomatch
PROJECT_SOURCE="$(realpath "${PROJECT_DIR}")"
REPO_ROOT_REAL="$(realpath "${REPO_ROOT}")"
# Compute destination relpath: PROJECT_DIR relative to REPO_ROOT.
# This makes $wt/$PROJECT_REL valid regardless of whether the operator
# passed --project as relative (.claude/projects/...) or absolute.
# python3 + os.path.relpath is stdlib and portable - see the note below the
# block for why no realpath flag may be used here.
PROJECT_REL="$(python3 -c 'import os.path,sys; print(os.path.relpath(sys.argv[1], sys.argv[2]))' "$PROJECT_SOURCE" "$REPO_ROOT_REAL")"
case "$PROJECT_REL" in
  ""|..*)
    echo "Error: cannot derive a project relpath inside the repo ($PROJECT_SOURCE vs $REPO_ROOT_REAL)." >&2
    exit 1 ;;
esac
for wt in "$WORKTREE_DIR"/session-*; do
  [ -d "$wt" ] || continue
  mkdir -p "$wt/$PROJECT_REL"
  cp "$PROJECT_SOURCE"/brief.md "$wt/$PROJECT_REL/"
  cp "$PROJECT_SOURCE"/plan.md  "$wt/$PROJECT_REL/"
  if [ -d "$PROJECT_SOURCE/research" ]; then
    cp -r "$PROJECT_SOURCE/research" "$wt/$PROJECT_REL/"
  fi
done
```

Do not "improve" the relpath line into `realpath --relative-to=...`. That flag
is GNU coreutils only; BSD `realpath` (the macOS default) rejects it, and the
failure is **silent** — the command substitution leaves `PROJECT_REL` empty, so
`mkdir -p "$wt/"` and `cp ... "$wt//"` both succeed and drop `brief.md`/`plan.md`
at the worktree root, where no session looks for them. Measured on an
Intel Mac 2026-08-31: `realpath --relative-to=... ` → `realpath: illegal option
-- -`, while bare `realpath <path>` works; a whole wave ran with zero steps
executed. Both `realpath` calls above are bare path resolution, which BSD and
GNU handle identically; resolving both operands before the relpath is what keeps
it correct when one side goes through a symlink (macOS `/var` → `/private/var`).

Failure modes: an underivable relpath (empty, or outside the repo) aborts
before anything is copied — better a loud stop than files delivered where no
session reads them; any `cp` failure exits the wave non-zero, reported via
Step 5 cleanup. A project without `research/` is not a failure.
Source: brief Constraint 2.

### Step 2 — Write the session orders for wave W, then stop

```bash
(cd "$REPO_ROOT" && node "$VOYAGE_ROOT/lib/util/session-orders.mjs" write --plan "$PLAN_REL" --wave "{W}" --session-dir "$SESSION_DIR" --branch "$ORIGINAL_BRANCH")
```

`$PLAN_REL` is relative to the main checkout (Step 0; the tool refuses an
absolute path): each session resolves it inside its own worktree, which has the
same repo content from HEAD. The tool writes `$ORDERS_DIR/wave-{W}-session-{N}.md`
per session (naming its worktree, directory and progress file) and
`$ORDERS_DIR/wave.json` (`status: awaiting-sessions`, the plan path, the
sha256 of its content and the branch the wave is prepared on), and prints, per
session, the directory to open and the starter line
(`/trekexecute --session {N} $PLAN_REL`). A session's per-session `cwd:`
field in the Execution Strategy moves the directory it opens in to that
subdirectory of its worktree (plugin-in-monorepo layouts, brief Constraint 1,
Option B); default `.` is the worktree root.

Show the tool's output to the user verbatim, then report and **stop**:

```
Wave {W}: {N} session order(s) written in {ORDERS_DIR}. Awaiting sessions.
Open each session yourself in the directory its order names and give it the
starter line. When every session is done, run this same /trekexecute command
again here to merge the wave.
```

This run ends here. It writes no Phase 8 report: the plan is not finished, and
the orders are the hand-over.

### Step 3 — Collect wave W (a later run)

```bash
(cd "$REPO_ROOT" && node "$VOYAGE_ROOT/lib/util/session-orders.mjs" status --plan "$PLAN_REL" --wave "{W}" --session-dir "$SESSION_DIR" --branch "$ORIGINAL_BRANCH")
```

If it exits 1, stop and report its message, touching nothing (`wave.json`
stays). Either `wave.json` was written for another plan or another version of
this one — re-run with the plan (version) that wrote the wave, or abandon the
wave (the way out below) — or the main checkout is on another branch than the
wave was prepared on (Step 0's `ORIGINAL_BRANCH` of that run): the user
switches back to that branch and re-runs, so the wave never merges elsewhere.

The JSON names each session's progress file (the file `--session N` writes,
Phase 3), its raw `status`, and its `state`, exactly one of:
`completed`; `running` — no progress file yet, `pending`, `in-progress`,
`in_progress`, or any status not named here (an unknown status is never treated
as ended); `ended-bad` — `failed`, `stopped`, `partial`, `blocked` or
`unreadable`. `running` and `ended_bad` list the sessions in each state. Check
in this order:

- **Any `running` (checked FIRST):** a session is still open. Report which
  sessions are still running, with their raw status, point at their order files
  (`$ORDERS_DIR/wave-{W}-session-{N}.md`), and **stop** — even when another
  session in the wave already ended badly. Touch no worktree, no branch and not
  `wave.json`: no merge, no archive, no cleanup.
  **Way out of a stuck wave** (a session the user decided not to run): the user
  deletes `$ORDERS_DIR/wave.json` and re-runs. That run takes the fresh path,
  and Phase 2.55 Check 4 removes the wave's clean worktrees and merged branches
  without force and stops on everything that holds work, listing it to merge by
  hand or delete.
- No session is running. Before any worktree is removed (the failure branch's
  Step 5 and the merge below both remove them), archive every session's
  progress file:
  ```bash
  (cd "$REPO_ROOT" && node "$VOYAGE_ROOT/lib/util/session-orders.mjs" archive --plan "$PLAN_REL" --wave "{W}" --session-dir "$SESSION_DIR")
  ```
  It copies each one to `$ORDERS_DIR/wave-{W}-session-{N}.progress.json`. Step 5
  never deletes these copies; Step 6 and Phase 8 read them.
- **Any `ended-bad`:**
  ```
  Wave {W} FAILED: Session {N} ended {status}.
  Stopping — later waves depend on this wave.
  See its order: {ORDERS_DIR}/wave-{W}-session-{N}.md
  ```
  Do NOT merge. Do NOT prepare later waves. Jump to Step 5 (cleanup; it keeps
  every unmerged branch and every worktree git refuses to remove), then Phase 8.
- **`all_completed: true`:** continue with the merge. The executor asks
  nothing here, `gates_mode` or not. Each session's push and merge below run
  in one Bash call, and the guard asks the operator before it (a push always,
  a merge when the branch is main), so that answer is the one question for the
  merge (operator decision 2026-10-08; it was two when `--gates` added a pause
  of its own). A declined guard question means the call did not run: stop and
  report it like `MERGE_REFUSED`, keeping `wave.json`. In the permission mode
  that shows no prompts the guard does not ask: it refuses the push and the
  merge (exit 2, "no one to ask"). Then stop, keep `wave.json`, and report that
  the guard refused because no one can be asked, not that local changes are in
  the way: the operator runs this session's push-and-merge block by hand, or
  switches to a mode that asks and re-runs. A re-run in the same mode is
  refused again.

**Merge session branches back (SEQUENTIAL, one at a time):**

Return to the main worktree and make sure it is clean. While the sessions ran
the user may have kept working here, and Phase 2.55 (its Check 1) did not run
for this collect:
```bash
cd "$REPO_ROOT" || exit 1
if ! git diff --quiet || ! git diff --cached --quiet; then
  echo "Error: uncommitted changes in $REPO_ROOT. Commit or stash your changes in $REPO_ROOT, then re-run." >&2
  exit 1
fi
```

If it exits 1, stop and report its message: no merge, no cleanup, and keep
`wave.json`, so the re-run collects this wave again.

For each session N in the wave (in order), push BEFORE merge so the wave
branch survives even if cleanup races ahead (research/02 R3 — converts an
unrecoverable failure to a recoverable one). Push failure is non-fatal
(no remote, offline, etc.). Run the whole block as one Bash call, never split
into a push call and a merge call: the guard reads the call and asks once for
both.
```bash
GIT_OPTIONAL_LOCKS=0 git push origin "trek/{slug}/session-{N}" 2>/dev/null || true
if GIT_OPTIONAL_LOCKS=0 git merge --no-ff "trek/{slug}/session-{N}" \
     -m "merge: trekplan session {N} — {session-title}"; then
  echo "MERGED session {N}"
elif git rev-parse -q --verify MERGE_HEAD >/dev/null; then
  git diff --name-only --diff-filter=U
  git merge --abort
  echo "MERGE_CONFLICT session {N}"
  exit 1
else
  echo "MERGE_REFUSED session {N}"
  exit 1
fi
```

- `MERGED`: continue to the next session.
- `MERGE_REFUSED`: git refused to start the merge (no `MERGE_HEAD`; its message
  names the local changes or untracked files in the way). Stop and report
  `commit, stash or move your changes in {REPO_ROOT}, then re-run`: no Step 5, and
  keep `wave.json`. Sessions merged before it in this wave stay merged; the
  re-run merges them again as no-ops.
- `MERGE_CONFLICT`: a real conflict, already aborted. Report:
  ```
  Wave {W} MERGE CONFLICT: Session {N} branch conflicts with merged state.
  Conflicting files:
  {the files the block printed}

  Session {N} order: {ORDERS_DIR}/wave-{W}-session-{N}.md
  Aborting further merges. Sessions already merged in this wave are preserved.
  ```
  Mark remaining sessions as "merge-failed". Jump to Step 5 (it keeps every
  unmerged branch), then Phase 8.

**Record the merged wave, then remove its worktrees:**

After successful merge of all sessions in the wave, record it (Step 0 reads the
record, so a later run never prepares this wave again):
```bash
(cd "$REPO_ROOT" && node "$VOYAGE_ROOT/lib/util/session-orders.mjs" record-merged --plan "$PLAN_REL" --wave "{W}" --session-dir "$SESSION_DIR")
```

Then drop the wave marker and remove each session's worktree and merged branch,
never with force. A progress file still in a worktree is deleted only when it is
untracked and byte-identical to its archived copy (the archive is the record);
anything else in a worktree makes git refuse, and that worktree — and the branch
checked out in it — is kept and reported:
```bash
cd "$REPO_ROOT" || exit 1
rm -f "$ORDERS_DIR/wave.json"
for N in {wave W session numbers}; do
  WT="$WORKTREE_DIR/session-$N"
  ARCHIVED="$ORDERS_DIR/wave-{W}-session-$N.progress.json"
  P="$(sed -n 's/^- progress file: //p' "$ORDERS_DIR/wave-{W}-session-$N.md")"
  if [ -n "$P" ] && [ -f "$P" ] && cmp -s "$ARCHIVED" "$P" \
     && ! git -C "$WT" ls-files --error-unmatch "$P" >/dev/null 2>&1; then
    rm -f "$P"
  fi
  GIT_OPTIONAL_LOCKS=0 git worktree remove "$WT" 2>/dev/null || echo "KEPT worktree $WT"
  GIT_OPTIONAL_LOCKS=0 git branch -d "trek/{slug}/session-$N" >/dev/null 2>&1 || echo "KEPT branch trek/{slug}/session-$N"
done
GIT_OPTIONAL_LOCKS=0 git worktree prune
```

Report: `Wave {W}: {N} sessions merged.` plus every `KEPT` line, each with what
the user can do (inspect it with `git -C <path> status --short`, commit or move
what matters, then `git worktree remove <path>` and `git branch -d <branch>`).

**Next wave:** run Step 0's `next-wave` command. A number is the next `W`: go
back to Step 1 — this run prepares that wave's orders and stops again. `none`
(every wave merged): continue to Step 4.

### Step 4 — Run master verification

After all waves complete and merge successfully, run the plan's `## Verification`
section commands to verify the integrated result, through the same criteria
runner block as Phase 7 (`### trekplans — run the plan's ## Verification`),
from `$REPO_ROOT`. Record `plan_verification` and `end_to_end` exactly as
Phase 7 does (the same exit table, the same `exitCode` → `exit_code`
translation): the review (Phase 7.2) and the completion gate read them. Step 4
passed = the runner exited 0.

### Step 5 — Cleanup (ALWAYS runs when the run ends, even on failure)

This step MUST execute whenever this phase ends the run with a failure, a merge
conflict, or after the last wave — never while a wave is awaiting its sessions
(Step 2, and a Step 3 that finds a session `running` or a dirty or refused
merge, stop without it). It is the worktree equivalent of a `finally` block, and
it never forces: `git worktree remove` without force refuses a worktree with
modified or untracked files, `git branch -d` refuses an unmerged branch, and
whatever git refuses is kept and reported, never retried with force. From
`$ORDERS_DIR` it deletes only `wave.json`: the orders, the archived progress
copies and the merged-waves record stay until the main-merge gate's confirm
(Phase 8) clears them.

```bash
# zsh (the Bash tool runs the user's shell): an unmatched glob stays literal, as in bash.
[ -n "${ZSH_VERSION:-}" ] && setopt nonomatch
cd "$REPO_ROOT" || exit 1

# Remove worktrees git agrees are clean (GIT_OPTIONAL_LOCKS=0 to avoid lock-file races)
for wt in "$WORKTREE_DIR"/session-*; do
  [ -d "$wt" ] || continue
  GIT_OPTIONAL_LOCKS=0 git worktree remove "$wt" 2>/dev/null || echo "KEPT worktree $wt"
done
GIT_OPTIONAL_LOCKS=0 git worktree prune

# Delete merged session branches; every unmerged one is kept
git for-each-ref --format='%(refname:short)' "refs/heads/trek/{slug}/" | while read -r b; do
  GIT_OPTIONAL_LOCKS=0 git branch -d "$b" >/dev/null 2>&1 || echo "KEPT branch $b"
done

# Clean up the wave marker and an empty worktree directory
rm -f "$ORDERS_DIR/wave.json"
rmdir "$WORKTREE_DIR" 2>/dev/null || true
```

Report:
```
Cleanup: worktrees removed and merged branches deleted.
Kept (they hold work): {every KEPT line}
```

For every kept item, the report says what the user can do: a worktree —
inspect it (`git -C <path> status --short`), commit or move what matters, then
`git worktree remove <path>`; a branch — inspect it (`git log HEAD..<branch>`),
merge it by hand (`git merge --no-ff <branch>`), or delete it themselves once
its commits are not needed. A re-run stops at Phase 2.55 Check 4 until they are
dealt with.

### Step 6 — Aggregate results

Read every archived copy, `$ORDERS_DIR/wave-*-session-*.progress.json`, into an
aggregated report — never the worktree copies, which Steps 3 and 5 remove with
their worktrees (earlier waves' in earlier runs).

Keep the orders directory here, whatever the outcome. Only Phase 8's
main-merge gate clears it, on confirm, when `next-wave` said `none` (every wave
merged) and Step 4 passed. Until then the next run resumes at the lowest wave
not yet merged (Step 0), or re-runs Step 4 and returns to the gate when every
wave is merged.

When every wave is merged and Step 4 passed, the integrated result is checked
and reviewed like a single-session run, from the run's start point
(`session_start_sha` = the contents of `$ORDERS_DIR/run-base.sha`, Step 1):
Phase 7's architecture rules and plan-file sweep (K5, K6), then Phase 7.2
(Step 4 is its "run the thing"). Otherwise skip both. Then jump to Phase 8.

### --session N mode

When mode = `session N`:
1. Find session N in the Execution Strategy
2. Extract its step numbers (e.g., Steps: 4, 5, 6)
3. Extract its scope fence (Touch / Never touch lists)
4. Execute ONLY those steps, in order, using the single-session protocol (Phase 3→7)
5. Enforce the session's scope fence as if it were a session spec's scope fence
6. Report results for those steps only

This mode is what each session order's starter runs, in a session the user
opened in that order's worktree. It can also be used manually to re-run a
specific session.

When `--session N` runs inside a git worktree (as each session order sets up),
all git operations (add, commit) apply to the worktree's branch. The session does
not need to know it is in a worktree — git handles this transparently.

## Phase 3 — Progress file setup

The progress file location depends on whether `--project` is in use:

- **With `--project <dir>`:** progress lives at `{project_dir}/progress.json`.
- **Without `--project`:** progress lives at
  `{plan-dir}/.trekexecute-progress-{slug}.json`, where `{slug}` is the plan
  filename without extension.

**Session-scoped naming:** When `mode = session N`:
- With `--project`: `{project_dir}/progress-session-{N}.json`.
- Without `--project`: `{plan-dir}/.trekexecute-progress-{slug}-session-{N}.json`.

This prevents merge conflicts when parallel sessions each write their own
progress file.

### Progress file schema

```json
{
  "schema_version": "1",
  "plan": "{path}",
  "plan_type": "{plan | session-spec}",
  "plan_version": "{1.7 | 1.6 | legacy}",
  "started_at": "{ISO-8601}",
  "updated_at": "{ISO-8601}",
  "mode": "{execute | resume | step}",
  "total_steps": 0,
  "current_step": 0,
  "session_start_sha": null,
  "status": "{in_progress | completed | failed | stopped | partial}",
  "steps": {
    "1": { "status": "pending", "attempts": 0, "fix_rounds": 0, "start_sha": null, "report_path": null, "red_proof": null, "test_lock": null, "step_check": null, "regression": null, "error": null, "completed_at": null, "commit": null }
  },
  "iterations_remaining": 25,
  "plan_approval": null,
  "entry_condition_checked": false,
  "exit_condition_checked": false,
  "plan_verification": null,
  "end_to_end": null,
  "arch_rules": null,
  "scope_sweep": null,
  "simplify": null,
  "review": null,
  "decisions": [],
  "summary": null
}
```

**The step-loop fields (Handover 5, additive-optional).** Written by Phase 6;
a progress file without them still validates and resumes:

| Field | Written | Meaning |
|---|---|---|
| `session_start_sha` | Phase 3 | the commit the run started from; Phase 7.5 audits the whole run from it |
| `steps.{N}.start_sha` | Sub-step 0 | the commit the step started from; every check of the step reads `git diff {start_sha}` |
| `steps.{N}.report_path` | Sub-step 0 | the step's report file (helper rounds + the done line) |
| `steps.{N}.red_proof` | Sub-step B | `"proven" \| "rejected" \| "not-run"` — the exit of `red-proof.mjs` |
| `steps.{N}.test_lock` | Sub-steps B, G | `"locked" \| "released" \| "not-locked"` (K8) |
| `steps.{N}.fix_rounds` | Sub-step F | 0–5: 0 = passed its first control, 1–3 = fix rounds, 4 = sent up to the plan, 5 = sent up to the operator |
| `steps.{N}.attempts` | Sub-steps C, F | helpers launched for the step: 1 + the fix rounds that launched one |
| `end_to_end` | Phase 7 | `"verified" \| "not-verified"` (P9 (6)) |
| `decisions` | any phase | `[{step, decision, cost_if_wrong}]` — every call the executor made on its own (Phase 5.5) |

`progress-validator.mjs` rejects `fix_rounds` outside 0–5 (there is no sixth
round) and a `decisions` entry without its `cost_if_wrong`.

**The coupling fields (Handover 5, wave 2, additive-optional).** Each is a
contract CLI's exit said in words. A progress file without them still
validates and resumes; when present, `progress-validator.mjs` rejects any
other value:

| Field | Written | Values (exit 0 / 1 / 2) |
|---|---|---|
| `plan_approval` | Phase 1 (K2) | `"approved"`, or `"not-checked"` for a session spec |
| `steps.{N}.step_check` | Sub-step D4 (K9) | `"clean"` / `"findings"` / `"not-measured"` |
| `steps.{N}.regression` | Sub-step D4 (K10) | `"passed"` or `"absent"` (no field) / `"failed"` or `"unrunnable"` / `"not-run"` |
| `arch_rules` | Phase 7 (K5) | `"pass"` / `"violation"` / `"not-measured"` |
| `scope_sweep` | Phase 7 (K6) | `{status: "pass" \| "deviation" \| "not-measured", outside: [paths]}` |
| `simplify` | Phase 7.2 | `"applied"` \| `"clean"` \| `"reverted"` \| `"not-run"` |
| `review` | Phase 7.2 (K7) | `{round, path, gate_exit: 0 \| 1 \| 2, verdict}`; `round` counts reviews from 1 |

`"not-measured"` and `"not-run"` are never green: the final report says them
in those words, never "pass".

`plan_version` is the value Phase 2 parsed from the plan header (required by
`progress-validator.mjs`). The status words here are the validator's:
`PROGRESS_VALID_STATUSES` for the run, `PROGRESS_STEP_STATUSES` for a step.

**`plan_verification` (additive-optional):** written by Phase 7 when the input
is a trekplan — `{status, summary, failed_criteria}`, where `status` is
`"passed" | "failed" | "not-run"`. `null` for session specs (they have an exit
condition instead) and on early stop. Unknown keys are tolerated by
`progress-validator.mjs`, so a legacy progress file without it still validates.

**`iterations_remaining` (v1.7+, additive-optional):** the remaining
recovery/retry budget against the global hard cap (unit = **iterations**, per the
brief — token/cost budgeting is out of scope). Seeded to
`TREKEXECUTE_MAX_RECOVERY_ITERATIONS` (default 25) at start. **Single writer:** the
executor decrements it by 1 on **every recovery/retry iteration** — each fix
round of a step (Sub-step F), and each Phase 7.6 recovery dispatch. **Backfill-on-absent:**
when resuming a legacy `progress.json` that lacks the field, seed it to the cap
rather than hard-failing (forward/backward-compatible; shape-validated by
`progress-validator.mjs` — non-negative integer, never required-top). The field is
present in the spec at minimum — there is **no `(if wired)` conditional**.

### Mode-specific behavior

**Run start point (every mode that executes):** a fresh progress file records
`session_start_sha` = `git rev-parse HEAD` before step 1; a resumed one keeps
the value it has (a legacy file without it is backfilled with the parent of
the first completed step's `commit`, or `HEAD` when none is completed). Phase
7.5 audits the whole run from it — never from a step's own `start_sha`.

**mode = execute (fresh):**
- If a progress file exists with status `in_progress`, `failed`, `stopped` or `partial`: warn that
  `--resume` is available, then wait 3 seconds (`sleep 3`) and start fresh.
  This allows headless runs to proceed without blocking.
- Otherwise: create the progress file with all steps in `pending` status.

**mode = resume:**
- If no progress file exists: start from step 1 (same as fresh execute).
- If progress file exists: find the first step with status != `completed`.
  A legacy progress file may say `passed` for a finished step; treat it as `completed`.
  ```
  Resuming from step {N}. {M}/{total} steps already completed.
  ```

**mode = dry-run:**
- Do NOT create or modify the progress file.

**mode = step N:**
- Create the progress file if it does not exist.
- Only step N will be executed.

## Phase 4 — Entry condition check (session specs only)

**Skip for trekplans.** Skip in dry-run mode (report what would be checked instead).

Read the entry condition. Evaluate it:

- `"none"` or similar → pass immediately
- References git state (e.g., "git status clean") → run `git status --porcelain`
- References passing tests → run the specified command
- References a previous session → check `git log --oneline` for commit pattern

If the entry condition **fails**:
```
Entry condition FAILED: {condition text}
Reason: {what was checked, what was found}
Complete the prerequisite first, then re-run.
```
Update progress file with `status: "stopped"`. Stop execution.

**Also write `.session-state.local.json`** (Handover 7) with the same
`status: "stopped"` and `next_session_brief_path` pointing at the brief that
the failed entry-condition session was supposed to consume. This lets
`/trekcontinue` surface the stop in the next session. Use the same atomic
write pattern + validator check as Phase 2.55. On validator failure, warn
but do not block.

**Also write sibling `NEXT-SESSION-PROMPT.local.md`** with frontmatter
(`produced_by: trekexecute`, `produced_at: <ISO-8601>`,
`status: stopped`) — same combined ESM pattern as Phase 8 — so Phase 1.5
of `/trekcontinue` can compare project-dir and plugin-root candidates.

If the entry condition **passes**:
```
Entry condition: PASS
```
Update `entry_condition_checked: true` in the progress file.

## Phase 5 — Dry-run report (dry-run mode only)

**Only runs when mode = dry-run.** Produces a validation report, then stops.

```
## Dry Run Report: {filename}

**Type:** {plan | session-spec}
**Steps:** {N}

### Step Validation

| Step | Description | Verify | On failure | Checkpoint | Issues |
|------|-------------|--------|------------|------------|--------|
| 1 | {desc} | {cmd} | {action} | {msg} | {none / missing X} |

### File References

{For each file in Files: fields, check existence with Glob}
- {path}: EXISTS | NOT FOUND {(marked as new file) | (unexpected — may be missing)}

### Entry / Exit Conditions (session specs)

{What would be checked}

### Execution Preview (only when plan has Execution Strategy)

If `has_execution_strategy = true`, show a preview of multi-session orchestration:

```
**Sessions:** {S} across {W} waves

| Wave | Session | Steps | Depends on | Starter (the user runs it in a session they open) |
|------|---------|-------|------------|---------|
| 1 | Session 1: {title} | {nums} | none | `/trekexecute --session 1 {path}` |
| 1 | Session 2: {title} | {nums} | none | `/trekexecute --session 2 {path}` |
| 2 | Session 3: {title} | {nums} | S1, S2 | `/trekexecute --session 3 {path}` |
```

### Verdict

{READY | NEEDS ATTENTION — N issues found}
```

Stop after the dry-run report. Do not execute anything.

## Phase 5.5 — Autonomy: what stops a run, and the decision log

A run is long and mostly unattended. It does not stop to ask: what it decides
on its own it writes down, and it stops only for the four reasons below.

### Closed stop list

The list is **closed**: a run stops on these four classes and on nothing else.
Every stop names its class in the final report (Phase 8 `### Stops`).

1. **Something that cannot be undone.** A step or command whose effect cannot
   be reverted from git: deleting data outside the repo's tracked files, a
   migration against a live store, anything the plan marks irreversible — and
   a dirty main checkout before a multi-session wave (Phase 2.55 Check 1:
   merging would lose the uncommitted work).
2. **Something security-sensitive.** A command the executor denylist blocks
   (Phase 2.4, Sub-step D1), a write to a security-sensitive path (Hard
   rule 16), credentials or secrets in a diff.
3. **Something outside the working copy.** Merge to the main branch, push,
   tag, publish, a write outside the repository (Hard rule 15). The main-merge
   gate (Phase 8) is this class: it always pauses.
4. **A plan so broken that everything after it is guesswork.** The plan fails
   to parse, a ≥ 1.8 step has no `Test first:`, a step's own `On failure:
   escalate` fired (the plan's author declared that past this point is
   guesswork), a step went up the fix ladder (Sub-step F), the global
   iteration budget reached 0 — and the plan's own preconditions failing: an
   unmet entry condition (Phase 4), or the sandbox pre-flight exiting 77
   (Sub-step D1: the plan cannot be carried out where it runs). The review
   loop's stops are this class too (Phase 7.2): a BLOCK on the wave path,
   remediation steps that are not executable, the plan not approved again,
   and a BLOCK at the review cap.

Every stop the executor can make maps to one of these four; `stop_class` in
the summary is that number.

Not on the list, and therefore never a stop: a failing test (that is a fix
round), an ambiguity the plan leaves open (decide, and log it), a style
choice, a missing optional field.

### Decision log

Every decision the executor (or a helper, through its report) takes that the
plan did not dictate goes into progress `decisions` as one entry:
`{"step": N, "decision": "...", "cost_if_wrong": "..."}`. `cost_if_wrong` is
concrete: what has to be redone, by whom, how big — "one rename commit",
"step 4's API shape; steps 5–7 build on it". The final report prints the log
(Phase 8 `### Decisions taken`), so the operator reviews the calls instead of
being asked them one by one.

Borrowed: Superpowers subagent-driven-development (MIT) — the stop classes and
the log of choices made while unattended.

## Phase 6 — Step execution loop

The core execution phase. Runs for modes: `execute`, `resume`, `step`.

### Determine starting step

- **execute**: step 1
- **resume**: first step where status != `completed`.
  A legacy progress file may say `passed` for a finished step; treat it as `completed`.
- **step N**: step N only

### For each step

Update progress: `steps.{N}.status = "in_progress"`, `current_step = N`, `updated_at = now`.

```
--- Step {N}/{total}: {description} ---
```

One step at a time. Inside one session the steps run in order in one working
tree; parallel steps are the multi-session wave path (Phase 2.6), never two
helpers in one tree.

#### Sub-step 0 — Record the start point

Before anything touches the tree, record where the step begins:

```bash
git rev-parse HEAD
git status --porcelain
```

- `steps.{N}.start_sha` = the `HEAD` sha. Every later check of this step reads
  `git diff {start_sha}`: the review package is the diff from this recorded
  start point, not anything the helper says. On `--resume` of a step that
  already has a `start_sha`, keep it.
- `steps.{N}.report_path` = `{progress-dir}/steps/step-{N}.report.md` (create
  the directory). Every helper round of the step appends to it, and the done
  line lands in it (Sub-step G). Hand-over between the executor, the helper
  and the controller is in files: the plan, this report, the diff.
- A non-empty `git status --porcelain` (beyond Voyage's own progress and report
  files) means work the plan does not know about would mix into this step's
  diff. Not a stop (Phase 5.5): log it as a decision
  (`cost_if_wrong`: "the controller judges unrelated changes as part of step N")
  and name the paths in the report.

#### Sub-step A — Scope fence check (session specs only)

Before touching any file, verify that every file in the step's `Files:` field is
in the session spec's Touch list (or is a new file to create). If ANY file is in
the Never-touch list:

```
SCOPE VIOLATION: Step {N} requires {file} which is in the never-touch list.
Escalating — this step cannot be executed within this session's scope.
```

Treat this as an automatic `escalate`. Jump to the stop-and-report logic.

#### Sub-step B — Test first and proof of red

The step's test is written first, and a command proves it red — never the
model's word that "it failed first". This sub-step blocks: a step whose test
is not proven red at its start point and green at its result does not pass.

**How to write the test first is the `test-first` skill** (S2, Voyage plugin:
`voyage:test-first`): the build helper is told it by name (Sub-step C). The
skill is the advice; the gate below, `red-proof.mjs`, is the guarantee, and it
stays a command whatever the skill says.

**The step's test files** are the `File:` paths under its `Test first:`. The
plan template lists them apart from `Files:`, so everywhere below **the step's
scope = its `Files:` + its test files**: both are built, both are committed at
the checkpoint, and neither is a scope finding.

**The test command** is the step's `Verify:` command: the FIRST backticked
span of the field. Anything after it (expected output, notes) is description
and is not run. It must be ONE test-runner invocation without shell operators
(the allowlist of `lib/verification/criteria-runner.mjs`); the tools below
refuse anything else with exit 2, and from plan_version 1.8 the plan validator
already rejects such a step (`PLAN_STEP_VERIFY_NOT_RUNNABLE`).

1. **The helper proves red before it builds** (Sub-step C): it writes the test
   from `Test first:`, runs the gate
   `red-proof.mjs --red-only --base {start_sha} --cmd "{Verify}" --tests {test files, ONE comma-separated argument} --plan "{plan_path}" --step {N}`
   (the test must FAIL at the start point), locks the test files, and only then
   implements. A `tests_only: true` answer stops the helper before it builds
   (it does not rewrite the test); the executor's own run below then sends the
   step up to the plan.
2. **The executor proves it both ways after the helper returns:**
   ```bash
   node ${CLAUDE_PLUGIN_ROOT}/lib/verification/red-proof.mjs --base {start_sha} --cmd "{Verify command}" --tests {test files, ONE comma-separated argument} --plan "{plan_path}" --step {N} --json
   ```
   The test must FAIL against the start point and PASS against the result
   (the working tree), and a **control run** must PASS: the start-point copy
   with the step's whole change laid on top. The start point is a temp
   `git clone --shared` checked out at `start_sha` (a real git checkout), with
   the step's test files copied in and every gitignored top-level entry of the
   working tree (`node_modules`, `.venv`, …) linked in; `--link a,b` adds
   deeper dependency paths. A start point that fails for an environment reason
   fails the control too, so it is never read as red.

| Exit | `steps.{N}.red_proof` | Executor |
|------|-----------------------|----------|
| 0 | `"proven"` | continue |
| 1, `not-red-at-base`, `tests_only: true` | `"rejected"` | every file in the step's `Files:` is a test (the plan validator's `PLAN_STEP_TESTS_ONLY`, the same reading): the behaviour its tests cover already exists at the start point (an earlier step built it, or it was there before the plan), so the step can never be red and no rewrite of the test can fix that. The plan is what failed: the step goes straight up to the plan (Sub-step F, `fix_rounds = 4`, stop class 4), with no fix round — the planner moves the test into the step that builds the behaviour, or makes a test meant to pass from the start the `Regression:` of the step that changes the code |
| 1, `not-red-at-base`, otherwise | `"rejected"` | the test passes without the change, so the TEST is wrong: a finding for Sub-step F, and that fix round is the one exception to the lock — the executor releases the step's test lock for it, the fix helper rewrites the test, passes the `--red-only` gate and locks again. `tests_only: null` (the plan or the step could not be read) counts here too |
| 1, `not-green-at-result` | `"rejected"` | the change does not make the test pass: a finding for Sub-step F |
| 2 | `"not-run"` | never a pass and never proven. **plan_version ≥ 1.8:** when the reason is the command (the `Verify:` is not one test-runner invocation), the plan is what failed: the step goes straight up to the plan (Sub-step F, `fix_rounds = 4`, stop class 4); any other reason (a missing test file, an unresolvable start point, a control run that stays red) is a finding for Sub-step F. **Below 1.8:** a step with no `Test first:`, or whose `Verify:` is not a test-runner command, is tolerated as `"not-run"` — counted in the final report among the steps without proof of red, never called proven; any other reason is a finding |

The exit code is the verdict, the output text is not. `base.tap` (when the
runner prints TAP) says what the red was: `fail 1 of 1` on a node test file is
usually a load error, not a named failing test — say so in the step report.

**The test lock (K8).** After its red gate the helper runs
`node ${CLAUDE_PLUGIN_ROOT}/lib/util/test-lock.mjs lock --files {test files} --step {N} --cmd "{Verify command}"`;
from then on the guard refuses Write/Edit/NotebookEdit on those files, so the
code moves to meet the test and never the reverse. The executor reads
`node ${CLAUDE_PLUGIN_ROOT}/lib/util/test-lock.mjs status` and records
`steps.{N}.test_lock = "locked"` when it exits 0 and names the step's files.
If `lib/util/test-lock.mjs` is not in this plugin, record `"not-locked"` and
write "not locked: test-lock.mjs missing" in the step report — never silent.
The floor guard (Sub-step D3) still reads every test change in the diff. The
lock is released in Sub-step G, or when the run stops.

#### Sub-step C — Implement through one fresh helper

The executor does not write the step's code. **Launch** one fresh helper for
the step with the Agent tool:

Launch `subagent_type: "voyage:step-implementer"` with a short `description`
("step {N}: {title}") and a prompt that carries, as files and values, not as a
summary: the plan path, `plan_version`, the step number, the step's text
verbatim (every field, including `Interface in:`, `Interface out:` and
`Review focus:` when present), `start_sha`, `report_path`, `mode: build`, the
round label (`build`, or `fix round R`), `voyage_root: ${CLAUDE_PLUGIN_ROOT}`,
and the skill to work by: `skill: test-first` for a build round,
`skill: debugging` for a fix round (S2; Sub-steps B and F).

**A step at `fix_rounds` 5 is never built again** (Sub-step F): skip the
launch and run only the checks (B, D1, D2, D3, D4, E) on whatever the operator
changed. A step at `fix_rounds` 4 on `--resume` was re-planned: launch a fresh
`build` helper for the revised step.

- **Never pass the Agent tool's `name` parameter.** A named spawn becomes an
  `in_process_teammate`: it does the work, but its result never reaches this
  orchestrator (measured: named 0/5 returned, unnamed 3/3 —
  `docs/agent-return-channel-defect.md`). The same holds for the controller
  (Sub-step E).
- **Never pass `isolation`.** Measured 2026-10-06 (Claude Code 2.1.291): a
  worktree-isolated helper branched from the repository's default branch
  (`02f320f`), not from the executor's `HEAD` (`2c89a6b`), so it did not see
  the earlier steps. Only the operator's `worktree.baseRef: "head"` setting
  changes that, and a plugin cannot set it. The helper works in this tree,
  from the recorded `start_sha`.
- **Wait for the helper to finish** before anything else; when it runs in the
  background, its completion notification is the signal. Never start the next
  sub-step or step while a helper runs.
- `steps.{N}.attempts` += 1 for every helper launched for the step — this
  one, each fix round's, and the `build` helper after a re-plan. It is never
  reset, and every launch after a step's first also takes 1 from
  `iterations_remaining`, so the completion gate's reconciliation
  (`Σ (attempts − 1)`) holds across re-plans.

The helper's one-line answer is not evidence. After it returns:
1. The report at `report_path` must carry a NEW section for this round
   (`## Step {N} - {round label}`) with its `### Ran`, `### Saw` and
   `### Did NOT check`; earlier rounds' sections and verdicts stay. A missing
   section is a finding for Sub-step F (stale sections do not count).
2. Register EVERY new file so the diff and every check see it — not only the
   listed ones: for each path `git ls-files --others --exclude-standard`
   prints, run `git add --intent-to-add -- {path}` (stages nothing). A new file
   the step did not list is otherwise invisible to `git diff`, to the floor
   guard and to the controller. Voyage's own progress file and step reports
   are the one exception: never registered.
3. A changed or new path outside the step's scope (`Files:` + test files) is a
   scope finding (Hard rule 2) for the controller. The executor does not
   revert it on its own.

**Rules the helper is held to** (its agent file carries them; the controller
checks them in the diff): follow `Changes:` exactly — no improvising, no added
scope; touch only the step's scope (`Files:` + test files); read `Reuses:`
first; never weaken a test; never write a stub; never commit.

#### Sub-step D1 — Command verification

**Security check (mandatory):** Before running the Verify command, check it against
the executor security denylist. If the command matches ANY of these patterns,
**refuse to execute** — treat as `On failure: escalate` regardless of the plan's
On failure setting:

- `rm -rf` or `rm -fr` with any path
- `chmod 777` or `chmod -R 777`
- Pipe-to-shell: `curl ... | bash`, `wget ... | sh`, `base64 ... | bash`
- `eval` with variable expansion: `eval $VAR`, `eval $(cmd)`, `` eval `cmd` ``
- `mkfs`, `dd` writing to block devices (`/dev/sd*`, `/dev/nvme*`)
- `shutdown`, `reboot`, `halt`, `poweroff`
- Fork bomb patterns
- `crontab` writes, `/etc/cron*` modifications
- `kill -9 -1` or `pkill -9 -1` (kill all processes)
- `history -c` or truncating `~/.bash_history`

If matched:
1. Do NOT execute the command
2. Set step status = "failed"
3. Log: `SECURITY: Verify command blocked — matches executor denylist: {pattern name}`
4. Apply `On failure: escalate` regardless of the plan's On failure setting
5. Include in final report under a "Security blocks" section

If the command passes the security check, run it:

Run the `Verify:` command exactly as written, via Bash.

**Rules:**
- Always a fresh run — never trust prior results
- Exit code is the authoritative truth:
  - Exit 0 + expected output (if specified) = **PASS**
  - Exit non-zero = **FAIL** regardless of output text
  - Exit 0 but wrong output = **FAIL**

```
Verify: {command}
Result: {PASS | FAIL} (exit code {N})
{if FAIL}: Output (first 10 lines): {output}
```

**Step 0 sentinel:** if the Verify command exits `77` AND the step's manifest
has `sandbox_preflight: true`, do NOT treat as a normal failure. Set step
status = `blocked` and apply `On failure: escalate`. Skip D2 manifest
verification (nothing to verify for a read-only sandbox test). Commit none —
jump straight to Phase 7 with a structured "sandbox-blocked" reason.

If **PASS**: mark the step's test lock green, then proceed to Sub-step D2
(manifest verification). The mark is what lets the session wait for its
controller (Sub-step E) without the stop guard refusing every turn — the
test files stay locked against edits (operator decision 2026-10-08):

```bash
node ${CLAUDE_PLUGIN_ROOT}/lib/util/test-lock.mjs green
```

It runs the test command the helper stored in the lock (`lock --cmd`), never
one given now, and marks only on exit 0; a lock without a stored command is
never marked (exit 2), so the stop guard keeps holding as before; exit 1 (the test
did not pass this time) is a finding for Sub-step F like a FAIL, exit 2 (could
not run) is never green. A step that is `"not-locked"` skips it.
If **FAIL**: the failure output is a finding for Sub-step F; still run D2 and
D3, so the controller and the next fix round see every failure at once.

#### Sub-step D2 — Manifest verification

After the Verify command passes, verify the step's Manifest block. This is
the objective completion predicate: a step is not passed until its manifest
holds, regardless of Verify exit code.

**Checks to run (in order):**

1. **Expected paths exist:** for each `expected_paths` entry, verify the
   file exists in the repo. Count how many exist.
2. **min_file_count satisfied:** count from (1) must be ≥ `min_file_count`.
3. **Forbidden paths untouched:** for each `forbidden_paths` entry, run
   `git diff --name-only {start_sha} -- {path}` (since this step
   began). Any modified forbidden path = fail.
4. **Bash syntax check:** for each entry in `bash_syntax_check` AND any
   `.sh` file that appears in `git diff --name-only {start_sha}` (safety
   net for unlisted scripts), run `bash -n {path}`. Non-zero exit = fail.
5. **must_contain patterns:** for each `{path, pattern}` pair, run
   `grep -E -e "{pattern}" -- {path}` (`-e` and `--`: a pattern such as `--sep`
   is never read as an option). No match = fail.

**On manifest failure:**

```
Manifest verification FAIL for step {N}:
- {which check failed with detail}
```

A manifest failure is a finding for Sub-step F, exactly like a command
failure: it counts against the same fix rounds.

Either way, proceed to Sub-step D3 (floor guard).

Record per-step manifest audit result in progress file:
`steps.{N}.manifest_audit = "pass" | "fail"`,
`steps.{N}.manifest_drift = [{check: reason, ...}]` on fail.

#### Sub-step D3 — Floor guard

Read the step's diff for weakened tests — by a command:

```bash
node ${CLAUDE_PLUGIN_ROOT}/lib/verification/test-integrity.mjs --base {start_sha} --json
```

It reports a removed assert, a deleted or skipped test, a muted check
(`|| true`, continue-on-error, an inline lint/type suppression), a stub body
("not implemented") and a threshold loosened in the permissive direction.

| Exit | Meaning | Executor |
|------|---------|----------|
| 0 | clean | continue |
| 1 | findings | each finding goes to the controller (Sub-step E), which rules it `justified` only by quoting the plan line that asks for the change; every other finding is a `violation` |
| 2 | could not run | exit 2 is never green: "floor guard not run: {reason}" is a finding for Sub-step F, and the step cannot pass this round |

A finding is never dropped silently: the step report and the final report list
every one with its ruling.

#### Sub-step D4 — Step check and regression

Two more commands at step end, before the controller and before the
checkpoint (Sub-step G). Run them in one Bash call. The plugin root is resolved
first, as in Phase 7: an unresolved root would make `node` exit 1, which reads
as a finding when it is in fact a check that never ran.

```bash
# zsh (the Bash tool runs the user's shell): an unmatched glob stays literal, as in bash.
[ -n "${ZSH_VERSION:-}" ] && setopt nonomatch
VOYAGE_ROOT="${CLAUDE_PLUGIN_ROOT}"
case "$VOYAGE_ROOT" in
  /*) ;;
  *) VOYAGE_ROOT="$(ls -d "$HOME"/.claude/plugins/cache/*/voyage/[0-9]*/ 2>/dev/null \
       | awk -F/ '{ split($(NF-1), v, "."); printf "%09d%09d%09d %s\n", v[1], v[2], v[3], $(0) }' \
       | sort | tail -1 | cut -d' ' -f2-)"
     VOYAGE_ROOT="${VOYAGE_ROOT%/}" ;;
esac
CHECK_CWD="$(git rev-parse --show-toplevel 2>/dev/null || pwd)"
if [ ! -f "$VOYAGE_ROOT/lib/verification/step-check.mjs" ]; then
  echo "[voyage] step check not run - plugin root unresolved (exit 2)"
else
  node "$VOYAGE_ROOT/lib/verification/step-check.mjs" --cwd "$CHECK_CWD"; echo "step-check exit $?"
fi
if [ ! -f "$VOYAGE_ROOT/lib/verification/regression-check.mjs" ]; then
  echo "[voyage] regression not run - plugin root unresolved (exit 2)"
else
  node "$VOYAGE_ROOT/lib/verification/regression-check.mjs" --plan "{plan_path}" --step {N} --cwd "$CHECK_CWD" --json; echo "regression exit $?"
fi
```

**The step check (K9, P7)** runs the target repo's OWN formatters, linters and
type checkers over the step's changes (the diff against `HEAD` plus untracked
files: nothing of the step is committed yet) and reads the post-edit guard's
log. It installs nothing.

| Exit | `steps.{N}.step_check` | Executor |
|------|------------------------|----------|
| 0 | `"clean"` | continue |
| 1 | `"findings"` | every finding goes to the controller (Sub-step E) as a quality finding; the round does not pass |
| 2 | `"not-measured"` | the repo has no tool for these files, or one could not run. Write "step check: not measured — {reason}" in the step report. Not a finding, and never green: the final report counts the step among those whose step check was not measured |

**The regression (K10)** runs the step's `Regression:` command through the
criteria runner's two screens (the allowlist of test runners, then the
executor denylist), before the checkpoint:

`steps.{N}.regression` is the JSON's `progress_status`, copied as it is: the
CLI already speaks progress.json's words (`"blocked"` → `"unrunnable"`,
`"error"` → `"not-run"`).

| Exit | `steps.{N}.regression` | Executor |
|------|------------------------|----------|
| 0 | `"passed"`, or `"absent"` when the step has no `Regression:` (nothing new happens) | continue |
| 1 | `"failed"` (the suite went red) or `"unrunnable"` (not one allowlisted command; `"blocked"` by the denylist counts here too) | the step is not done: a finding for Sub-step F, exactly like a red Verify — it goes into the fix rounds, never to the checkpoint |
| 2 | `"not-run"` | the CLI could not run (plan unreadable, no such step): a finding for Sub-step F, never green |

#### Sub-step E — Control

**One controller, two verdicts.** After the mechanical checks (B, D1, D2, D3,
D4) — whatever they said — launch one controller with the Agent tool:
`subagent_type: "general-purpose"`, `model: "opus"`, no `name` (Sub-step C),
no `isolation`. It is a general helper with the prompt below, not a second
Voyage agent. The Agent tool sets no reasoning effort, so the controller runs
at the session's effort: run `/trekexecute` at effort `high` or above (the
standard). A session below `high` is a decision-log entry ("controller ran at
effort {level}"), never silent. It reads the diff, not the helper's summary: it is never given
the step report, and it judges what changed, not what the helper says changed.

The prompt (fill in every `{…}`; pass the mechanical results verbatim as JSON):

```text
You are the controller for step {N} of the plan {plan path}. You judge; you
change nothing: no Write, no Edit, no git command that writes.

Read the step's diff yourself: git diff {start_sha} --stat, then
git diff {start_sha}. The diff is the evidence. You are not given the
helper's report and must not look for it.

The step, verbatim:
{every field of the step}

Review focus from the plan (look hardest here): {Review focus, or "none"}

Mechanical results: proof of red {red-proof JSON}; Verify exit {code};
manifest {pass | fail + drift}; floor guard {test-integrity JSON};
step check {step-check JSON}; regression {regression-check JSON}.
Every step-check finding is a quality finding unless you show it is not in
this step's diff.

Give two verdicts:
- "spec": does the diff do what the step's Changes, Files and Interface say -
  no more, no less? Name any changed path outside Files.
- "quality": does the code hold - correctness, error handling, edge cases the
  step names, no stub, no weakened test, the repo's own patterns?
Rule every floor-guard finding: "justified: <the plan line, quoted>" or
"violation". List what you did not judge.

Answer with exactly one JSON block:
{"spec": "pass|fail", "quality": "pass|fail",
 "findings": [{"verdict": "spec|quality", "file": "...", "line": 0, "problem": "...", "fix": "..."}],
 "floor_guard": [{"kind": "...", "file": "...", "ruling": "justified: ... | violation"}],
 "not_judged": ["..."]}
```

Wait for the controller to finish. Parse its JSON block; an answer without a
parseable block is a failed control (a finding for Sub-step F), never a pass.
Append both verdicts, the findings and `not_judged` to the step report.

**The round passes** only when ALL hold: `red_proof` is `"proven"` (or, below
plan_version 1.8, the tolerated `"not-run"` of Sub-step B), Verify PASS,
manifest pass, every floor-guard finding ruled `justified` (and the guard
ran), `step_check` is `"clean"` or `"not-measured"` (Sub-step D4), `regression` is `"passed"` or `"absent"`,
`"spec": "pass"` and `"quality": "pass"`. Then go to Sub-step G.
Otherwise go to Sub-step F with every finding.

**Re-control after a fix** checks only what was fixed. A fresh controller gets
the previous round's verdicts, findings and floor-guard rulings, and the
round's own change — before the fix round the executor saves
`git diff {start_sha}` to `{report dir}/step-{N}-round-{R}.diff`, and afterwards
hands over `diff -u` of that file against the new `git diff {start_sha}`. It
answers in the SAME JSON block as above:
- per previous finding, fixed or not — a finding not fixed stays in
  `findings`; whether the round changed anything the findings did not name
  (that is a new finding);
- `"spec"` and `"quality"` for the step as a whole: the previous verdict
  carries over for every part the round did not touch, re-judged only where
  the round changed something;
- `floor_guard`: a finding identical (same kind, file and text) to one the
  previous round already ruled keeps that ruling; only new floor-guard
  findings are ruled.
It does not re-judge the rest of the step.

#### Sub-step F — Fix rounds

**How a fix helper finds the cause is the `debugging` skill** (S2, Voyage
plugin: `voyage:debugging`): it is told it by name (Sub-step C,
`skill: debugging`). The skill is the advice; the ladder below and the checks
that re-run after every round are the guarantee.

A failed round never loops sideways. **The fix rounds are capped at maximum 5 fix rounds per step, and they escalate upward** — to a fresh helper, then to
the plan, then to the operator. The executor does not improvise a new design,
and there is no ladder of cheaper models: every helper and every controller
runs `opus` (the step helper pins effort `high`; the controller follows the
session's effort, Sub-step E).

| `fix_rounds` | Goes to | What happens |
|---|---|---|
| 1, 2, 3 | a fresh helper | First `node ${CLAUDE_PLUGIN_ROOT}/lib/util/test-lock.mjs pending` (the step is no longer seen green; D1 marks it again). Launch `voyage:step-implementer` again (no `name`, no `isolation`), `mode: fix`, with the findings (file, line, problem, fix) and the mechanical failures. It fixes only those; the tests stay locked (except in a `not-red-at-base` round, Sub-step B). Then B (both ways), D1, D2, D3, D4 run again and a fresh controller re-controls only what was fixed (Sub-step E). `attempts` +1; `iterations_remaining` −1 |
| 4 | the plan | **After three failed fix rounds the question is the architecture, not a fourth fix.** The step goes back to planning (below). Sub-step B sends two reds here directly, with no fix round: a `"not-run"` caused by the `Verify:` command, and a `not-red-at-base` with `tests_only: true` (a step of only tests). Stop class 4 |
| 5 | the operator | A step already sent to the plan (`fix_rounds` 4) that fails its control again after re-planning goes to the operator. The executor never builds this step again: on a later `--resume` it only runs the checks (B, D1, D2, D3, D4, E) on whatever the operator changed. If they fail again the step stays at 5 — there is no sixth round, `fix_rounds` never exceeds 5 — and the run stops again. Stop class 4 |

**Back to planning** (`fix_rounds = 4`): save `git diff {start_sha}` to
`{report dir}/step-{N}-upward.diff` and write `{report dir}/step-{N}-upward.md`:
the step verbatim, every round's findings and verdicts, and the question for
the planner — which assumption in the step (its Changes, its Interface, its
test) makes it fail. Then stop: step `failed`, run `failed`, and tell the
operator to re-plan the step (`/trekplan` revises it) and run
`/trekexecute --resume`, which launches a fresh `build` helper for the revised
step (`attempts` +1, `iterations_remaining` −1) and keeps `fix_rounds` at 4. A step whose proof of red cannot run on a
≥ 1.8 plan because its `Verify:` is not one test-runner invocation goes here
directly (Sub-step B).

**The plan's `On failure:` clause** decides what happens around the ladder:

**`On failure: revert`** and **`On failure: retry`**
- Fix rounds 1–3 run as above; for `retry`, the clause's alternative approach
  is handed to the round-1 fix helper.
- When the step goes up (round 4 or 5), first save the upward files, then
  revert this step's changes (nothing of the step is committed yet):
  ```bash
  git checkout -- {the step's tracked files changed since start_sha}
  git rm --cached -q -- {the step's new files: registered with --intent-to-add since start_sha}
  ```
  The new files stay on disk, untracked, and `step-{N}-upward.md` names them —
  nothing the step made is deleted, and none of it is left registered.
  Record failure. **Do NOT proceed to next step.** Jump to Phase 7.5 (Phase 7
  runs only when every step passed).

**`On failure: skip`**
- Mark step as skipped at its first failed round, without fix rounds. Continue
  to next step.
  ```
  Step {N}: SKIPPED (non-critical per plan)
  ```
  Update `steps.{N}.status = "skipped"`.

**`On failure: escalate`**
- Stop at the first failed round, without fix rounds (stop class 4: the plan's
  author declared that past this point is guesswork).
  ```
  Step {N}: ESCALATED — requires human judgment
  ```
  Commit all completed work before stopping. Stage ONLY files from steps with
  `status: "completed"` in the progress file — collect their `Files:` fields. Never
  use `git add -A` (risks staging secrets, binaries, or unrelated work).
  ```bash
  git add {files from completed steps' Files: fields} && git commit -m "wip: trekexecute stopped at step {N} — escalation needed"
  ```
  Jump to Phase 7.5 (Phase 7 runs only when every step passed).

The same wip commit of completed work runs whenever a step goes up (round 4
or 5). Release the step's test lock before stopping
(`node ${CLAUDE_PLUGIN_ROOT}/lib/util/test-lock.mjs unlock`, `test_lock` =
`"released"`), so the operator and the planner can edit the test.

#### Sub-step G — Checkpoint, done line, unlock

1. **Checkpoint.** Stage the step's scope — its `Files:` and its test files,
   and only those, never `git add -A` — then run the `Checkpoint:` git commit
   command exactly as written in the plan. (The test files are listed apart
   from `Files:` in the plan; staging only `Files:` would leave the step's
   test uncommitted and charge it to the next step's diff.)
   If the commit fails (nothing to commit, etc.): warn but do NOT fail the
   step. The step's verification already passed — the commit is bookkeeping.
2. **The done line**, at the step's own commit. A step is done only when a
   script says so, and the script writes its line only when the test command
   exits 0:
   ```bash
   node ${CLAUDE_PLUGIN_ROOT}/lib/verification/done-line.mjs --step {N} --cmd "{Verify command}" --report {report_path}
   ```
   Exit 0 = `DONE step {N}: … exit 0 at {the checkpoint sha} …` appended to the
   step report. Confirm with
   `node ${CLAUDE_PLUGIN_ROOT}/lib/verification/done-line.mjs --check --step {N} --report {report_path} --commit {hash}`
   (exit 0 = the line names this step's commit). Neither the helper nor the
   executor ever types a DONE line.
   - Exit 1 = the test went red after the checkpoint (it passed in Sub-step E
     moments before: a flaky test or an order dependency). A finding for
     Sub-step F; the fix lands as a second commit with the same message, and
     Phase 7.5's commit count reports that extra commit as drift — said, not
     hidden.
   - Exit 2 = it could not run: never green — on a ≥ 1.8 plan that is the
     plan's `Verify:` (up to the plan, as in Sub-step B); below 1.8, a step
     whose `Verify:` is not a test-runner command records "no done line
     (Verify is not a test-runner command)" in its report and rests on
     Sub-step D1's exit code.
3. **Release the test lock**:
   `node ${CLAUDE_PLUGIN_ROOT}/lib/util/test-lock.mjs unlock` → `test_lock` =
   `"released"` (a step that was `"not-locked"` stays so).

```
Step {N}: PASS (committed: {hash})
```

**Commit-message-pattern check:** after the commit succeeds, read the HEAD
commit message (`git log -1 --pretty=%s`) and match it against the step's
`commit_message_pattern`. Mismatch does NOT fail the step (verification
already passed) but is recorded as `checkpoint_drift: {expected_pattern,
actual_message}` in the progress file. Phase 7.5 audit reports drift as
an advisory.

Update progress: `steps.{N}.status = "completed"`, `steps.{N}.commit = {hash}`,
`steps.{N}.completed_at = now`, `steps.{N}.manifest_audit = "pass"`.

### Step mode exit

If mode = `step N`: after completing step N (pass or fail), skip remaining steps
and jump to Phase 8 (final report).

## Phase 7 — Exit / verification check

**Runs only when all steps passed** (not on early stop). Which check runs
depends on what was executed:

| Input | Check |
|-------|-------|
| session spec | the `## Exit Condition` checklist |
| trekplan | the plan's `## Verification` criteria |

Phase 4's entry-condition skip for trekplans stands — a plan carries no entry
condition. The exit side is not symmetrical: a trekplan's `## Verification`
section is where the brief's success criteria land, and it used to run only on
the multi-session wave path (Phase 2.6 Step 4). A single-session run therefore
reported `completed` without ever executing the criteria it was measured
against. It no longer does.

### Session specs — exit condition checklist

Run each exit condition command from the `## Exit Condition` checklist:

```
Exit condition check:
- [ ] {command} → {PASS | FAIL}
- [ ] {command} → {PASS | FAIL}
```

If all pass: `exit_condition_checked: true` in progress file.
If any fail: record which failed. Include in final report.

### trekplans — run the plan's `## Verification`

Run the criteria runner over the plan file parsed in Phase 1
(`{plan_path}`). It parses the `## Verification` section, screens every command
through the plugin's own PreToolUse denylist before it reaches a shell, and
runs what survives — in the FOREGROUND, never backgrounded. (A command spawned
from node does not pass through the Bash tool, so that hook cannot fire by
itself; the runner invokes it over its documented stdin protocol instead of
carrying a second copy of the denylist.)

```bash
# Resolve the plugin root ONCE. ${CLAUDE_PLUGIN_ROOT} is substituted in this
# command's text but is EMPTY in the Bash tool's process env, and a bare
# `node ${CLAUDE_PLUGIN_ROOT}/lib/…` then runs `node /lib/…`, which exits 1 —
# indistinguishable from a criterion that failed.
# Only the literal form is substituted (a `:-` default is never replaced); the
# fallback takes the highest installed version under cache/<market>/voyage/.
# zsh (the Bash tool runs the user's shell): an unmatched glob stays literal, as in bash.
[ -n "${ZSH_VERSION:-}" ] && setopt nonomatch
VOYAGE_ROOT="${CLAUDE_PLUGIN_ROOT}"
case "$VOYAGE_ROOT" in
  /*) ;;
  *) VOYAGE_ROOT="$(ls -d "$HOME"/.claude/plugins/cache/*/voyage/[0-9]*/ 2>/dev/null \
       | awk -F/ '{ split($(NF-1), v, "."); printf "%09d%09d%09d %s\n", v[1], v[2], v[3], $(0) }' \
       | sort | tail -1 | cut -d' ' -f2-)"
     VOYAGE_ROOT="${VOYAGE_ROOT%/}" ;;
esac
if [ ! -f "$VOYAGE_ROOT/lib/verification/criteria-runner.mjs" ]; then
  echo "[voyage] plan verification could not run - plugin root unresolved (exit 2)."
  echo "         NOT a pass: report it and never emit result: completed."
  exit 2
fi

# The working tree the criteria run in. It is where every allowlisted command
# is executed and where a `bash tests/<script>.sh` criterion resolves, so it is
# resolved, never left to the process cwd - and a repo-less checkout falls back
# rather than passing "".
CRITERIA_CWD="$(git rev-parse --show-toplevel 2>/dev/null || pwd)"

node "$VOYAGE_ROOT/lib/verification/criteria-runner.mjs" --plan "{plan_path}" \
  --json --cwd "$CRITERIA_CWD"
```

The exit code is the verdict, and it is not advisory:

| Exit | Meaning | Executor |
|------|---------|----------|
| 0 | every criterion passed | `plan_verification.status = "passed"`; continue |
| 1 | a criterion failed, was blocked, or could not run (no command, or a command outside the allowlist of test runners) | `plan_verification.status = "failed"`; progress `status: "failed"` |
| 2 | the runner itself could not run | `plan_verification.status = "not-run"`; treated exactly like exit 1 |

A plan with no `## Verification` section exits 1 with
`error.code = NO_VERIFICATION_SECTION`. That is deliberate: a plan that
promises no end-to-end check cannot be reported as verified.

A plan whose `## Verification` section IS there but declares nothing the runner
can read exits 1 with `error.code = NO_CRITERIA` and a **source line**
(`{plan_path}:NN`). Say that in the report in plain words — "the plan's
`## Verification` at {plan_path}:NN declares no criterion the runner reads; the
plan is what failed here, not the run" — and name the two forms it does read
(a bullet whose first backticked span is the command; a shell-tagged fence).
Measured 2026-09-18: nine ordinary shapes of that section — an untagged fence,
a ```text fence, a table, `## Verification (acceptance)`, `### Verification` —
all parsed to zero criteria, and Phase 7 then forbade `result: completed`
without anyone being told that the format, not the code, was the problem.
Silence is what made an unreadable section indistinguishable from a broken run.

Record in the progress file (additive-optional; unknown keys are tolerated by
`progress-validator.mjs`, so a legacy progress file still validates):

- `plan_verification.status` — `"passed" | "failed" | "not-run"`
- `plan_verification.summary` — `{total, passed, failed, blocked, unrunnable}`
- `plan_verification.failed_criteria` — `[{label, command, exit_code}]`, one
  per runner result whose `status` is not `passed`. The runner's JSON says
  `exitCode`; progress says `exit_code`, so translate the key explicitly,
  `exitCode` → `exit_code`, and copy `null` as `null` (a blocked or
  unrunnable criterion never ran). Never write the runner's key into progress:
  `progress-validator.mjs` rejects it (`PROGRESS_FAILED_CRITERIA_KEY`, C15).

**A failing criterion FELLS the run.** It is not "recorded and included in the
final report": the executor MUST NOT emit `result: completed` while
`plan_verification.status != "passed"`. This is clause 2 of the stop-signal
contract below (Phase 7.5) — "the plan's Verify command(s) passed (exit 0)" —
now enforced on the single-session path and not only on the multi-session one.
Continue to Phase 7.5 either way: the manifest audit is independent, and a
verification failure must not hide a manifest drift.

### End to end — "run the thing" (P9 (6))

Tests passing is not the product working. Copy `end_to_end.status` from the
runner's JSON into `end_to_end` — the runner decides it, not this prose:

- `"verified"` — the verification passed and at least one passed criterion
  runs a step's `End-to-end:` command (`by: "end-to-end-field"`), or, the
  older form, says in its text that it runs the thing end to end (`end to
  end`, `end-to-end` or `run the thing`, any case; `by: "criterion-text"`);
- `"not-verified"` — otherwise, including a session spec and a plan whose
  verification did not pass.

`"not-verified"` is never green: the report says **not verified end to end**
in plain words, and the completion gate (Phase 7.5, clause 4) turns
`completed` into `partial`. The fix is in the plan — a criterion that runs the
built thing — not in the run. (A ≥ 1.8 plan cannot reach here with its
`End-to-end:` command missing from `## Verification`: the plan validator
rejects that as `PLAN_END_TO_END_NOT_VERIFIED`.)

### Architecture rules (K5) and the plan-file sweep (K6)

Two whole-run checks, for a trekplan and a session spec alike, in one Bash
call. Shell state does not survive between Bash calls, so the block resolves
the plugin root itself; an unresolved root prints exit 2, never a `node`
exit 1 that would read as a violation.

```bash
# zsh (the Bash tool runs the user's shell): an unmatched glob stays literal, as in bash.
[ -n "${ZSH_VERSION:-}" ] && setopt nonomatch
VOYAGE_ROOT="${CLAUDE_PLUGIN_ROOT}"
case "$VOYAGE_ROOT" in
  /*) ;;
  *) VOYAGE_ROOT="$(ls -d "$HOME"/.claude/plugins/cache/*/voyage/[0-9]*/ 2>/dev/null \
       | awk -F/ '{ split($(NF-1), v, "."); printf "%09d%09d%09d %s\n", v[1], v[2], v[3], $(0) }' \
       | sort | tail -1 | cut -d' ' -f2-)"
     VOYAGE_ROOT="${VOYAGE_ROOT%/}" ;;
esac
CHECK_CWD="$(git rev-parse --show-toplevel 2>/dev/null || pwd)"
if [ ! -f "$VOYAGE_ROOT/lib/verification/arch-rules.mjs" ]; then
  echo "[voyage] architecture rules not run - plugin root unresolved"; echo "arch-rules exit 2"
else
  node "$VOYAGE_ROOT/lib/verification/arch-rules.mjs" --repo "$CHECK_CWD"; echo "arch-rules exit $?"
fi
if [ ! -f "$VOYAGE_ROOT/lib/verification/plan-scope-sweep.mjs" ]; then
  echo "[voyage] plan-file sweep not run - plugin root unresolved"; echo "scope-sweep exit 2"
else
  node "$VOYAGE_ROOT/lib/verification/plan-scope-sweep.mjs" --plan "{plan_path}" --base "{session_start_sha}" --repo "$CHECK_CWD" \
    --process .claude/voyage/approvals.jsonl --process .claude/rules/voyage-review-lessons.md {--process CLAUDE.md, see below}; echo "scope-sweep exit $?"
fi
```

`{--process CLAUDE.md, see below}` is filled in, or left out, before the call:
it is passed only when every commit since the start point that touches
`CLAUDE.md` is a review-lessons commit (Phase 7.2), which
`git log --format=%s {session_start_sha}..HEAD -- CLAUDE.md` shows. A plan
step's own change to `CLAUDE.md` is never hidden by it.

**K5, the architecture rules (P3/P7)**, runs the target repo's OWN
architecture tool (dependency-cruiser, import-linter) and installs nothing:

| Exit | `arch_rules` | Executor |
|------|--------------|----------|
| 0 | `"pass"` | continue |
| 1 | `"violation"` | a finding in the final report with every violation; the completion gate turns `completed` into `partial` (clause 5) |
| 2 | `"not-measured"` | the repo has no such tool, or it could not run. The report says "architecture rules: not measured — {reason}", never "pass". Not a finding |

**K6, the plan-file sweep (P3)**, from the run's start point
(`session_start_sha`, Phase 3): every file the run changed must be named by
the plan (a step's `Files:`, its `Test first:` file, its manifest) or be a
process file. Voyage's own approval log and the review's project-memory file
(and its one-line `CLAUDE.md` pointer, as above) are passed as process files:
the run writes them, the plan does not name them.

| Exit | `scope_sweep` | Executor |
|------|---------------|----------|
| 0 | `{status: "pass", outside: []}` | continue |
| 1 | `{status: "deviation", outside: [...]}` | a finding in the final report with the file list (`outside`), never a silent warning; the completion gate turns `completed` into `partial` (clause 5). A deviation is cleared only by the plan naming the file in the same commit |
| 2 | `{status: "not-measured", outside: []}` | it could not run (not a git repo, an unknown start point). "plan-file sweep: not measured" in the report, never "pass" |

## Phase 7.2 — Simplify, review, verdict (P11)

**Runs only in the closing run, and only when Phase 7 ran** (every step
passed). The closing run is the one that ends a trekplan: a single-session
execute or resume of the whole plan, or the wave parent once every wave is
merged (Phase 2.6 Step 6). It is never a `--step N` run, a `--session N`
child or a session spec: those deliver a part, the review is of the whole
delivery, and a wave session's work is reviewed once the wave is merged
(Phase 8 leaves their result alone). It starts by itself after the last step,
never typed by the operator, in this order (Cherny's):

1. **run the thing** — Phase 7's `## Verification` and its `End-to-end:`
   criterion already ran (on the wave path: Step 4, which runs the same
   criteria runner). `end_to_end` must be `"verified"`; otherwise skip the rest
   of this phase (`review = {round: 1, path: null, gate_exit: 2, verdict: null}`:
   there is nothing proven to review) and go to Phase 7.5.
2. **`/simplify`** — Claude Code's bundled cleanup skill: four agents look at
   reuse, simplification, efficiency and altitude, and it applies the fixes.
   Measured 2026-10-08: the Skill tool starts it from the session. It reviews
   "the changed code": its upstream range, else `main...HEAD` or `HEAD~1`, plus
   uncommitted changes, or the PR, branch or path given as its argument. Give
   it the run as its argument:
   `Skill("simplify", args: "the changes of this run: git diff {session_start_sha}..HEAD — files: {git diff --name-only {session_start_sha} HEAD}")`.
   Wait for it to finish. Then, from the working tree:
   - **Outside the run's changed files:** every path it changed that is not
     in `git diff --name-only {session_start_sha} HEAD` is restored
     (`git checkout -- {path}`; a new file it made is removed from the index
     with `git rm --cached -q -- {path}` and left on disk), and listed in the
     final report. Nothing it did is dropped silently.
   - **Nothing changed:** `simplify = "clean"`.
   - **Changes:** run Phase 7's criteria runner again (same block, same exit
     table). Exit 0 → stage exactly the changed paths and commit them as
     `refactor: simplify pass (trekexecute)`; `simplify = "applied"`. Exit 1 or
     2 → restore every path it changed as above, `simplify = "reverted"`, and
     say why in the report: the cleanup broke the verification.
   - **It could not start** (the Skill tool refused, the skill is not there):
     `simplify = "not-run"`, with the reason. Not a stop: `/simplify` is a
     cleanup pass, not a gate. Continue.
3. **`/trekreview`** — Voyage's review gate: Claude Code's `/code-review` and
   `/security-review` as the engine, then Voyage's control against the brief,
   which is what stops. Start it through the Skill tool, with the run's range:
   `Skill("voyage:trekreview", args: "--project {project_dir} --since {session_start_sha}")`.
   A plugin command is a skill the model may start unless it carries
   `disable-model-invocation`, which `/trekreview` does not (the Claude Code
   skills documentation, read 2026-10-08). Follow its phases to the end in
   this session; its own questions (project-memory lines, one by one) are its
   own. **Without `--project`** there is no brief to review against:
   `review = {round: 1, path: null, gate_exit: 2, verdict: null}`, "review not
   run — no project directory", and the merge stays closed (Phase 8).
   **Its writes are committed.** `/trekreview` may have written approved
   project-memory lines (`.claude/rules/voyage-review-lessons.md`) and a
   one-line pointer in `CLAUDE.md`. Commit exactly those paths, when they
   changed, as `docs(voyage): review lessons (round {R})`: a process commit
   (Phase 7.5 step 3). Nothing the review wrote is left uncommitted for the
   next round's checks or for the merge.
4. **`verdict-gate.mjs`** — the review's verdict decides, as a command:
   ```bash
   node ${CLAUDE_PLUGIN_ROOT}/lib/review/verdict-gate.mjs --json "{project_dir}/review.md"
   ```
   Record `review = {round, path, gate_exit, verdict}`. Exit 0 (ALLOW/WARN) →
   Phase 7.5. Exit 2 (could not decide, or a reviewer or engine that did not
   run) → Phase 7.5 with the merge closed: never green. Exit 1 (BLOCK) → the
   loop below.

**A BLOCK is fixed by new plan steps, in a bounded loop.** The review writes
every BLOCKER as a numbered `### Step R<n>` under `## Remediation Steps`
(Handover 6: Files, Source finding, Test first, Verify, On failure). The fix is
those steps, not improvised. **Today the loop runs only for steps written as
runnable plan steps:** `Test first:` with its `File:` and `Verifies:`, and a
`Verify:` that is one allowlisted test command. A step in the review
template's own form (a prose `Test first:`, `Verify:` "re-run `/trekreview`")
does not pass step 3, and the run stops with "re-plan from the review" — the
usual outcome until a later order makes the template's steps runnable as
written. Every stop below is stop class 4 (Phase 5.5):
the run is `stopped`, and the merge stays closed.

0. **On the wave path there is no loop.** The plan's sha256 binds the
   merged-waves record (Phase 2.6), so new steps would strand the waves. Stop,
   and tell the operator to re-plan from the review: `/trekplan --brief
   {project_dir}/review.md` (Handover 6's remediation plan).
1. Copy the approved plan aside: `{report dir}/plan-approved-round-{R}.md`. It
   is the text the log approved, and it is how every stop below leaves the plan
   matching its approval.
2. Append each `### Step R<n>` to the plan's `## Implementation Plan` as the
   next numbered step (`### Step {total + 1}: …`, then +2, …), its fields
   copied as they are, never reworded. Add a `Checkpoint:`
   (`git commit -m "fix(review): {title} [{finding id, first 8}]"`), and on a
   plan_version ≥ 1.7 plan the manifest the legacy rule synthesizes
   (Phase 2: `expected_paths` ← its Files, …): a rule already in this file, not
   a new design. Earlier steps are never touched.
3. Check that the new steps can run, before anyone is asked. `--steps-from`
   holds the appended steps to the step rules (`Test first:` with its `File:`,
   one runnable `Verify:`) whatever the plan's version; below 1.8 nothing else
   would:
   ```bash
   node ${CLAUDE_PLUGIN_ROOT}/lib/validators/plan-validator.mjs --strict --json --steps-from {total + 1} "{plan_path}"
   ```
   Any exit but 0 (a `Verify:` that is not one test-runner call, a
   `Test first:` without its `File:`, …): restore the plan from the copy,
   save the appended text as `{report dir}/review-round-{R}-steps.md`, and
   stop. Say that the review's remediation steps are not executable as plan
   steps ({first error code}) and that the way on is a re-plan from the review,
   `/trekplan --brief {project_dir}/review.md`.
4. The plan changed, so its approval is stale (Phase 1). Ask for it again in
   one question, `AskUserQuestion`: **"The review blocked: {N} BLOCKER(s),
   added as steps {list}. Approve the plan as it is now?"** Options:
   **Approve** / **Not yet**. Check the answer with
   `approval-log.mjs answer` (stdin) exactly as `/trekplan` Phase 11 does;
   exit 0 → `approval-log.mjs append --kind plan --subject "{plan_path}" --sha256-of "{plan_path}"`
   and `artifact-commit.mjs --store {artifact_store} --artifact "{plan_path}" --message "docs(voyage): approve plan {slug}"`.
   This is an approval of new plan content, not an execution decision
   (Hard rule 1), and not a merge: no guard asks it.
5. **Approve** → add the new steps to progress (`steps.{M}` pending,
   `total_steps` raised), run Phase 6 for them (the same loop: helper, checks,
   controller, fix rounds), then Phase 7, then this phase again with
   `review.round` + 1. **Not yet**, or an answer that is not an approval →
   restore the plan from the copy, save the appended text as
   `{report dir}/review-round-{R}-steps.md`, and stop. A later `--resume`
   finds the plan as approved and comes back to this review.

**The cap:** `TREKEXECUTE_MAX_REVIEW_ROUNDS` reviews per run, default **3**
(the first review and two fix loops; env-overridable).
A BLOCK at the cap goes to the operator: stop, and the report names every
BLOCKER still open. Each loop also takes 1 from `iterations_remaining`, which
bounds it a second time (the completion gate's clause 3 counts it).

Borrowed: the order (run the thing, simplify, review) is Cherny's; a verdict in
a file that a command gates on, and the bounded fix-and-review loop, are
Kiro's `feature-pipeline` gate and Spec Kit's `/converge` loop (MIT); that no
finding is dropped silently is Superpowers' (MIT). Ideas only.

## Phase 7.5 — Manifest audit (independent)

**Runs for all modes except dry-run.** This is the last-line-of-defense
check: it ignores the executor's own per-step bookkeeping and re-verifies
session-wide state directly from the filesystem and git log. If the audit
disagrees with the executor's self-report, the audit wins.

This phase exists because agents can hallucinate completion. Phase 7.5
produces an independent truth based on objective state, not self-narrative.

**Steps:**

1. **Enumerate expected paths:** aggregate `expected_paths` across every
   step manifest (and the session_manifest, if present). Deduplicate.

2. **Filesystem check:** for each expected_path, confirm the file exists.

3. **Commit-count check:** count commits since session-start
   (`git rev-list --count {session_start_sha}..HEAD`). Expected count =
   number of steps with `status=completed` (excludes Step 0 if sandbox_preflight)
   + the run's own process commits, and only these: the simplify commit
   (`refactor: simplify pass (trekexecute)`, when `simplify = "applied"`), each
   review-lessons commit (`docs(voyage): review lessons (round R)`) and each
   plan approval the review loop committed (`docs(voyage): approve plan …`),
   all from Phase 7.2. Each is named in the audit, never folded in silently.
   (A remediation step's commit is a completed step like any other; the
   Phase 8 merge comes after the audit.)

4. **Commit-message pattern sweep:** walk `git log {session_start_sha}..HEAD` and
   confirm each commit matches one of the declared
   `commit_message_patterns` (in any order — order is advisory). The process
   commits of step 3 match their own fixed messages above.

5. **Bash syntax sweep:** for every `.sh` file in
   `git diff --name-only {session_start_sha} HEAD`, run `bash -n`. Collect failures.

6. **Forbidden-path sweep:** for each `scope_forbidden` entry, check
   `git diff --name-only {session_start_sha} HEAD -- {path}` is empty.

7. **Done-line sweep:** for every step with `status=completed` that carries a
   `report_path`, run
   `node ${CLAUDE_PLUGIN_ROOT}/lib/verification/done-line.mjs --check --step {N} --report {report_path} --commit {steps.N.commit}`
   (the line must name the step's own checkpoint commit).
   Exit 1 on a plan ≥ 1.8 = drift (`{check: "done-line", expected: "DONE step N", actual: "absent"}`);
   below 1.8 it is drift only when the step's report does not say why it has
   none (Sub-step G).

Compare the audit result against the executor's `progress.status`:

- **Audit pass + progress=completed:** status stays `completed`.
- **Audit fail + progress=completed:** OVERRIDE to `partial`. The executor
  believed it was done; the filesystem says otherwise. This is the Wave 1
  hallucination case — the audit is the defense.
- **Audit fail + progress=failed/stopped:** status stays as-is; drift is
  informational.

Record in progress file:
- `manifest_audit.status = "pass" | "drift"`
- `manifest_audit.drift_details = [{check, expected, actual}, ...]`

### Machine-verifiable completion gate (stop-signal contract)

> **Sealed inline so the termination rule survives even when the executor
> model is the very thing it constrains.**
>
> This is the `machine-verifiable completion gate` (the `stop-signal
> contract`): the executor may emit `result: completed` ONLY when BOTH hold —
>
> 1. **Objective predicate** — the **Phase 7.5** manifest audit (above) PASSED,
>    re-verified directly from the filesystem + git log, ignoring the executor's
>    own per-step bookkeeping. "The audit wins"; a self-reported `completed` over
>    a drifting audit is OVERRIDDEN to `partial` (Phase 7.5, `:1221`).
> 2. **Explicit stop-signal** — a signal *distinct from the executor's
>    self-assessment* is satisfied: the plan's Verify command(s) **passed (exit
>    0)** / lint clean / an explicit **DONE token emitted AFTER the Phase 7.5
>    audit ran** (never before, never in place of it). A transcript that merely
>    "feels done" is NOT a stop-signal — victory-declaration bias is the exact
>    failure mode this gate exists to defeat. For a trekplan this clause is
>    **Phase 7's** `plan_verification.status == "passed"` — a real exit code
>    from `lib/verification/criteria-runner.mjs`, on the single-session path as
>    well as the multi-session one. `"failed"` or `"not-run"` OVERRIDES
>    `completed` to `failed`, exactly as the audit-override does.
> 3. **Counter liveness (deterministic, defeats "never decremented")** — the gate
>    reconciles the budget counter against the ground-truth counters the Phase 7.5
>    audit already derives:
>    `iterations_remaining == TREKEXECUTE_MAX_RECOVERY_ITERATIONS − (recovery_depth + Σ steps.*.attempts-beyond-first + (review.round − 1))`
>    (the last term is 0 without a review; each review loop of Phase 7.2 takes 1).
>    A field left un-decremented (or tampered) fails this reconciliation and the
>    result is OVERRIDDEN `completed → partial`, exactly as the audit-override
>    already does (`:1221`). So the counter's liveness is auditable at the gate,
>    not merely asserted in prose.
> 4. **End to end** — for a trekplan, Phase 7's `end_to_end == "verified"`.
>    `"not-verified"` OVERRIDES `completed → partial` with the reason
>    "not verified end to end": tests that pass are not the thing running.
> 5. **Architecture and plan scope** — Phase 7's `arch_rules` is not
>    `"violation"` and `scope_sweep.status` is not `"deviation"`. Either one
>    OVERRIDES `completed → partial`, and the report lists the violations or
>    the files outside the plan. `"not-measured"` does not override, and it is
>    never reported as a pass.
>
> The review verdict (Phase 7.2) is decided after this gate, by the lock in
> Phase 8: in the closing run, a closed lock or a declined merge turns
> `completed` into `partial`, as a declined gate always has.
>
> Termination authority therefore rests on the deterministic audit + an
> objective stop-signal, never on the model's narrative. Native `/goal` (when
> capability-probed and wired) is an OPTIONAL accelerator only: transcript-only,
> it cannot run the real check, so it can never be the sole gate.

## Phase 7.6 — Recovery dispatch (multi-session parent context only)

**Preconditions:**
- This is the parent trekexecute invocation (not a child `--session N`)
- Phase 7.5 reported `drift`
- `recovery_depth < 2` (hard cap to prevent infinite loops)

**Skip otherwise.** Recovery in child context or at depth 2+ escalates to
the user for manual resolution.

**Synthesize a recovery session spec:**

1. Determine the missing step numbers from `manifest_audit.drift_details`
   (steps whose expected_paths are absent or whose commits are missing).
2. Read the original session spec. Copy only the missing steps (preserving
   their Manifest blocks) into a new file:
   `{output_dir}/session-{N}-recovery-{depth}.md`
3. Populate `## Recovery Metadata`:
   - `recovery_of: {original session spec path}`
   - `recovery_depth: {current depth + 1}`
   - `missing_steps: [N, M, ...]`
   - `entry_condition_override: "previous partial session committed at {sha}"`
   - `parent_progress_file: {path}`
4. Prepend the synthetic Step 0 pre-flight (same as normal session specs).
5. Set `recovery_dispatched = true` in parent progress file.

**Hand the recovery session over as an order (Voyage does not start it):**

Report the recovery spec as a session order and stop the run as `partial`:

```
Recovery order: session {N}, depth {depth}
Open a Claude Code session yourself in {REPO_ROOT} (the main checkout, which
holds the session's merged work) and give it:
    /trekexecute --session {N} {recovery spec path}
That session runs the missing steps and its own Phase 7.5 audit.
```

Nothing routes a later run of this command back to the recovery: the recovery
session's own audit is its check. It runs as a child, so if it still drifts it
stops `partial` and escalates to the user (the preconditions above) instead of
dispatching again. If Phase 7.5 drifts here while `recovery_depth` is already 2,
report instead:

```
RECOVERY EXHAUSTED: session {N} drifted after 2 recovery attempts.
Missing: {steps and details}
Status: partial (recovery_depth=2, escalated to user)
```

Do NOT dispatch a third recovery. Report to the user.

### Iteration caps + global recovery/retry budget

Every recovery/retry loop in this executor has a documented numeric bound.
These are **three distinct axes** — not one nested counter:

- **Per-step fix-round cap** — `fix_rounds ≤ 5`: maximum 5 fix rounds per step, escalating upward
  (rounds 1–3 fix with a fresh helper, 4 goes to the plan, 5 to the operator;
  Hard Rule 5 / Sub-step F). `attempts` counts the helpers a step launched.
  Bounds the rounds of a *single* step.
- **Per-session recovery cap** — `recovery_depth < 2` (Phase 7.6 hard cap).
  Bounds how deep recovery *dispatch* nests.
- **Global recovery/retry budget** — a new env-overridable constant
  `TREKEXECUTE_MAX_RECOVERY_ITERATIONS` (default **25**) — the aggregate ceiling
  on the **total count of recovery + retry iterations across the whole
  execution**. This is the case the two caps above do NOT bound: many steps each
  using up to 3 fix rounds can sum unbounded. It primarily backstops the **fix-round
  aggregate** (recovery dispatch is already hard-capped at 2). Reaching 0 stops
  the run (stop class 4: a plan that needs that many fixes is guesswork). Surfaced and
  enforced via the `iterations_remaining` counter (Phase 3 schema; decremented
  on every recovery/retry iteration; reconciled at the Phase 7.5 completion
  gate).

Default **25** is an independent value from the cap research (practitioner range
10–50; OWASP Agentic ASI08 financial-DoS), tuned down from the research ~50
starting point for a tighter backstop. Operators may override:
`TREKEXECUTE_MAX_RECOVERY_ITERATIONS=10 /trekexecute --project ...`. The
`effort=='low'` single-foreground-loop path and the wave path are both subject to
this aggregate ceiling; it is an execution-spec ceiling (enforced via the
`iterations_remaining` counter), not a code-loop edit.

## Phase 8 — Final report

Always produce a final report.

### Main-merge gate (MAIN_MERGE_GATE — always pauses)

Before writing the final progress + state files (and before any "merge to
main" prose), emit the `main-merge-gate` lifecycle event so observability
and operator tooling can see that the pipeline reached its terminal
boundary:

```bash
node ${CLAUDE_PLUGIN_ROOT}/lib/stats/event-emit.mjs --event main-merge-gate --payload - <<'JSON'
{"plan":"{plan-path}","wave_count":{wave-count}}
JSON
```

Fill in the placeholders yourself. The payload goes on stdin through a quoted
heredoc, so the shell expands nothing in it: not a variable (shell state from an
earlier Bash call does not survive, and an expanded variable is how this event
used to print `payload-not-json`), and not a quote character or `$(...)` in the
plan path. `{plan-path}` is the repo-relative plan path written as a JSON
string (escape a `"` or `\` in it). `{wave-count}` is the number of merged
waves, `1` on the single-session path.

Run each event call as its own command, never chained with `&&`. The writer
prints `{"written": true, ...}`. On `"written": false` (exit 1), print its
`reason` in one line and continue — an event failure never blocks the gate.

**The gate is a lock, not a question** (operator decision 2026-10-08). The
guard (`pre-bash-executor`) asks the operator before every merge into main and
every push, in auto mode too. When the executor first asked "ready to merge?"
itself, one merge cost two questions. Now the executor decides whether the
merge may run at all, and the guard's question is the one question.

**Only the closing run passes the lock** (Phase 7.2: a single-session run of
the whole plan, or the wave parent after the last wave). A `--session N`
child, a `--step N` run and a session spec deliver a part: they emit no gate
event, merge nothing, and their result is left as Phase 7.5 decided it
(`main_merge: "n/a"`). A wave session's `completed` must reach its parent as
`completed`, or Step 3 would read the wave as failed.

**1. The verdict.** Decide with the review's verdict as a command, never from
a summary:

```bash
node ${CLAUDE_PLUGIN_ROOT}/lib/review/verdict-gate.mjs --json "{review_path}"
```

`{review_path}` is `review.path` from Phase 7.2. No review (Phase 7.2 did not
run, ran without a project directory, or the run stopped before it) counts as
exit 2 without the call.

| Exit | Verdict | Merge |
|------|---------|-------|
| 0 | ALLOW / WARN | open, when the run's result is `completed` (Phase 7.5) |
| 1 | BLOCK | closed |
| 2 | not measured | closed: a review that could not decide is never green |

The merge runs only on exit 0 and a `completed` result. **Closed:** emit
`main-merge-declined` with the reason `review-block`, `review-not-measured` or
`run-not-completed`. Nothing is finalized: a `completed` result becomes
`partial` (`failed` and `stopped` stay), and the commits stay where they are
for review. Say in one line why it is closed and what opens it: the
BLOCKERs fixed through Phase 7.2's loop, a review that runs in full, or a run
that completes.

**2. Open: the merge, and the one question.** Find the run's branch and where
main is checked out, in a Bash call of its own:

```bash
git rev-parse --abbrev-ref HEAD
for b in main master; do git rev-parse -q --verify "refs/heads/$b" >/dev/null && echo "MAIN=$b" && break; done
git worktree list --porcelain
```

- **No `MAIN=` line** (the repo has neither branch): there is nothing to merge
  into. Emit `main-merge-declined` with the reason `no-main-branch`.
- **The run's branch IS main (or master):** there is nothing to merge; the
  commits are already on main. Emit `main-merge-approved` and say in the
  report that the review ran after the commits landed on main and could not
  hold them back: run on a branch when the review should gate the merge.
- **Another branch:** merge it into main in ONE Bash call, with the values
  written out as literals (the guard reads the command; it cannot follow a
  shell variable). When `git worktree list` shows main checked out in a
  worktree, merge there:
  ```bash
  if git -C "{main worktree path}" merge --no-ff "{run branch}" -m "merge: trekexecute {slug}"; then
    echo "MERGED"
  elif git -C "{main worktree path}" rev-parse -q --verify MERGE_HEAD >/dev/null; then
    git -C "{main worktree path}" diff --name-only --diff-filter=U
    git -C "{main worktree path}" merge --abort
    echo "MERGE_CONFLICT"
  else
    echo "MERGE_REFUSED"
  fi
  ```
  Otherwise switch this tree to main, and back to the run's branch on any
  failure:
  ```bash
  git switch "{main}" || { echo "MERGE_REFUSED"; exit 1; }
  if git merge --no-ff "{run branch}" -m "merge: trekexecute {slug}"; then
    echo "MERGED"
  elif git rev-parse -q --verify MERGE_HEAD >/dev/null; then
    git diff --name-only --diff-filter=U
    git merge --abort
    git switch "{run branch}"
    echo "MERGE_CONFLICT"
  else
    git switch "{run branch}"
    echo "MERGE_REFUSED"
  fi
  ```
  The guard answers "ask" before it runs (measured 2026-10-08/09 against
  both blocks: they ask, and a merge into another branch does not). The
  operator's answer there is the one question; the post-approval hook logs it
  as a `merge` approval (K2). The executor asks nothing before or after it. In
  the permission mode where Claude Code asks nothing, the guard refuses the
  call instead, because there is no one to ask (operator decision 2026-10-09).
  - `MERGED` → emit `main-merge-approved`.
  - The call did not run (the operator declined at the guard's question, or
    the guard refused it) → emit `main-merge-declined` with the reason
    `hold-for-review`; the run is `partial`, and the commits stay on the run's
    branch. When the guard refused, say so, and that the operator merges by
    hand.
  - `MERGE_CONFLICT` → list the conflicting files the block printed (the
    merge is already aborted), emit `main-merge-declined` with the reason
    `merge-conflict`; the run is `partial`. Never resolve a conflict with
    `-X ours/theirs`.
  - `MERGE_REFUSED` → git refused to start (local changes in the main tree, or
    untracked files in the way: its message says which). Emit
    `main-merge-declined` with the reason `merge-refused` and report git's
    message; the run is `partial`.

This gate is **always on**, regardless of `gates_mode`: a lock that every run
passes through, the one boundary that ALWAYS pauses on every run, either at
its lock or at the guard's question. It is the safety stop between completed
work and the merge that publishes the integrated result. On the multi-session
wave path the waves are already merged on the current branch, the branch the
run started on (Phase 2.6 Step 3, one guard question per session); when that
branch is not main, this gate merges it into main like a single-session run,
and the merged-waves record is kept until the confirm below.

On confirm:
(the merge ran, or there was nothing to merge)
```bash
node ${CLAUDE_PLUGIN_ROOT}/lib/stats/event-emit.mjs --event main-merge-approved --payload - <<'JSON'
{"plan":"{plan-path}"}
JSON
```

On the multi-session wave path (Phase 2.6), and only when `next-wave` said
`none` (every wave merged) and Step 4 passed, also clear the plan's orders
directory — orders, archived progress copies and the merged-waves record — so a
later plan with the same `{slug}` starts clean. This is the one place it is
cleared:
```bash
(cd "$REPO_ROOT" && node "$VOYAGE_ROOT/lib/util/session-orders.mjs" clear --session-dir "$SESSION_DIR")
```

On decline:
(a closed lock, or the guard's question declined, or a conflict)
```bash
node ${CLAUDE_PLUGIN_ROOT}/lib/stats/event-emit.mjs --event main-merge-declined --payload - <<'JSON'
{"plan":"{plan-path}","reason":"{reason}"}
JSON
```

The reason is one of the literal words above (`review-block`,
`review-not-measured`, `run-not-completed`, `no-main-branch`, `hold-for-review`,
`merge-conflict`, `merge-refused`), never the operator's free text (free text breaks the JSON).

On decline, nothing is cleared: the merged-waves record is kept.

**Recovery surface:** on the single-session path, if declined,
`--resume re-enters at the gate` — re-running
`/trekexecute --resume --project <dir>` skips the completed steps and returns
to the main-merge gate: the lock reads `review.md` again (a review fixed or
re-run in between counts), and when it opens, the guard asks again. On the
multi-session wave path,
re-run the same `/trekexecute` command instead, not `--resume` (Phase 2.5 runs
a `--resume` as a single session): the waves are already merged on the current
branch, the kept merged-waves record makes Step 0's `next-wave` say `none`,
master verification (Step 4) runs again, and the run returns to this gate. The
session branches (`trek/{slug}/session-N`) are merged and deleted unless
Step 3 or 5 kept them; Step 3 pushed each one before merging it (Hard Rule 19),
so where that push succeeded it also survives on the remote. Inspect the
integrated result with `git log` on the current branch.

### Progress + state-file writes

Update progress file: `status` to `completed`/`failed`/`stopped`/`partial`, `updated_at`, `summary`.
A sandbox-blocked run (Step 0 sentinel) writes run status `stopped`; its report
result is `blocked`.

**Also atomically write `.session-state.local.json`** (Handover 7) at this
convergence point — every successful, failed, stopped, or partial run that
reaches Phase 8 must produce or refresh the state file. Schema:

```json
{
  "schema_version": 1,
  "project": "{project_dir}",
  "next_session_brief_path": "{determined from Execution Strategy: next session's brief path, or current brief path if last session}",
  "next_session_label": "{label of next session from Execution Strategy, or 'Complete' if last}",
  "status": "{same as progress.json status — completed | failed | stopped | partial}",
  "updated_at": "{ISO-8601 now}"
}
```

Use `lib/util/atomic-write.mjs` (`atomicWriteJson`) — same crash-safety as
`progress.json`. Then verify: `node ${CLAUDE_PLUGIN_ROOT}/lib/validators/session-state-validator.mjs
--json {project_dir}/.session-state.local.json`. On validator failure, warn
to stderr but do NOT block — Phase 8 must always reach the final report.

**Also write sibling `NEXT-SESSION-PROMPT.local.md`** (Bug 3 frontmatter
contract — see `docs/HANDOVER-CONTRACTS.md` § Handover 7 Lifecycle) in the
project directory. The frontmatter MUST contain `produced_by: trekexecute`
and `produced_at: <ISO-8601>` so `/trekcontinue` Phase 1.5 can detect
producer drift between project-dir and plugin-root candidates. Use a single
ESM inline block so state-file + prompt-file writes succeed or fail together:

```bash
node --input-type=module -e "
import path from 'node:path';
import { writeFileSync } from 'node:fs';
import { atomicWriteJson } from '${CLAUDE_PLUGIN_ROOT}/lib/util/atomic-write.mjs';
const [, dir, briefPath, label, status] = process.argv;
const now = new Date().toISOString();
const stateObj = { schema_version: 1, project: dir, next_session_brief_path: briefPath, next_session_label: label, status, updated_at: now };
atomicWriteJson(path.join(dir, '.session-state.local.json'), stateObj);
const promptBody = '---\\nproduced_by: trekexecute\\nproduced_at: ' + now + '\\nproject: ' + dir + '\\nstatus: ' + status + '\\n---\\n\\n# ' + label + '\\n\\nResume via /trekcontinue.\\n';
writeFileSync(path.join(dir, 'NEXT-SESSION-PROMPT.local.md'), promptBody);
" '{project_dir}' '{next_session_brief_path}' '{next_session_label}' '{status}'
```

> Note: this block is a runtime template for Phase 8 orchestration; the
> `{project_dir}`/`{next_session_brief_path}`/`{next_session_label}`/`{status}`
> placeholders are filled in by the orchestrator at execution time. The
> leading `!` prefix that previously wrapped this block was removed because
> Claude Code's slash-command parser auto-executes `!`...` patterns at
> skill-load time, even inside bash code fences — see
> `docs/HANDOVER-CONTRACTS.md` § Handover 7 Lifecycle for context.

This single insertion covers every multi-session execution path that
converges here (Path A: successful single session, Path B: `--session N`
explicit, Path C: compaction-survival recovery, Path D: standard plan
completion). Phase 2.55 and Phase 4 cover the early-stop paths E1/E2.
Phase 2.3 (validate exit) and Phase 5 (dry-run) intentionally do not write
— neither path is resumable.

```
## Ultraexecute Local Complete

**Plan:** {path}
**Type:** {plan | session-spec}
**Mode:** {execute | resume | step N}
**Result:** {COMPLETED | FAILED at step N | STOPPED (escalation) | PARTIAL (N/total passed)}
**End to end:** {verified | not verified end to end}

### Step Results

| Step | Description | Result | Red proof | Fix rounds | Test lock | Done line | Attempts | Commit | Manifest |
|------|-------------|--------|-----------|------------|-----------|-----------|----------|--------|----------|
| 0 | Sandbox pre-flight | PASS | n/a | 0 | n/a | n/a | 1 | — | n/a |
| 1 | {desc} | PASS | proven | 0 | released | yes | 1 | abc1234 | pass |
| 2 | {desc} | FAIL | rejected | 4 (sent to the plan) | released | no | 4 | — | — |
| 3 | {desc} | — | — | 0 | — | — | 0 | — | — |

Steps without proof of red: {N} ({step numbers}; below plan_version 1.8 only)

### Controller verdicts

Per step and round: spec {pass | fail}, quality {pass | fail}, findings (file:line — problem),
floor-guard rulings, and what the controller did not judge. Report paths: {report_path per step}.

### Stops

{none — the run ended without a stop | the stop that ended the run, with its class from the
closed stop list (Phase 5.5): 1 cannot be undone · 2 security-sensitive · 3 outside the working
copy · 4 plan so broken that everything after it is guesswork, and the file or command that shows it}

### Decisions taken

| Step | Decision | Cost if wrong |
|------|----------|---------------|
| {N} | {what the executor or a helper decided that the plan did not dictate} | {what must be redone, by whom, how big} |

{none, when the plan dictated every call}

### Plan Verification (Phase 7, trekplans only)

- **Status:** {passed | failed | not-run | n/a}
- **Criteria:** {passed}/{total} passed, {failed} failed, {blocked} blocked, {unrunnable} not run
- **Failed criteria:** {label + command + exit code, one per line; empty when passed}

### Manifest Audit (Phase 7.5)

- **Status:** {pass | drift}
- **Drift details:** {enumerated; empty on pass}
- **Recovery dispatched:** {true | false}
- **Recovery depth:** {N}
- **Legacy plan:** {true | false}

### Checks and review (wave 2)

- **Plan approval (K2):** {approved | not checked (session spec)}
- **Step checks (K9):** {N clean · N with findings (fixed in rounds) · N not measured: steps {list}}
- **Regressions (K10):** {N passed · N absent · failed: steps {list}}
- **Architecture rules (K5):** {pass | violation: {each one} | not measured — {reason}}
- **Plan-file sweep (K6):** {pass | deviation — files outside the plan: {outside, one per line} | not measured — {reason}}
- **Simplify:** {applied (commit {hash}) | clean | reverted — {why} | not run — {reason}}{; edits outside the run restored: {paths}}
- **Review (K7):** round {R} of {cap} · {review_path} · verdict {ALLOW | WARN | BLOCK | none} · gate exit {0 | 1 | 2}{; open BLOCKERs: {ids}}
- **Merge into main:** {merged ({commit}) after the guard's question | nothing to merge (the run was on main) | closed — {reason} | declined at the guard's question | n/a — a part of the plan (`--session N`, `--step N`, a session spec)}

### Summary

- Passed: {N}/{total}
- Skipped: {N}
- Failed: {N}
- Not reached: {N}
- Blocked (sandbox): {N}

{if all passed + exit condition passed + plan verification passed + end to end verified}:
All steps completed. Exit condition: PASS. Plan verification: PASS. End to end: verified.

{if all passed but end_to_end = not-verified}:
All steps passed their checks, but the plan has no passing run-the-thing criterion:
not verified end to end. Result: PARTIAL.

{if failed/stopped}:
### Failure Details

Step {N}: {description}
On failure: {action}
Error: {error output, first 20 lines}
Attempts: {N}

### What Remains

{Numbered list of unexecuted steps}

To resume (single session): /trekexecute --resume {path}
To continue (multi-session waves): re-run the same /trekexecute command (not --resume)
```

**Result vocabulary (v1.7, strict):**
- `completed` — all steps passed AND Phase 7.5 manifest audit passed AND
  (for trekplans) Phase 7 plan verification passed
- `partial` — steps passed per executor but Phase 7.5 found drift, OR
  Phase 7.6 recovery incomplete, OR the run is not verified end to end
  (Phase 7, gate clause 4), OR an architecture violation or a file outside the
  plan (gate clause 5), OR — in the closing run — the main-merge lock stayed
  closed or the merge was declined (Phase 8)
- `blocked` — Step 0 sandbox pre-flight exited 77; no real work attempted
- `failed` — a step failed and went up the fix ladder (On failure revert/retry: round 4 to the plan, or 5 to the operator)
- `stopped` — On failure: escalate triggered, or another stop on the closed stop list (Phase 5.5)

**JSON summary block** (always at the end, machine-parseable):

```json
{
  "trekexecute_summary": {
    "plan": "{path}",
    "plan_type": "{plan | session-spec}",
    "plan_version": "{1.7 | 1.6 | legacy}",
    "result": "{completed | partial | blocked | failed | stopped}",
    "steps_total": 0,
    "steps_passed": 0,
    "steps_failed": 0,
    "steps_skipped": 0,
    "steps_not_reached": 0,
    "steps_blocked": 0,
    "failed_at_step": null,
    "exit_condition": "{pass | fail | skipped | n/a}",
    "plan_verification": "{passed | failed | not-run | n/a}",
    "manifest_audit": "{pass | drift | n/a}",
    "drift_details": [],
    "recovery_dispatched": false,
    "recovery_depth": 0,
    "iterations_remaining": 25,
    "legacy_plan": false,
    "progress_file": "{path}",
    "end_to_end": "{verified | not-verified | n/a}",
    "steps_without_red_proof": 0,
    "stop_class": "{none | 1 | 2 | 3 | 4}",
    "decisions": 0,
    "plan_approval": "{approved | not-checked}",
    "steps_check_not_measured": 0,
    "arch_rules": "{pass | violation | not-measured | n/a}",
    "scope_sweep": "{pass | deviation | not-measured | n/a}",
    "simplify": "{applied | clean | reverted | not-run | n/a}",
    "review_verdict": "{ALLOW | WARN | BLOCK | none}",
    "review_gate_exit": "{0 | 1 | 2}",
    "main_merge": "{merged | nothing-to-merge | closed | declined | n/a}"
  }
}
```

The `trekexecute_summary` key makes it grep-able in a session's output.

**Multi-session path (Phase 2.6).** Per-session results come from Step 6's
aggregate of the archived copies `$ORDERS_DIR/wave-*-session-*.progress.json`.
The report lists every worktree and `trek/{slug}/*` branch Steps 3 and 5 kept,
with what the user can do (Step 5). If the orders directory was kept (not every
wave merged, Step 4 did not pass, or the gate was declined), say so: the next
run resumes at the lowest wave not yet merged, or re-runs Step 4 and returns to
the gate, and the `clear` command in Step 0 starts the plan over from its first
wave instead.

## Phase 9 — Stats tracking

Append one record to `trekexecute-stats.jsonl` in the plugin data directory.
Run it exactly like this. The record goes on stdin, and the writer resolves
the directory: `CLAUDE_PLUGIN_DATA`, which the Bash tool env does not carry,
else the directory `scripts/yardstick.mjs` reads.

```bash
node ${CLAUDE_PLUGIN_ROOT}/lib/stats/stats-append.mjs trekexecute <<'JSON'
{
  "ts": "{ISO-8601}",
  "plan": "{filename only}",
  "plan_type": "{plan | session-spec}",
  "mode": "{execute | resume | dry-run | step}",
  "result": "{completed | failed | stopped | partial}",
  "steps_total": 0,
  "steps_passed": 0,
  "steps_failed": 0,
  "steps_skipped": 0,
  "failed_at_step": null
}
JSON
```

`steps_passed` counts the steps whose status is `completed`.

The writer prints `{"written": true, ...}`. On `"written": false` (exit 1),
print its `reason` in one line and continue. A stats failure never blocks the
workflow, but it is reported, not skipped silently.

## Profile (v4.1)

Accepts `--profile <name>` where `<name>` is `economy`, `balanced`, `premium`,
`fable`, or a custom profile under `voyage-profiles/`. Default: `premium`.

Resolution order (per `lib/profiles/resolver.mjs`):
1. `--profile` flag (source: `flag`)
2. `VOYAGE_PROFILE` env-var (source: `env`)
3. Inherited from `plan.md` frontmatter `profile:` field (source: `inheritance`)
4. `premium` default for v4.0-style plans without `profile:` (source: `default`)

The selected profile drives `phase_models.execute` (model for execution
orchestrator) and `parallel_agents` for wave-parallel sessions.

Examples:
```
/trekexecute --profile economy --project .claude/projects/2026-05-09-add-auth
VOYAGE_PROFILE=balanced /trekexecute --project ...
```

Stats records emit `profile`, `phase_models`, and `profile_source` per
Phase 9 record.

## Composition rule (v5.1)

Independent of the profile system. When `brief.md` carries
`phase_signals` (brief_version ≥ 2.1), each downstream phase resolves
effort + model as:

```
effort_for_phase = brief.phase_signals[<phase>]?.effort ?? 'standard'
model_for_phase  = brief.phase_signals[<phase>]?.model  ?? profile.phase_models[<phase>]
```

The brief signal wins per-phase when present; the profile fills any
gaps. Both fields are mechanically resolved by the single composed CLI,
invoked in Phase 2.4 alongside the sequencing-gate brief-validator call:

```bash
# v5.9 — composed phase-model resolution (brief > profile > default) for the
# execute phase. ONE call returns {model, source}, plus
# effort only when the brief's phase signal sets one; without it the phase
# runs at effort `standard` (no change). Captured as phase_signal_result.
# Append --profile {profile} when the operator passed --profile.
node ${CLAUDE_PLUGIN_ROOT}/lib/profiles/resolver.mjs --resolve-phase-model --phase execute --brief-path "{dir}/brief.md" [--profile {profile}] --json
```

`phase_signal_result.effort` (absent = `standard`) is consumed when picking the execution
strategy (gates auto-escalation, parallel-wave choice — see High-effort
behavior below). The resolver does NOT control the orchestrator's own
model — that is fixed at invocation time (command frontmatter omits
`model:`, so it follows the session model) and cannot be switched mid-turn.
`/trekexecute` spawns no swarm: one step helper at a time and one controller
(Hard Rule 10), and both run `opus` — the step agent's pin and the
controller's `model: "opus"` — so `phase_signal_result.model` still has no
spawn site here; it is returned for cross-command uniformity and stats.

For `/trekexecute` specifically: `effort == 'low'` activates `--gates open`
+ sequential-only execution (no worktree-isolated parallel waves — runs
all sessions in a single foreground loop). `effort == 'standard'` (or
absent) → no change (default execution strategy applies). `effort == 'high'`
activates the high-effort behavior documented under `### High-effort
behavior (v5.1.1)` below.

### Sequencing gate surface

When `/trekexecute --project <dir>` is invoked, ALWAYS run
`brief-validator.mjs --soft --json` against `{dir}/brief.md`. If
`BRIEF_V51_MISSING_SIGNALS` appears in `errors` (brief_version ≥ 2.1
without `phase_signals` or `phase_signals_partial: true`), halt with:
`Brief is brief_version 2.1 but does not carry phase_signals — re-run
/trekbrief to commit them (Phase 3.5).` Enforcement is validator-only;
commands surface, don't re-enforce.

### High-effort behavior (v5.1.1)

When `phase_signal_result.effort == 'high'` for the `execute` phase,
set `gates_mode = 'closed'` automatically (equivalent to passing
`--gates closed` on the command line). All autonomy boundaries become
operator-stopping points: manifest-audit FAIL halts immediately, the
main-merge gate stays a lock whose one question is the guard's (Phase 8), and Phase 7.5
manifest-audit runs in its strictest form (fails on ANY mismatch, not
just deltas above threshold). Operator explicit `--gates` flag still
wins over the brief signal — if the operator passes `--gates open` on
the command line while `phase_signal_result.effort == 'high'`, the
flag takes precedence and the override is logged:

```bash
node ${CLAUDE_PLUGIN_ROOT}/lib/stats/event-emit.mjs \
  --event gates_mode_flag_override --payload '{"flag":"--gates","signal_effort":"high"}'
```

The record lands in `trekexecute-stats.jsonl` in the plugin data directory as
`{ts, event, known_event, payload:{flag, signal_effort}}`. The two payload keys
stay in the jsonl; the OTel export allowlist drops them by omission. On
`"written": false` (exit 1), print its `reason` in one line and continue — the
override record never blocks the run.

Standard effort (or absent): use `gates_mode = 'adaptive'` (the
default). Low effort: `gates_mode = 'open'` plus sequential-only
execution (no parallel waves) — existing `--quick`-equivalent
code-path.

## Hard rules

1. **No AskUserQuestion for execution decisions.** All execution decisions come
   from the plan's On failure clauses. If the plan says escalate, stop and
   report — never ask. What the plan leaves open, the executor decides and
   writes into the decision log with its `cost_if_wrong`; it stops only on the
   closed stop list (Phase 5.5). The one question the executor asks itself is
   an approval, not an execution decision: the plan's approval after the
   review loop added remediation steps (Phase 7.2). A merge or a push is asked
   by the guard, and the executor never asks again (operator decision
   2026-10-08).

2. **No scope creep.** Only touch files listed in the step's `Files:` field.
   If a file outside the list seems to need changing, record it as a finding
   in the final report — do not touch it.

3. **Exit code is truth.** The Verify command's exit code is authoritative.
   Non-zero = FAIL regardless of output. Zero with wrong output = FAIL.

4. **Fresh verification.** Re-run the Verify command from scratch every time.
   Never trust cached or prior results.

5. **Fix rounds go up — maximum 5 fix rounds per step, escalating upward.**
   Rounds 1–3 are fixes by a fresh helper, round 4 sends the step back to
   planning, round 5 to the operator (Sub-step F). Never a fourth guess at the
   same level, never a cheaper model, never a loop.

6. **Never corrupt completed work.** Only revert files from the failing step.
   Never touch files from earlier passed steps.

7. **Checkpoint discipline.** Run the Checkpoint commit exactly as written.
   Do not combine, reorder, or skip checkpoints on passed steps.

8. **Scope fence enforcement.** For session specs: never modify files in the
   Never-touch list, regardless of what the Changes field says.

9. **Progress file is ground truth.** Resume uses the progress file, not git log.

10. **One fresh helper per plan step, one controller, nothing more.** The
    executor writes no product code: each step is built by a fresh
    `voyage:step-implementer` (Sub-step C) and judged by one controller, a
    general-purpose helper that reads the diff (Sub-step E).
    Helpers never start helpers: the step agent has no Agent tool, and the
    controller is told it changes nothing. Never the Agent tool's `name` (a named spawn's
    result never returns), never `isolation` (measured: wrong base). No
    TeamCreate — kept out via `disallowed-tools: TeamCreate`, since omission
    from `allowed-tools` alone leaves a tool callable (CC 2.1.152).

11. **Worktree isolation is mandatory for multi-session execution.** Every
    session order names its own git worktree. Never run two or more sessions
    in the same working directory. This rule has no exceptions.
    Sequential (single-session) execution does not require worktrees.

12. **Worktree cleanup always runs, and never with force.** Before producing
    the final report (Phase 8), remove the worktrees and merged session
    branches created during this execution, even if the run failed or was
    stopped — but only with `git worktree remove` without force and
    `git branch -d`. A worktree git refuses to remove or a branch it refuses to
    delete holds work: keep it, never retry with force, and list it in the
    final report with what the user can do (Phase 2.6 Step 5). Every unmerged
    `trek/{slug}/*` branch survives every failure path. The one exception to
    running cleanup: never while a wave awaits its sessions — a run that stops
    at Phase 2.6 Step 2, or at a Step 3 that finds a session `running` or a
    dirty or refused merge, writes no Phase 8 report and leaves every worktree
    and branch in place.

13. **Merge sequentially, abort on conflict.** After a parallel wave completes,
    merge each session's branch into the main branch one at a time with
    `--no-ff`. If any merge produces a conflict, run `git merge --abort`,
    report the conflicting files, and do not attempt further merges. Never use
    `--force` or `--strategy-option theirs/ours` to silently resolve conflicts.

14. **Verify command security check.** Before executing any `Verify:` or
    `Checkpoint:` command, check it against the executor security denylist
    (Sub-step D). If the command matches a blocked pattern, escalate
    immediately — do not execute, do not retry.

15. **No writing outside the repository.** During step execution, never write
    files outside the git repository root (`git rev-parse --show-toplevel`).
    Exception: `.claude/` paths for plans, progress files, and stats,
    AND `~/.claude/projects/*/memory/` paths for memory files when the
    step's manifest declares `memory_write: true`. The `memory_write: true`
    opt-in is a second gate: unauthorized memory writes still fail. This
    prevents escape-from-repo attacks where a plan step modifies home
    directory or system files, while permitting the narrow case of
    deliberate memory updates.

16. **No writing to security-sensitive paths.** Never write to `.git/hooks/`
    (git hook injection), `~/.ssh/`, `~/.aws/`, `~/.gnupg/`, `.env` files,
    shell configs (`~/.zshrc`, `~/.bashrc`, `~/.profile`), or
    `.claude/settings.json` / `.claude/hooks/` (infrastructure self-modification).

17. **Manifest is the completion predicate.** A step may not be marked passed
    if its manifest does not verify, regardless of the Verify command's exit
    code. The manifest is the objective contract — Verify is necessary but
    not sufficient. For v1.7+ plans: a Verify pass with a manifest fail sets
    step result to `failed` and triggers the On-failure clause. For legacy
    v1.6 plans: synthesized manifests apply with the same force, but
    `legacy_plan: true` is logged in progress.

18. **Last-activity rule + stop-signal.** The executor's final tool call before
    writing Phase 8 must be a manifest check (Phase 7.5 audit), never an arbitrary
    file review. This prevents the "hallucinated completion" failure mode
    where a transcript ends on an unrelated Read and the agent self-reports
    `completed` without verifying. If Phase 7.5 has not run, the executor
    may not emit `result: completed` under any circumstances. Beyond that:
    `result: completed` requires the **machine-verifiable completion gate**
    (the **stop-signal contract**, Phase 7.5) satisfied in full — Phase 7.5
    audit PASS **and** an objective stop-signal (Verify exit 0 / DONE token
    emitted AFTER the audit), never executor self-assessment alone.

19. **push-before-cleanup.** After successful `git merge --no-ff` of a wave
    branch, run `git push origin <branch>` BEFORE `git worktree remove` and
    `git branch -d`. Push failure is non-fatal (no remote, offline, etc.) —
    cleanup proceeds regardless. Rationale: this converts an unrecoverable
    failure (worktree removed, branch deleted, work lost) into a recoverable
    one (push succeeded, branch preserved on remote). Source: research/02 R3.
    The push and the merge go in one Bash call, so the guard asks once for
    both (Phase 2.6 Step 3).

20. **Three distinct iteration axes.** Per-step `fix_rounds` (≤5, upward),
    per-session `recovery_depth` (<2), and the global
    `TREKEXECUTE_MAX_RECOVERY_ITERATIONS` budget (default 25 — aggregate
    fix-round + recovery backstop) are independent bounds, not one nested
    counter. Every recovery/retry loop is bounded by at least one of them. See
    "Iteration caps + global recovery/retry budget".

21. **Never start Claude Code.** No `claude` CLI invocation, no Agent SDK, no
    background process that runs a session — not for waves, not for recovery,
    not for a test. Work that needs another session becomes a session order
    plus a starter line the user gives a session they open themselves
    (Phase 2.6, Phase 7.6).

22. **Proof, not word.** Red before green, an unweakened test and "done" are
    each a command's exit code — `red-proof.mjs`, `test-integrity.mjs`,
    `done-line.mjs` — never the helper's or the executor's statement. Exit 2
    from any of them ("could not run") is never green.

23. **The review is a gate, and the guard asks the one question.** A run
    starts only on a plan approved as it is now (K2, Phase 1). It ends with
    `/simplify`, `/trekreview` and the verdict gate, started by the executor
    itself (Phase 7.2). Exit 1 (BLOCK) or 2 (not measured) from the verdict
    gate keeps the merge into main closed (Phase 8). A BLOCKER is fixed by new
    numbered plan steps the operator approves, in a loop capped at
    `TREKEXECUTE_MAX_REVIEW_ROUNDS`, never by improvising. When the lock
    opens, the guard asks before the merge, and the executor never asks again.
    Exit 2 from the step check (K9), the architecture rules (K5) or the
    plan-file sweep (K6) is "not measured", never green.

## Credits

Every borrowing in this executor is named here, never silent. All sources are
MIT-licensed open source except Kiro (a closed product: only its published
documentation was read) and Cherny (public talks and posts). Read 2026-10-06;
pins and quotes in the local practice analysis.

- **Superpowers** — adapted from obra/superpowers@8ca22db (MIT, © 2025 Jesse
  Vincent): `subagent-driven-development` — a fresh helper per task, hand-over
  in files, a review package from a recorded start point, a reviewer between
  tasks, the stop classes and the decision log of an unattended run (P8, P4);
  `executing-plans/scripts/task-done` — the completion line appended only when
  the test command exits 0, here `done-line.mjs` (P9 (4));
  `systematic-debugging` — after three failed fixes, question the
  architecture (P9 (7)). Not borrowed: its ladder of cheaper models.
- **ai-native-sdlc** — bashebr/ai-native-sdlc@11fb8d7 (MIT): the helper's
  report contract, ran / saw / did NOT check (P8).
- **Kiro** (documentation only): the task runner takes the diff, not the
  agent's account of it, as the reviewer's input (P8). Its background daemon is
  not borrowed; only the step loop.
- **GitHub Spec Kit** (MIT), github/spec-kit@2e941fe: test-first as a rule,
  mechanized here as `red-proof.mjs` (P9 (1)).
- **agent-skills** — addyosmani/agent-skills@9d0c60d (MIT): the floor guard of
  constraint-driven development, as `test-integrity.mjs` (P9 (2)).
- **Cherny** (public primary sources): "run the thing" — a plan is verified
  end to end only by a criterion that runs what was built (P9 (6)).
- **Claude Code** itself: subagents for the helper and the controller; the
  `PreToolUse` guard behind the test lock (K8); `/simplify`, `/code-review` and
  `/security-review` as the review's engine, started through the Skill tool
  (P11).
- **The review at the end (P11, wave 2)** — Cherny: the order — run the
  thing, simplify, then review.
  Kiro (`feature-pipeline`, documentation only): the gate — a verdict in a file.
  Spec Kit (MIT, `/converge`): the bounded fix-and-review loop, its
  remediation steps appended and never reworded.
  Superpowers (MIT): nothing is dropped silently — what the controller did not
  judge, and every edit restored, is listed.
- **The checks wired in (P7, P3, P12)** — agent-skills (MIT): the step check's
  tiers and "not measured"; ai-native-sdlc (MIT): the sweep for files outside
  the plan and the guard + log; Superpowers (MIT): the four classes the guard
  asks about. Ideas only.