Phase 3 (atomic-write) and Phase 4 (validator) used !`...` eager-exec
with unresolved runtime placeholders; the harness executes those at
command LOAD time, so zsh parsed <project-dir> as input redirection and
/trekendsession aborted before the model saw a single instruction.
Both blocks are now plain runtime Bash fences with {curly} placeholders
(shell-inert, trekplan.md convention) and absolute ${CLAUDE_PLUGIN_ROOT}
paths (cwd-relative plugin paths were a latent ERR_MODULE_NOT_FOUND in
any user repo). Phase 1 discovery block keeps its legitimate eager-exec.
Regression guard: new tests/commands/trekendsession.test.mjs flags any
!`-block in commands/*.md containing <angle>/{curly} placeholders, and
pins Phase 3/4 as runtime Bash. Suite 828 -> 832 (830/0/2). E2E: fixed
blocks run with real values write both state files, validator valid:true;
trekcontinue.md:147 runtime-verified self-contained.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_013NXzF3F2zAM8S7FCBXCqAb
7.2 KiB
| name | description | argument-hint |
|---|---|---|
| trekendsession | Mark the current session as complete and write session-state pointing at the next session. Helper for informal multi-session flows. | <next-brief-path> <next-label> | --help |
Voyage End-Session Local v1.0
Tiny helper for informal multi-session flows (no formal plan with
Execution Strategy). Writes a .session-state.local.json pointing at the
next session so /trekcontinue can resume in a fresh Claude chat.
For formal flows (a plan produced by /trekplan --project),
/trekexecute Phase 8 already writes the state file — this helper
is unnecessary there. Use this command for ad-hoc release runs, manual
multi-session handovers, or any flow that does not run through
/trekexecute.
Pipeline position:
... session N work ...
/trekendsession <brief> "<next-label>" → writes state
... session boundary, fresh chat ...
/trekcontinue → reads state, starts session N+1
See Handover 7 in docs/HANDOVER-CONTRACTS.md for the schema.
Phase 0 — --help handling
If $ARGUMENTS contains --help or -h, print the usage block below and exit
cleanly. Do NOT proceed to any further phase.
/trekendsession — Mark current session done; point at next session.
Usage:
/trekendsession <next-brief-path> <next-label>
/trekendsession --help
Both arguments are REQUIRED. No interactive prompt — headless-safe.
Writes <project-dir>/.session-state.local.json with:
schema_version 1
project <auto-resolved from cwd>
next_session_brief_path <next-brief-path argument>
next_session_label <next-label argument>
status in_progress
updated_at <now, ISO-8601>
Then validates via lib/validators/session-state-validator.mjs and prints
the same 3-line narration that /trekcontinue will show in the next session.
Example:
/trekendsession .claude/projects/2026-05-01-feature/brief.md "Session 2 of 3"
Phase 1 — Resolve project directory
Resolve the nearest .claude/projects/*/brief.md from cwd (the current working
directory). Use node -e enumeration (NOT shell glob — harness-mode safety):
!`node --input-type=module -e "import {existsSync, readdirSync} from 'node:fs'; import {join} from 'node:path'; const root='.claude/projects'; if(!existsSync(root)) process.exit(0); readdirSync(root).filter(d=>existsSync(join(root,d,'brief.md'))).forEach(d=>process.stdout.write(join(root,d)+'\\n'));"`
Decision tree:
- 0 candidates: print error to stderr — "no
.claude/projects/<dir>/brief.mdfound under cwd; cannot determine project directory" — and exit 1. Do NOT fall back to a synthesized path. - 1 candidate: use it as
<project-dir>. Continue. - >1 candidates: print all paths and ask the operator to
cdinto the intended project directory before retrying. Exit 1.
Phase 2 — Required args check (headless-safe)
Read $ARGUMENTS. Both <next-brief-path> and <next-label> are required.
If either is missing or empty:
Error: missing required args.
Usage: /trekendsession <next-brief-path> '<next-label>'
Print to stderr and exit 1. No interactive prompt — this keeps the helper
headless-safe (per brief NFR; addresses adversarial-review major #11). If you
want an interactive flow, use /trekcontinue --help to see the full pipeline.
Phase 3 — Atomically write .session-state.local.json + sibling NEXT-SESSION-PROMPT.local.md
Write {project_dir}/.session-state.local.json with the schema-v1 object:
{
"schema_version": 1,
"project": "{project_dir}",
"next_session_brief_path": "{arg 1}",
"next_session_label": "{arg 2}",
"status": "in_progress",
"updated_at": "{now, ISO-8601}"
}
Use the atomic-write util — write to <path>.tmp, then rename into place —
to avoid partial-state on crash. The util is ESM, so invoke via
node --input-type=module -e with an import statement (a CommonJS shim
would throw ERR_REQUIRE_ESM on Node 18+ since atomic-write.mjs is ESM).
Under node --input-type=module -e "<script>" arg1 arg2 arg3, Node sets
process.argv[0] to the node binary path and user args start at
process.argv[1]. Adjust the destructure if your Node version differs.
This phase ALSO writes a sibling NEXT-SESSION-PROMPT.local.md in the
project directory with YAML frontmatter (produced_by: trekendsession,
produced_at: {ISO-8601}, project: {project_dir}). Both files are written
in a single ESM block so the writes succeed or fail together.
Run the block below via the Bash tool at runtime, substituting the resolved
values for the {curly} placeholders (Phase 1 gives {project_dir}, Phase 2
gives {next_brief_path} and {next_label}). This is NOT an eager-exec
block — the values do not exist at command-load time. The import path must
stay absolute via ${CLAUDE_PLUGIN_ROOT} — your Bash cwd is the user's
repo, not the plugin root, so a cwd-relative import throws
ERR_MODULE_NOT_FOUND:
node --input-type=module -e "
import path from 'node:path';
import { writeFileSync } from 'node:fs';
import { atomicWriteJson } from '${CLAUDE_PLUGIN_ROOT}/lib/util/atomic-write.mjs';
const [, dir, brief, label] = process.argv;
const now = new Date().toISOString();
const stateObj = { schema_version: 1, project: dir, next_session_brief_path: brief, next_session_label: label, status: 'in_progress', updated_at: now };
const stateFile = path.join(dir, '.session-state.local.json');
atomicWriteJson(stateFile, stateObj);
const promptFile = path.join(dir, 'NEXT-SESSION-PROMPT.local.md');
const promptBody = '---\\nproduced_by: trekendsession\\nproduced_at: ' + now + '\\nproject: ' + dir + '\\n---\\n\\n# ' + label + '\\n\\nResume via /trekcontinue.\\n';
writeFileSync(promptFile, promptBody);
console.log(stateFile);
console.log(promptFile);
" '{project_dir}' '{next_brief_path}' '{next_label}'
Phase 4 — Validate + narrate
Validate the freshly-written state file via the Bash tool at runtime,
substituting the resolved {project_dir} (NOT eager-exec — the file does
not exist at command-load time):
node ${CLAUDE_PLUGIN_ROOT}/lib/validators/session-state-validator.mjs --json {project_dir}/.session-state.local.json
If valid: true, print the success block matching /trekcontinue Phase 3
narration (SC-8 cross-project consistency — same template both sides):
Session state written: {project_dir}/.session-state.local.json
Project: {project_dir}
Next session: {next_label}
Brief: {next_brief_path}
In a fresh Claude session, run /trekcontinue to resume.
If valid: false, print the structured errors[] and exit 1. Investigate
before retrying — usually means a bad path or label argument.
Hard rules
- Required args, no defaults. Never invent a brief path or session label. If args are missing, fail loud.
- Atomic write only. Tmp + rename — no partial state files on disk.
- Zero secrets. Status, paths, labels — never API keys, never user content beyond filenames.
- NEVER auto-invoke this command. It is operator-typed only at session-end.
- Idempotent within a session. Running twice with the same args overwrites cleanly (atomic rename); does not double-advance.