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/redogit 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 | $0.00911 |
| Opus 5 | $0.00000 | $0.00456 |
| Sonnet 5 | $0.00000 | $0.00182 |
| Haiku 4.5 | $0.00000 | $0.00091 |
Grade A, and why
redo 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/redo
Mark a Method stage as needing rework. Cascades staleness to all downstream artifacts so /method-check and /frenchie-method accurately reflect what is current.
Syntax: /redo <stage>
Aliases: /frenchie-redo.
Stages
| Argument | Artifact | Downstream cascade |
|---|---|---|
requirement |
01-requirement.md |
02-acceptance-criteria.md, 03-test-case.md, 04-implementation-plan.md, 05-design.md, 06-test-report.md, 09-release-checklist.md |
qa-analysis |
03-test-case.md |
04-implementation-plan.md, 06-test-report.md, 09-release-checklist.md |
design |
05-design.md |
04-implementation-plan.md, 06-test-report.md, 09-release-checklist.md |
sa-analysis |
04-implementation-plan.md |
06-test-report.md, 09-release-checklist.md |
run-test |
06-test-report.md |
09-release-checklist.md |
walkthrough |
07-walkthrough.md |
08-review-report.md, 09-release-checklist.md |
pr-review |
08-review-report.md |
09-release-checklist.md |
release-check |
09-release-checklist.md |
(none) |
security-review and task-plan do not produce a single canonical artifact — /redo does not accept them as direct stages. To redo security analysis, redo the upstream stage (requirement or sa-analysis) and re-invoke /security-review.
If /redo design changes user-facing affordances (button labels, control visibility, flow ordering), also /redo qa-analysis afterward. The cascade table does not auto-invalidate qa-analysis on design because most design redos are visual (color, spacing, typography) and do not affect Gherkin scenarios — but the moment a label or control changes, scenarios like "Then the user clicks Save" become stale and the test cases need a refresh. The chain is manual to keep the common case (visual tweaks) cheap.
Behavior
- Resolve the active feature using the rules in
skills/core/state-check.md. - Look up the artifact for
<stage>in the active feature's state. - Mark that artifact's
statusasstale(ordraftif no body has been written). - Cascade: for every downstream artifact in the table above, if it currently has
status: ready, downgrade it tostale. Artifacts alreadymissingordraftstay as they are. - Append to
state.json.decisions[]:{ "at": "<ISO>", "decision": "redo-<stage>", "reason": "<user reason if given>" } - Update
state.json.lastModifiedAt(current ISO) andlastModifiedBy(current agent identifier). - Recommend the next command — typically the slash command that produces the artifact for
<stage>(e.g./redo designrecommends/design). The user is responsible for invoking it.
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 · 50 lines · 0 tokens per session scan A 3aae7e4e70d6
redo 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 911 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
git
Git operations with intelligent commit messages and workflow optimization.
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.
constitution
Create or update the project constitution from interactive or provided principle inputs.