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/implementgit 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 | $0.00658 |
| Opus 5 | $0.00000 | $0.00329 |
| Sonnet 5 | $0.00000 | $0.00132 |
| Haiku 4.5 | $0.00000 | $0.00066 |
Grade A, and why
implement 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.
How it starts
The opening of the file, as written. The whole thing — 30 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/implement
Instruct the executing agent to implement from Method artifacts.
Run the pre-implement readiness check before touching code:
- Resolve the active feature folder and read
state.json. - Verify the task-type-specific canonical artifacts exist and are not stale:
new-feature/bug-fix:01-requirement.md,02-acceptance-criteria.md,03-test-case.md,04-implementation-plan.md.hotfix:01-requirement.md,02-acceptance-criteria.md,03-test-case.md;04-implementation-plan.mdis expected for SEV1/SEV2/SEV3, multi-file fixes, or sensitive paths, but may be skipped for SEV4.documentation,refactor,tech-debt,dep-bump,spike:01-requirement.md; other artifacts follow their workflow docs when they are useful.05-design.mdis also expected for user-facing changes.
- Treat unresolved
state.json.openQuestions[]as a blocker until the user answers them or records explicit decisions instate.json.decisions[]. - Treat non-canonical numbered artifacts as blockers before implementation, especially invented files such as
03-design.md,04-sa-analysis.md,05-security-review.md, or06-qa-analysis.md. Normalize content into the canonical artifacts first. - Treat
security-review.mdinstate.json.artifactsas a non-canonical Method artifact./security-reviewupdates the## Securityand## Riskssections of04-implementation-plan.md; mirror or move the decisions there before implementation. - If
state.jsonis invalid, repair state.json before editing code by regenerating it from canonical artifacts. The repaired state needsschemaVersion,artifactRoot, andartifacts.{file}.statusplusartifacts.{file}.dependenciesentries.
Decision Reconciliation
Before editing code, do a semantic consistency pass across 01-requirement.md, 02-acceptance-criteria.md, 03-test-case.md, 04-implementation-plan.md, and 05-design.md when present:
- Scan for critical nouns and decision terms that affect implementation, such as auth scopes, billing units, job lifecycle, storage policy, logging/PII, external service clients, feature flags, and user-visible UX.
- If a direction changed mid-work, purge or supersede the old decision in every artifact instead of leaving both options in place.
- If two artifacts disagree on user-visible behavior, billing, security, storage, logging, external service boundaries, or async state, stop and ask for a decision.
- Verify
04-implementation-plan.mdhas oneChosen Implementation Boundariesanswer per important boundary. Do not bury competing implementation strategies in Risks.
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 · 30 lines · 0 tokens per session scan A c5896e072579
implement 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 658 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.