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/releasegit clone --depth 1 https://github.com/Lab94/frenchie-skillWhat 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 | $0.00342 |
| Opus 5 | $0.00000 | $0.00171 |
| Sonnet 5 | $0.00000 | $0.00068 |
| Haiku 4.5 | $0.00000 | $0.00034 |
Grade A, and why
release 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 yesterday.
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.
What it actually says
/release
Execute release only after explicit human invocation and approval.
Confirm release target, commands, environment, credentials, expected impact, rollback plan, and monitoring. Never run from /frenchie-method automatically.
Alias: /frenchie-release.
Release Gates (warning-only)
Before any release action, surface warnings for the conditions below. Method does not block — the user has final authority on whether to release. Proceed only after explicit user confirmation, but explicit confirmation is consent, not enforcement.
- Warn if
/release-checkhas not run for the current artifact state. Recommend running it before release. Proceed if the user explicitly confirms. - Warn when releasing from
taskType: spike. Recommend promoting the spike into a production task first. Proceed if the user explicitly confirms. - Warn when merge may deploy automatically through CI/CD, protected branch automation, Vercel, GitHub Actions, or another configured deployment path.
- Update
09-release-checklist.mdwith target, commands, approvals, rollback, monitoring, and final decision. - Confirm the user explicitly wants to proceed now.
/release does not remove worktrees, delete branches, prune git metadata, or perform cleanup. Cleanup belongs to /job-done and still asks for explicit approval before destructive actions.
User overrides
When the user proceeds past any warning above, append a record to the existing state.json.decisions[] array (schema: { at: string, decision: string, reason?: string }) with decision: "release-override-<reason>" and the user's stated reason if any. This is for audit only and does not change behavior.
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.
- yesterday First seen · 24 lines · 0 tokens per session scan A c6bdb31c7aff
release is a command published in the GitHub repository Lab94/frenchie-skill (0 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 342 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
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.