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/requirementgit 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 | $0.00633 |
| Opus 5 | $0.00000 | $0.00316 |
| Sonnet 5 | $0.00000 | $0.00127 |
| Haiku 4.5 | $0.00000 | $0.00063 |
Grade A, and why
requirement 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/requirement
Turn the user's request into implementable requirements.
Gather enough clarity for downstream work: problem, users, scope in/out, acceptance criteria candidates, constraints, dependencies, non-goals, risks, edge cases, data/security/privacy notes, and open questions. Ask focused questions until ambiguity is low enough to proceed.
Write 01-requirement.md and, when useful, 02-acceptance-criteria.md.
Auto-bootstrap when feature context is missing
If no active feature folder exists when /requirement is invoked, propose creating one before requirement work begins:
- Infer a feature slug and
taskTypefrom the user's request. - Ask once: "No active feature found. I'll create
<slug>(<taskType>) under.frenchie/docs/feature/. OK?" - On confirmation, run the
/prepare-featureworkflow internally withtaskSize: mediumas a provisional value (the scope hint below may refine it). - Proceed with requirement work.
The user does not need to invoke /prepare-feature separately. If the user declines, ask for the desired slug or stop.
Scope hint in chat output
While reading source for context gathering, the agent should also note the rough scope of the change. Mention this in the chat reply (not as a formal artifact section):
- estimated size (
xs,small,medium,large,epic) - which files will likely change
- whether sensitive paths are touched (auth, billing, payment, migrations, dependency files, crypto, env files)
- which subsequent commands look necessary vs. skippable
Before recommending follow-up commands, consult the selected workflow file under method/workflows/ and preserve that order. Do not reorder Method gates from general reasoning. For a standard feature, the advisory order after /requirement is /qa-analysis → /design when user-facing → /security-review when risk is present → /sa-analysis → /task-plan → /implement.
Structure the end of the chat reply with three short fields:
- Recommended Next Command: exactly one next Method command, or "resolve open questions in
/requirement" when the requirement is not ready to hand off. For non-XS standard features, this is normally/qa-analysisbefore/sa-analysis. - Later Recommended Commands: ordered later commands from the selected workflow, with brief reasons.
- Skippable / Not Needed: conditional commands that look unnecessary for this scope.
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 · 46 lines · 0 tokens per session scan A 073016d87d75
requirement 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 633 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.