Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/lab94/frenchie-skill/job-donegit clone --depth 1 https://github.com/Lab94/frenchie-skillWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/lab94/frenchie-skill/job-done)<a href="https://agentmods.dev/commands/lab94/frenchie-skill/job-done"><img src="https://agentmods.dev/badge/commands/lab94/frenchie-skill/job-done.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.00854 |
| Opus 5 | $0.00000 | $0.00427 |
| Sonnet 5 | $0.00000 | $0.00171 |
| Haiku 4.5 | $0.00000 | $0.00085 |
Grade A, and why
job-done scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/job-done
Close the Method workflow.
Verify gates, record final state, summarize artifacts/tests/release status, and ask before cleanup. Destructive worktree or branch cleanup requires explicit approval. Frenchie does not auto-archive or auto-delete completed feature folders — they stay in place by default.
Cleanup Policy
Frenchie's policy on completed feature folders is opt-in only:
- No auto-archive. Feature folders are never moved to a
_archive/or_done/directory by/job-doneor any other Method command. The folder stays at.frenchie/docs/feature/<slug>/indefinitely. - No auto-delete. Feature folders,
state.json, and produced artifacts are never deleted automatically. Even after/releaseand/job-done, all evidence stays on disk. - Explicit approval for destructive actions. If the user explicitly asks
/job-doneto clean up — for example, "remove the worktree", "delete the branch", or "archive this feature" — the agent confirms the exact action before executing. Worktree removal, branch deletion,git worktree prune, and any folder move/delete each require their own explicit confirmation. - No silent cleanup as a side effect.
/release,/pr-review, and/job-doneall stop at the cleanup step and surface what would be removed; nothing is removed without the user saying so in the chat.
Rationale: feature folders are durable evidence. Search, audit, and onboarding all benefit from the trail being intact. Storage cost is negligible. No auto-archive also keeps /method-check deterministic — silently archived folders would make later health checks fail to find features the user expects to still be there. Users who want to clean up can do so manually or by asking explicitly.
Spike
For taskType: spike, follow workflows/spike.md. Ask the user to pick promote or discard before any cleanup. On promote, flip state.json.taskType to new-feature and continue per the standard feature workflow — /job-done does not finalize a promoted spike. On discard, preserve the spike folder as evidence and proceed with cleanup-on-approval.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 45 lines · 0 tokens per session scan A 792331c06b31
job-done is a command published in the GitHub repository Lab94/frenchie-skill (0 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 854 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
project-recap
Generate a visual project recap for context switching.
standup
Show a daily standup summary with completed, in-progress, and blocked tasks across all active epics.
m-task-planner
Target: $ARGUMENTS (Default: requirement document(s) discovered in the project).
triage
Triage ServiceNow incidents — list open incidents, assess priority, investigate a specific INC, or analyze trends.
session-log
Create or append a session log entry.
my-tasks
Track, prioritize, and execute tasks with goal alignment and due date awareness. Claude doesn't just remind you — it helps get work done.