voyage/commands/trekreview.md

name	description	argument-hint	allowed-tools
trekreview	Independent post-hoc review of delivered code against the brief. Produces review.md with severity-tagged findings (BLOCKER/MAJOR/MINOR/SUGGESTION) per Handover 6 (review → plan).	--project <dir> [--since <ref>] [--quick] [--validate] [--dry-run]	Agent, Read, Glob, Grep, Write, Edit, Bash, AskUserQuestion, Skill

Ultrareview Local v1.0

Independent post-hoc review of code delivered by /trekexecute against the contract in brief.md. Produces review.md — a structured artifact with severity-tagged findings that /trekplan --brief review.md can consume as plan input (Handover 6).

Pipeline position:

/trekbrief     →  brief.md
/trekresearch  →  research/*.md
/trekplan      →  plan.md
/trekexecute   →  progress.json (+ commits)
/trekreview    →  review.md            (this command)

The review is independent: each reviewer runs without cross-feeding, and the coordinator applies BOUNDED operations only. Synthesis-level inference across files is forbidden in v1.0 (Judge Agent pattern).

The review is a gate (review_version 1.1, ordre 5). In this order: Claude Code's own /code-review and /security-review are the engine (Phase 4.7); Voyage's control against the brief runs after them and is the part that stops (Phase 5–6); the verdict is written in review.md and one command decides on it (lib/review/verdict-gate.mjs, Phase 8: 0 = ALLOW/WARN, 1 = BLOCK, 2 = could not decide, never green). No finding is struck for length. A finding class seen in two reviews becomes one proposal for the project's memory, approved line by line (Phase 8.7). Order credited to Boris Cherny's public workflow (engine → brief control); the gate to Kiro and Spec Kit — see docs/HANDOVER-CONTRACTS.md § Handover 6.

See agents/review-orchestrator.md for the canonical workflow this command executes inline.

Phase 1 — Parse mode and validate input

Parse the arguments with the shared arg-parser. Run it first, exactly like this, before anything else:

node ${CLAUDE_PLUGIN_ROOT}/lib/parsers/arg-parser.mjs --command trekreview -- $ARGUMENTS

It prints the parse as JSON on stdout. It also checks the required flag itself: on exit 1 it has printed the error and usage lines on stderr.

The parser recognizes these flags (see lib/parsers/arg-parser.mjs FLAG_SCHEMA trekreview entry):

Flag	Type	Purpose
--project <dir>	valued	Required. Path to trekplan project folder containing brief.md.
--since <ref>	valued	Optional. Override "before" SHA for the diff. Validated via git rev-parse --verify.
--quick	boolean	Skip the brief-conformance pass; run only the code-correctness reviewer; skip the coordinator's reasonableness filter.
--validate	boolean	Schema-only check on existing {project_dir}/review.md. No LLM calls.
--dry-run	boolean	Print the discovered scope and triage map. Skip writes.
--fg	boolean	No-op alias (foreground is default).
--workflow	boolean	(opt-in, NW2) Run Phase 5–6 on the bake-off-validated Workflow substrate (scripts/trekreview-armB.workflow.mjs) instead of the default prose Agent-tool path. Requires Claude Code 2.1.154+. Combines with --quick. See § Phase 5–6 via the Workflow substrate.

Resolution:

1. If the parser exits 1 (for example --project is missing), print its stderr lines verbatim, exactly as the parser wrote them, and stop. Do not compose the error message yourself.
2. Trim trailing slash from {dir}. Set:
   • project_dir = {dir}
   • brief_path = {dir}/brief.md
   • review_path = {dir}/review.md
3. If {dir} does not exist or {dir}/brief.md is missing:

   Error: project directory not initialized. Run /trekbrief first.
   Missing: {dir}/brief.md
   

Set mode:

• validate if --validate is set (overrides everything else; skip to Phase 8.5).
• dry-run if --dry-run is set.
• quick if --quick is set.
• default otherwise.

Set workflow_substrate (orthogonal to mode — a substrate choice, not a behavior mode):

• true if --workflow is set — Phase 5–6 run on the Workflow substrate (see the Phase 5 routing gate). The Workflow tool requires Claude Code 2.1.154+; if it is unavailable, fall back to the prose path and note the fallback in the Executive Summary.
• false otherwise. Default stays prose: the substrate is opt-in, so the lower portability floor of the prose path is preserved unless the operator opts in.

Phase 2 — Validate brief

Run the brief validator in soft mode — the brief is upstream context, not something this command produces, so partial grades are acceptable as long as the file is parseable:

node ${CLAUDE_PLUGIN_ROOT}/lib/validators/brief-validator.mjs --soft --json "{brief_path}"

# v5.9 — composed phase-model resolution (brief > profile > default) for the
# review phase. ONE call returns {effort, model, source}; captured as
# phase_signal_result and used in Phase 7 at the reviewer-launch site to
# inject the resolved model. Append --profile {profile} when the operator
# passed --profile.
node ${CLAUDE_PLUGIN_ROOT}/lib/profiles/resolver.mjs --resolve-phase-model --phase review --brief-path "{brief_path}" [--profile {profile}] --json

Read the JSON output. If valid: false AND any error has code BRIEF_MISSING_REQUIRED_FIELD or FRONTMATTER_PARSE_ERROR: stop and ask the user to re-run /trekbrief. Other soft errors become warnings in the review's Executive Summary.

Read the brief frontmatter. Capture for review.md:

• task → review frontmatter task
• slug → review frontmatter slug
• project_dir → review frontmatter project_dir (defaults to the CLI --project value when missing)

Phase 3 — Discover scope SHA range

Determine the "before" SHA that bounds the review:

1. --since <ref> override — if set, validate via:

   git rev-parse --verify "$since_ref"
   

   On failure: print Error: --since ref is not a valid git revision: {ref} and stop. Set before_sha = $(git rev-parse --verify "$since_ref").

2. Preferred path — read {project_dir}/progress.json if it exists. Extract session_start_sha. Validate it via git rev-parse --verify. Set before_sha = session_start_sha.

3. Fallback — no progress.json. Use the brief's mtime to find the most recent commit at or before the brief was written:

   brief_mtime=$(stat -f %m "{brief_path}")  # macOS; on Linux use stat -c %Y
   before_sha=$(git log --until="@$brief_mtime" -n 1 --format=%H)
   

   Emit a clear warning that gets surfaced in the review's Executive Summary: "scope_sha_start unavailable — falling back to brief mtime ({timestamp}). Coverage may include unrelated commits."

Compute the "after" SHA: after_sha=$(git rev-parse HEAD).

Capture working-tree changes (uncommitted at review time):

git diff --name-only "$before_sha".."$after_sha"
git diff --name-only HEAD       # uncommitted (annotated [uncommitted])

The combined file list is the review scope. Note that the [uncommitted] annotation is a brief-level contract — the brief's Assumptions section declares this is allowed; the review surfaces it explicitly in the Coverage table.

If the file count is 0, write a minimal review.md per the template: verdict: ALLOW, findings: [] (the empty list is the one inline form the parser reads — a bare findings: is null and fails validation), the required sections (## Executive Summary, ## Coverage, ## Declined to Judge with None. and Trimmed: 0, ## Remediation Summary), each saying "No diff between {before_sha} and {after_sha}; nothing to review.", and the trailing block {"verdict": "ALLOW", "counts": {"BLOCKER": 0, "MAJOR": 0, "MINOR": 0, "SUGGESTION": 0}, "allow_blocked_by": [], "findings": []} — without it the verdict gate cannot back the ALLOW and exits 2. There is nothing for the Phase 4.7 engine to review, so its absence does not withhold ALLOW here. Skip Phases 4–7. Continue to Phase 8 (validate + stats).

Phase 4 — Triage gate (deterministic path-pattern classifier)

The triage gate is deterministic — no LLM judgment. It classifies every file from Phase 3 into a treatment bucket:

Treatment	When
skip	Matches *.lock, *.svg, dist/**, build/**, node_modules/**, OR the file's first 3 lines contain a generated-file marker (@generated, Code generated by, DO NOT EDIT).
deep-review	Matches auth/**, crypto/**, **/security/**, hooks/**.
summary-only	Default treatment for everything else.

Hard refuse-with-suggestion gates — use AskUserQuestion:

if (reviewed_files_count > 100) → ask user
if (estimated_diff_tokens > 100000) → ask user

Token estimation: wc -c "$diff_file" / 4 (rough proxy). Use AskUserQuestion with the prompt:

The diff under review is large ({N} files / ~{T} tokens). Continue with the full scope, narrow with --since <closer-ref>, or stop?

Options:

1. Continue — proceed at this scope.
2. Narrow — print suggested git log --oneline {before}..HEAD so the user can pick a closer ref, then stop.
3. Stop — cancel.

Record the treatment for every file. Files marked skip MUST appear in the Coverage section of review.md — never silently drop them. Silent drops are COVERAGE_SILENT_SKIP (MAJOR) per the rule catalogue.

If mode == dry-run: print the triage map and exit.

Phase 4.5 — Run the brief's success-criteria checks

Skipped in quick mode (that mode does not launch brief-conformance-reviewer, so there is nobody to hand the result to) and in dry-run.

brief-conformance-reviewer is asked to decide whether each Success Criterion's verification command passes. Its tools are Read, Glob, Grep — it cannot run anything, and it stays that way: a reviewer that executes the code it reviews is not an independent reviewer. So THIS command runs the commands, and the reviewer judges the RESULT.

# 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 ${CLAUDE_PLUGIN_ROOT}/lib/…` then runs `node /lib/…`, which exits 1 —
# indistinguishable from a criterion that failed.
# Only the literal form is substituted (a `:-` default is never replaced); the
# fallback takes the highest installed version under cache/<market>/voyage/.
VOYAGE_ROOT="${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] success-criteria checks could not run - plugin root unresolved."
  echo "         NOT a pass: hand the reviewer NO results and say so."
  exit 2
fi

# Every command is screened twice before it reaches a shell: the runner's own
# ALLOWLIST of test runners (npm test, node --test, pytest, bash tests/<script>,
# a read-only git subcommand) reports anything else as NOT RUN, and the executor
# denylist (catastrophe) reports BLOCKED. Neither is ever run. Foreground only.
# The working tree the criteria run in - the same resolution trekexecute
# Phase 7 uses, so one criterion cannot resolve two ways in the two phases.
CRITERIA_CWD="$(git rev-parse --show-toplevel 2>/dev/null || pwd)"

node "$VOYAGE_ROOT/lib/verification/criteria-runner.mjs" \
  --brief "{brief_path}" --evidence --cwd "$CRITERIA_CWD"

Exit 0 means every criterion passed; exit 1 means at least one failed or was blocked by the executor denylist; a criterion with no command, or one outside the allowlist of test runners, is reported as NOT RUN; exit 2 means the runner could not run. The exit code does not stop the review — a failing criterion is exactly what the review exists to find. Capture stdout as sc_evidence_block.

If the runner exits 2 (or the root could not be resolved), set sc_evidence_block to a single line naming the failure and stating that no criterion was checked. An unrun check is never a pass, and the reviewer must be told which of the two it is looking at.

sc_evidence_block is pasted verbatim into the brief-conformance-reviewer prompt in Phase 5, and its summary line goes into the Coverage section of review.md. Do NOT summarise, re-word or re-judge it on the way — the block is built by formatCriteriaEvidence precisely so the orchestrator cannot narrate a pass that never happened.

Phase 4.7 — Claude Code's review engine (/code-review, /security-review)

Skipped in dry-run and validate. In quick mode only /code-review runs. Wrap, not a new engine: Claude Code's built-in reviews find the correctness and security defects; Voyage's brief control (Phase 5) runs after them and is what stops.

Verified in Claude Code's live documentation (2026-10-06):

• Claude may start /code-review itself (code-review.md: "Claude can start /code-review on its own", unconditionally from v2.1.246) and /security-review (skills.md: "A few built-in commands are also available through the Skill tool, including /init and /security-review").
• /code-review runs as a background subagent by default and its findings "arrive in your conversation when the review completes". It accepts a target such as a ref range.
• /security-review "Reviews the diff between your branch and origin's default branch" and "Needs an origin remote". The docs do not state its output format or whether it runs in the background.

Run both through the Skill tool, one after the other:

1. Skill("code-review", args: "high {before_sha}...{after_sha}") — the review's own SHA range from Phase 3. high is set explicitly; note in the Executive Summary that this also becomes the level later /code-review runs in this session reuse.
2. Skill("security-review") — no arguments; its base is fixed.

Never pass --fix, --comment, --post or ultra: a review never edits code, never posts anywhere, and never uploads the repo to a cloud review.

Wait for the findings. A background /code-review delivers its findings later in this conversation. Do not start Phase 6 before both engines have delivered or have been recorded as not run. For each engine that delivered, transcribe every finding — file, line (0 when none), the one-sentence summary, the failure scenario, the category if given (it decides the tier: simplification, efficiency, style and readability enter as MINOR), the fix the engine proposes (fix) only when its text states one — never write one the engine did not give — and a narrower catalogue rule_key only when one plainly fits — into {project_dir}/.review-engine-{code-review|security-review}.json as {"engine": "...", "findings": [...]}. Transcribe; never re-judge, merge or drop an engine finding on the way. Then convert it:

git diff --name-only "$before_sha".."$after_sha" > "{project_dir}/.review-scope.txt"
git diff --name-only HEAD >> "{project_dir}/.review-scope.txt"
node ${CLAUDE_PLUGIN_ROOT}/lib/review/engine-findings.mjs \
  --scope "{project_dir}/.review-scope.txt" --repo-root "$(git rev-parse --show-toplevel)" \
  "{project_dir}/.review-engine-code-review.json"

Exit 0 prints a reviewer payload (claude-code-review / claude-security-review) for Phase 6 plus out_of_scope: engine findings on files outside the review's SHA range (/security-review diffs against origin's default branch, which can be wider). Pass out_of_scope to the coordinator as well: each one is listed under ## Declined to Judge (engine:out-of-scope) and in Coverage — never silently dropped. One from /security-review is unverified and forbids ALLOW: its base is wider than this review and nobody here judged it. One from /code-review does not hold ALLOW back: that engine was given exactly this range, so a citation outside it is a remark about code this review did not change. Absolute paths under the repo root are made relative before the scope match (--repo-root). Exit 1 = the transcription is malformed, or the scope list is empty: fix it from the engine's own text (or the scope from Phase 3) and re-run; never feed a payload that did not pass. Exit 2 = could not run — record that engine as not run.

A "narrower" rule_key you transcribe is used only when its catalogue tier is at least the engine's own (MAJOR for /code-review, BLOCKER for /security-review); the adapter refuses to let a transcription lower an engine finding.

An engine that did not run (Claude Code older than v2.1.246, the Skill call refused, no origin remote, an ambiguous argument error, or no findings ever delivered) is recorded as not run with its reason. It stays in the expected reviewer set, so it forbids ALLOW (fail-closed); the Executive Summary's first sentence names it. An engine that ran and found nothing delivers an empty payload — that is a report, not an absence.

The two engine payloads are NOT shown to the Phase 5 reviewers: reviewers stay independent, and the coordinator is the only place the outputs meet.

Phase 5 — Launch parallel reviewers

Substrate routing (opt-in --workflow). When workflow_substrate == true, run Phases 5–6 via the Workflow substrate documented in § Phase 5–6 via the Workflow substrate (below Phase 6), then resume at Phase 7 with the returned {verdict, findings}. When false (the default), run the prose Agent-tool path described in the rest of this phase.

Launch two reviewer agents in parallel via the Agent tool — one message, multiple tool calls.

Never pass the Agent tool's name parameter — at this or any other spawn site in this command. name does not label a subagent, it changes its kind: the spawn is recorded as taskKind: "in_process_teammate" (spawnDepth: 0) instead of a subagent (spawnDepth: 1). A teammate's final assistant text is not a return value — it reaches the orchestrator only if the teammate itself calls SendMessage(to: "main"), and every agent in agents/ declares a tools: allowlist without SendMessage. The agent still runs and still produces correct output; the result is simply never delivered, so the phase presents as a hung agent that no re-prompting can revive. Measured 2026-08-17: named 0/5 returned, unnamed 3/3. Mechanism, denominators, and the on-disk recovery path: docs/agent-return-channel-defect.md.

Reviewers run independently. Do NOT pre-feed findings between them.

Agent	Mode-gated	Purpose
brief-conformance-reviewer	Skipped in quick	Trace each Success Criterion + Non-Goal to delivered code. Emits findings tagged with rule_keys from the conformance/scope categories.
code-correctness-reviewer	Always runs	7-dimension code review. Emits findings tagged with rule_keys from the correctness/security/maintenance/tests categories.

Each reviewer prompt includes:

• Diff context — the unified diff from Phase 3, truncated per file for files marked summary-only.
• Triage map — full file list with treatments. Reviewers must respect skip decisions.
• Brief path — {brief_path} (read on demand; do not inline).
• Rule catalogue — reference to lib/review/rule-catalogue.mjs.

brief-conformance-reviewer additionally receives sc_evidence_block from Phase 4.5, pasted verbatim — the command, exit code and first line of output for every Success Criterion. It is the ONLY evidence that agent has about whether a criterion's verification passes, because it cannot run one.

Collect each reviewer's trailing JSON block and validate it against the reviewer-output schema rather than merely parsing it. Run:

node ${CLAUDE_PLUGIN_ROOT}/lib/review/findings-schema.mjs --json --repo-root "$(git rev-parse --show-toplevel)" <reviewer-output-file>

validateReviewerOutput in lib/review/findings-schema.mjs extracts the last fenced json block, parses it, and schema-checks every finding (load-bearing fields: file, rule_key ∈ catalogue, severity ∈ enum, line integer ≥ 0). With --repo-root, a cited line past the end of a file that exists is FINDING_LINE_OUT_OF_RANGE: the reviewer cited the line in the diff, not in the file, and is re-asked like any other schema failure (the voyage-lekerepo trial, 2026-10-06, lost its only brief-anchored MAJOR that way). Parse failure and schema failure surface through the same stable error codes (FINDINGS_NO_JSON_BLOCK, FINDINGS_PARSE_ERROR, FINDING_*).

On any failure, re-ask that reviewer to re-emit a conforming JSON block only — quote the reported error codes/locations so the fix is targeted. Bounded retries: N=2. If the output still fails after 2 re-asks, stop and report which reviewer produced non-conforming output; do not feed unvalidated findings to the coordinator.

In quick mode, launch only code-correctness-reviewer. The Executive Summary will note the brief-conformance pass was skipped.

Reviewer accounting — every expected reviewer MUST report

Write down the expected reviewer set BEFORE the spawn: both reviewers in default mode, code-correctness-reviewer alone in quick mode — plus, in every mode, the Phase 4.7 engines that were due (claude-code-review, and claude-security-review outside quick). After the spawn, account for each one by name. An engine recorded as not run is passed on as missing, never left out of the set.

Zero findings from a silent reviewer is indistinguishable from zero findings from a clean diff — unless you check. A reviewer is accounted for only when it returned a payload that validated. Three ways it fails to:

Failure	Handling
Output fails the schema after the 2 bounded re-asks	STOP (already specified above)
Returned no final message at all	Re-ask that reviewer once. Still nothing → STOP.
Was never launched (spawn error, wrong mode)	STOP.

On STOP: name the reviewer and the failure, and do not proceed to Phase 6. Do not let the coordinator compute a verdict over a review one of whose reviewers never spoke — the count would be complete-looking and wrong. This is the same shape as the schema branch above ("do not feed unvalidated findings to the coordinator"), applied to the other two ways a reviewer can go missing.

A reviewer that ran but never delivered is most often the return-channel defect: check ~/.claude/projects/<proj>/<session>/subagents/agent-*.jsonl for its final assistant block before re-asking, and confirm no name parameter was passed at the spawn (see the warning at the top of this phase).

If you proceed anyway under an explicit operator instruction, pass the expected set to the coordinator as expectedReviewers so the missing reviewer at least forbids ALLOW (lib/review/coordinator-contract.mjs, missing_reviewers).

Phase 6 — Coordinator dedup + verdict

Launch review-coordinator (Agent tool) with the merged findings array from Phase 5 AND the Phase 4.7 engine payloads, plus the triage map, brief metadata, SHA range, the expected reviewer set (engines included), and each not-run engine with its reason.

The coordinator runs the 4-pass process documented in agents/review-coordinator.md:

1. Dedup by (file, line, rule_key) triplet.
2. HubSpot Judge filters — Succinctness, Accuracy, Actionability. Succinctness never removes a finding: only MINOR/SUGGESTION text is trimmed, and every trim is counted. A long BLOCKER or MAJOR keeps every character.
3. Cloudflare reasonableness — remove speculative or catalogue-violating findings (skipped in quick mode).
4. Verdict — BLOCK / WARN / ALLOW per the threshold table.

Fail-closed. Every removal in Pass 2 and Pass 3 is either dropped (the test refuted the finding as a claim about this codebase) or unverified (the finding was removed without its claim ever being settled). A non-empty unverified bucket forbids ALLOW; the verdict becomes WARN and the Executive Summary's first sentence must say why. The fail-closed rule never raises a verdict — it only withholds the clean one. Fate table, reason vocabulary, and the allow_blocked_by field: agents/review-coordinator.md §Suppression is two-valued, mirrored deterministically in lib/review/coordinator-contract.mjs.

The coordinator's output is the full review.md content — frontmatter (with the REQUIRED verdict:) + body sections (including ## Declined to Judge and, when there is a BLOCKER, ## Remediation Steps) + trailing JSON block. Do NOT re-run the reviewers based on the coordinator's output.

Phase 5–6 via the Workflow substrate (opt-in --workflow)

Runs only when workflow_substrate == true. This is the NW2 port: it expresses the SAME Phase 5–6 pipeline (parallel reviewers → triplet-dedup → coordinator verdict) as a single Workflow, reusing the NW1 findings schema. The S10 bake-off found it fidelity-equivalent to the prose path — see docs/T2-bakeoff-results.md (verdict POSITIVE: verdict-match 1.0, issue-coverage 100%, (file,rule_key) jaccard ≥ within-arm, tokens +4.4%). It stays opt-in, not the default, because the Workflow tool raises the consumer floor to Claude Code 2.1.154+ (outward-facing; the prose path keeps the lower floor).

Invoke the port via the Workflow tool with the Phase 1–4 output pinned into args:

Workflow({
  scriptPath: "${CLAUDE_PLUGIN_ROOT}/scripts/trekreview-armB.workflow.mjs",
  args: {
    briefPath: "{brief_path}",
    diffPath:  "{path to the unified diff file from Phase 3}",
    triage:    "{triage map as 'path → treatment' lines from Phase 4}",
    quick:     {true if mode == quick, else false},
    enginePayloads: [{the Phase 4.7 payloads from engine-findings.mjs}],
    engineNotRun:   [{each engine reviewer name recorded as not run}]
  }
})

A reviewer that returns nothing, or an engine listed in engineNotRun, forbids ALLOW on this path too (missing_reviewers in the result).

Contract (verified in S10 part B — follow exactly):

• Pass args as a JSON object. The script defensively re-parses a JSON string, but the object form is the contract.
• Reviewers are StructuredOutput-schema-forced — rule_key is enum-enforced at the tool layer (stronger than the prose path's post-hoc NW1 check), so there is no JSON.parse/re-ask dance.
• Recover the result from the RESULT_JSON:{…} line inside the workflow output logs. The script returns {verdict, findings, ...} AND logs it as that line; the notification's <result> may be truncated, so parse the logged line.
• The reviewer/coordinator agentTypes are namespaced inside the script (voyage:brief-conformance-reviewer, voyage:code-correctness-reviewer, voyage:review-coordinator).

Then continue at Phase 7 exactly as the prose path does — Phase 7 rendering, Phase 8 validation, and the operator gate are shared and substrate-independent (both paths return the same {verdict, findings} shape).

Known limitation (per bake-off §Posture, surfaced not hidden). Classifier interference was measured 0 at 9-agent concurrency in the session's default permission mode; an explicit auto/bypass-mode re-run was not performed (the permission mode is operator-set, not settable from within a session). trekreview's small fan-out showed 0 interference in S8 and S10. The large fan-out case (the trekplan swarm) is out of NW2 scope.

Phase 7 — Write review.md

Write the coordinator's output verbatim to:

{project_dir}/review.md

Create parent directories if they do not exist. Atomic write pattern: write to a temp file, then rename.

Then compute the finding ids — the coordinator has no shell and writes @@ID_<n>@@ placeholders (agents/review-coordinator.md, IDs are computed by code):

node ${CLAUDE_PLUGIN_ROOT}/lib/review/fill-finding-ids.mjs {project_dir}/review.md

Exit 0 = every placeholder filled (or none were left); 1 = a placeholder with no finding behind it, or a JSON id that is not the computed one — re-ask the coordinator once with the errors quoted, then stop and report; 2 = could not run (no JSON block) — stop. Never fill an id by hand. The frontmatter findings: field must use block-style YAML (one ID per line, - prefix). The parser at lib/util/frontmatter.mjs does not support flow-style arrays.

The verdict is in the file (K7). The frontmatter carries verdict: ALLOW | WARN | BLOCK, equal to the trailing JSON block's verdict. It is required at write time; a review without it fails Phase 8.

A BLOCKER is written as a plan step. For every BLOCKER the body carries, under ## Remediation Steps, one numbered step ### Step R<n>: <imperative action> with **Files:**, **Source finding:** <40-char id>, **Test first:** (a test that reproduces the finding and fails today), **Verify:** (the command that proves it fixed; default: re-run /trekreview and the finding is absent) and **On failure:** escalate. Handover 6 can append these to a plan without rewording them; earlier steps are never rewritten.

If mode == dry-run: skip the write; print the would-be path and the first 60 lines of the rendered output.

Phase 8 — Validate output + stats

Run the strict validator:

node ${CLAUDE_PLUGIN_ROOT}/lib/validators/review-validator.mjs --json "{review_path}"

If validation fails:

• For repairable errors (missing required body section, malformed finding-ID, REVIEW_VERSION_FORMAT warning): repair in place — re-emit the missing section, recompute the finding-ID, fix the version string. Re-validate.
• REVIEW_MISSING_VERDICT / REVIEW_MISSING_REMEDIATION_STEP: repair from the coordinator's own output — copy the JSON block's verdict into the frontmatter; write the missing ### Step R<n> from that BLOCKER's recommended_action, file and id. Never invent a verdict the JSON block does not carry. Re-validate.
• For unrepairable errors (REVIEW_WRONG_TYPE, malformed frontmatter): stop and ask the user to re-run; do not silently produce an invalid review.md.

Decide on the verdict with the gate (K7). Once the validator passes:

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

Exit 0 = ALLOW or WARN; exit 1 = BLOCK; exit 2 = the gate could not decide (missing verdict, a verdict the file contradicts — in its JSON block, its ## Findings (BLOCKER) section or its finding-id list — a JSON block that is not the last fence or has the wrong shape, two verdict lines, unreadable file) — never green. A WARN that exists because a reviewer or engine did not run (missing-reviewer: / unattributable-payload in allow_blocked_by) is also exit 2: a review not performed in full stops a merge (operator decision 2026-10-06). It takes exactly one file. On exit 0 with WARN, --json also returns warn_reasons (the JSON block's allow_blocked_by); print them. Capture the exit code as gate_exit and print it in Phase 9 exactly as returned. This is the command that later stops a merge or a release on BLOCK; /trekreview reports it and never overrides it.

Then append one record to trekreview-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.

node ${CLAUDE_PLUGIN_ROOT}/lib/stats/stats-append.mjs trekreview <<'JSON'
{"ts":"{ISO-8601}","slug":"{slug}","verdict":"BLOCK|WARN|ALLOW","counts":{"BLOCKER":N,"MAJOR":N,"MINOR":N,"SUGGESTION":N},"reviewed_files_count":N,"mode":"default|quick|validate|dry-run","duration_ms":N}
JSON

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

Build the operator-annotation HTML. After stats land, run:

ANNOT_HTML=$(node ${CLAUDE_PLUGIN_ROOT}/scripts/annotate.mjs "{review_path}" 2>&1)

stdout is the absolute path to the .html on success. The HTML renders review.md with line numbers, lets the operator click any line to attach their own note (not Claude-generated suggestions — the operator drives every annotation), keeps a sidebar of all notes, persists state in localStorage, and exposes a "Copy Prompt" button. If annotate.mjs exits non-zero, surface a one-line warning and continue — the annotation HTML is a convenience, not a gate.

Phase 8.5 — Validate-only mode (--validate)

When mode == validate:

1. Skip Phases 3–7 entirely.
2. Run the strict validator on {project_dir}/review.md.
3. Print a one-line PASS/FAIL summary plus the JSON output on FAIL. A review_version 1.0 review without verdict: FAILS here (K7 is a write-time rule); it still seeds a plan, because /trekplan reads in soft mode.
4. Run lib/review/verdict-gate.mjs on the same file and print its line and exit code.
5. Exit 0 on PASS, 1 on FAIL. Never write to disk. Never call any agent. Skip Phase 8.7.

Phase 8.7 — The project's memory (recurring finding classes)

Skipped in dry-run and validate. A finding class (the same catalogue rule_key) that shows up in two review.md files in this repo becomes ONE proposal; one sighting is no proposal. The history is the review.md files the repo already has (every .claude/projects/*/review.md, plus earlier committed versions of them) — no new store.

node ${CLAUDE_PLUGIN_ROOT}/lib/review/recurrence.mjs propose --repo "$PWD"

--repo is the session's working directory — the directory project_dir paths are relative to, and the project Claude Code loads .claude/rules/ from. Not the git toplevel: for a project in a subdirectory that would read no reviews and write the lessons in the wrong place.

It prints {"proposals": [...]} (exit 0) or exits 2 (could not run — say so in the summary; never read 2 as "nothing recurred"). Each proposal names its rule_key, its route and its evidence (the finding IDs from two reviews), and carries one line in the format mistake · fix · how to check:

• route check (mechanical) — the line names the deterministic check that catches the class;
• route rule (judgement) — the line is for the repo's .claude/rules/ file, which Claude Code loads at session start;
• review-hygiene classes are never proposed.

The operator approves every line. For each proposal, use AskUserQuestion (up to 4 proposals per call), in plain language, showing the line and its two pieces of evidence. Options: "Skriv linja inn" (recommended: the class has recurred) and "Ikke nå"; the operator may answer with an edited line through "Other". Never write a line the operator did not approve, and never treat "sounds good" or "do as you like" as a yes to a line it was not shown.

On yes:

node ${CLAUDE_PLUGIN_ROOT}/lib/review/recurrence.mjs apply --repo "$PWD" \
  --rule-key <RULE_KEY> [--line "<the operator's edited line>"]

It writes ONLY between Voyage's own markers in .claude/rules/voyage-review-lessons.md and, if the repo has a CLAUDE.md, gives it a one-line pointer once (never the lesson itself). Exit 1 with over-budget means the managed block is full: tell the operator the lessons belong in a skill now — that is the operator's decision, not this command's. Exit 1 with invalid-line means the line was refused by the schema check (missing one of the three parts, a line break or control character, marker text, or over 700 characters) — show the detail and ask again. Exit 1 with markers-damaged means Voyage's markers in the lessons file are not one start before one end: say so; the operator fixes the file by hand. A finding class only counts when two reviews hold two DIFFERENT findings of it — one unfixed finding seen again is a persisting defect, not a lesson — and the two catch-all engine keys are never proposed. Report every outcome in the summary; when no class recurred, say "no recurring finding class" — do not pad.

Borrowed: routing (Pocock retro), the three-part line (ai-native-sdlc), the managed block (Spec Kit agent-context), evidence per proposal and schema-check before write (Kiro), review → memory and the size budget (Cherny). Credits in lib/review/recurrence.mjs.

Phase 9 — Present summary

After the write succeeds, print:

## Ultrareview Complete

**Task:** {task}
**Mode:** {default | quick | dry-run}
**Brief:** {brief_path}
**Project:** {project_dir}
**Review:** {review_path}
**Annotation HTML:** file://{$ANNOT_HTML}
**Scope:** {before_sha}..{after_sha} ({reviewed_files_count} files)
**Verdict:** {BLOCK | WARN | ALLOW}
**Gate:** verdict-gate exit {gate_exit} ({0 = ALLOW/WARN | 1 = BLOCK | 2 = could not decide, or a control did not run — not green})
**Engine:** /code-review {delivered N | not run: reason} · /security-review {delivered N | not run: reason}

### Counts
- BLOCKER: {N}
- MAJOR: {N}
- MINOR: {N}
- SUGGESTION: {N}
- Trimmed (MINOR/SUGGESTION text only, never removed): {N}
- Declined to judge: {N} — {one line each: file:line rule_key — reason}

### Project memory
{each proposal: rule_key → written | declined by operator | over-budget | invalid-line;
 or "no recurring finding class"; or "recurrence check could not run"}

### Top findings
- [{severity}] {title} ({file}:{line})
  ...
{up to 5 highest-severity findings}

────────────────────────────────────────────────────────────────────
To review and annotate the review, open it in a browser:

    open file://{$ANNOT_HTML}

Click any line to add YOUR OWN note. The sidebar collects every note,
the "Copy Prompt" button gathers them into one structured prompt.
Paste that prompt back into this chat and Claude revises review.md
from your notes. Annotations persist in your browser if you close
the tab and reopen the same file.
────────────────────────────────────────────────────────────────────

You can also:
- Feed BLOCKER + MAJOR findings into a follow-up plan:
    /trekplan --brief {review_path}
- Re-run with `--quick` for a faster correctness-only pass
- Re-run with `--since <ref>` to narrow scope

Per Handover 6, BLOCKER and MAJOR findings are consumed by /trekplan --brief review.md to produce a remediation plan. The review's frontmatter findings: list and the trailing JSON block are the contract for that handover (see docs/HANDOVER-CONTRACTS.md).

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. premium default (source: default)

The selected profile drives phase_models.review — economy uses sonnet for the brief-conformance + code-correctness reviewers; balanced and premium use opus (review benefits from deeper reasoning).

Examples:

/trekreview --profile balanced --project .claude/projects/2026-05-09-add-auth
VOYAGE_PROFILE=premium /trekreview --project ...

Stats records emit profile and profile_source.

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 node ${CLAUDE_PLUGIN_ROOT}/lib/profiles/resolver.mjs --resolve-phase-model invoked in Phase 2; the resolved JSON {effort, model, source} is captured as phase_signal_result and passed to Agent tool calls explicitly. The resolver controls the model parameter at Agent-spawn sites only — the orchestrator's own model is fixed at invocation time (command frontmatter omits model:, so it follows the session model) and cannot be switched mid-turn. Sub-agents fall back to model: in their own agents/*.md frontmatter when no spawn-site injection happens.

For /trekreview specifically: effort == 'low' activates the existing --quick-equivalent code-path (skip the brief-conformance reviewer; run correctness-only). effort == 'standard' (or absent) → no change. effort == 'high' activates the high-effort behavior documented under ### High-effort behavior (v5.1.1) below.

Sequencing gate surface

Phase 1 already calls brief-validator.mjs --soft against {brief_path}. If the validator returns BRIEF_V51_MISSING_SIGNALS 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; this surface just makes the friendly hint readable.

High-effort behavior (v5.1.1)

When phase_signal_result.effort == 'high' for the review phase, skip Pass 3 (Cloudflare reasonableness filter) in agents/review-coordinator.md. Passes 1, 2, and 4 still run. Rationale: high-effort review trusts the operator to weigh borderline findings rather than have the coordinator drop them. To prevent unknown rule_key values from polluting downstream remediation plans (Handover 6), the coordinator applies its v5.1.1 high-effort normalization rule — substituting unknown rule_key values with the literal string PLAN_EXECUTE_DRIFT (the most general drift category in the catalogue) and preserving the original in original_rule_key. See agents/review-coordinator.md § Pass 3 "High-effort normalization (v5.1.1)" for the full normalization spec.

Standard effort (or absent): run all 4 passes as usual. Low effort: skip the brief-conformance reviewer entirely (existing --quick-equivalent code-path).

Hard rules

• Brief is the contract. Every finding in the review traces to a brief section via brief_ref, except SCOPE_CREEP_BUILT (which traces to "no anchor"). Conformance is the conformance reviewer's job — code-correctness findings carry generic anchors like "NFR — code correctness".
• Independent reviewers. Do NOT cross-feed findings between brief-conformance-reviewer and code-correctness-reviewer. The coordinator is the only place where outputs combine.
• Bounded coordination. Synthesis-level inference across files is forbidden in v1.0. The coordinator dedups, filters, and computes the verdict — nothing more.
• Triage map respected. Files marked skip MUST appear in the Coverage section. Silent drops are COVERAGE_SILENT_SKIP (MAJOR).
• Block-style YAML for findings list. The frontmatter parser does not support flow-style arrays. findings: [a, b] is broken; use findings:\n - a\n - b.
• Refuse-with-suggestion above 100 files / 100K tokens. Never run blind on a giant diff. Use AskUserQuestion to surface the gate.
• Cost. Model resolution at Agent-spawn sites is a three-layer fallback: brief phase_signals[<phase>].model > profile.phase_models[<phase>] > agent frontmatter model:. The composed resolver returns the first two layers as phase_signal_result.model; spawn sites inject it, and agent frontmatter is the fallback when no injection happens.
• Privacy. Never log secrets, tokens, or credentials in review.md. Findings citing files with secret-like content must redact the secret in the detail field.
• Honesty. If the diff is trivially small or all-skip, say so. Do not pad findings to make the review look thorough.
• No production code. This command never runs production code, never writes to anything outside {project_dir} and ${CLAUDE_PLUGIN_DATA} — with one exception, only after the operator approved that exact line in Phase 8.7: Voyage's own marked block in .claude/rules/voyage-review-lessons.md and a one-line pointer in CLAUDE.md.
• The engine never edits code. /code-review and /security-review run without --fix, --comment, --post or ultra. A review that changes code is not a review.
• No finding is struck for length. Only MINOR/SUGGESTION text is trimmed, and every trim is counted; what the coordinator set aside is listed under ## Declined to Judge.
• The verdict is in the file, and a command decides on it. verdict: is required (K7); lib/review/verdict-gate.mjs exit 2 is never green.