frenchie-method

A command that coordinates the Frenchie Method, a task workflow for software work. It classifies the request, checks project context and stale files, and recommends the next command while stopping for approval at risky points.

In plain words
What is it for?
It is for organizing new features, bug fixes, hotfixes, documentation, investigations, refactoring, technical debt, and dependency updates. It can also check branch and worktree alignment and recommend the next action.
Why use it?
It helps prevent work from starting with missing context, outdated planning files, or the wrong workflow step.

Command

Install

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.

agentmods
npx agentmods add commands/lab94/frenchie-skill/frenchie-method
Clone the repo
git clone --depth 1 https://github.com/Lab94/frenchie-skill
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,285 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.01285
Opus 5 $0.00000 $0.00642
Sonnet 5 $0.00000 $0.00257
Haiku 4.5 $0.00000 $0.00128

Measured yesterday against content hash 05adb07a0b29, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

frenchie-method 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.

method/commands/frenchie-method.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/frenchie-method

Orchestrate Frenchie Method. Classify the task, resolve or create feature context, check config/state/artifact freshness, and recommend the next Method command. Stop for user approval at risk points. The orchestrator emits warnings but never blocks — direct command invocation always overrides its recommendations.

Do not treat /frenchie as an alias. /frenchie is Frenchie Kit.

Flow:

  1. Identify task type: new-feature, bug-fix, hotfix, documentation, spike, refactor, tech-debt, or dep-bump.
  2. Detect whether the user made a freeform implementation request: Method was invoked in any form while also asking to build, change, edit, code, or implement.
  3. Resolve .frenchie/method.config.json; use defaults if missing.
  4. Locate or propose the feature artifact folder.
  5. Check stale artifacts, branch/worktree alignment, and missing recommended artifacts.
  6. Consult the selected workflow as the source of truth, recommend exactly one next Method command, and execute it on user confirmation.
  7. Never execute /release automatically.

Freeform implementation request handling

When the user invokes /frenchie-method, a Method wrapper skill, or the phrase Frenchie Method and also asks for implementation in the same request, the orchestrator routes into the selected Method workflow before production edits. It does not become a generic coding agent just because the implementation intent is clear.

For these requests, do not edit production code, create a feature branch, or start ordinary implementation until one of these is true:

  • Feature context exists and the minimum artifact set is present: state.json, 01-requirement.md, 02-acceptance-criteria.md, 03-test-case.md, and 04-implementation-plan.md.
  • For user-facing marketing, frontend, content, UI, navigation, page, component, or flow work, 05-design.md is also present.
  • The user explicitly approves a documented skip after the orchestrator names the missing artifacts and risk.

Read the full file on GitHub · 92 lines

Changes

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.

  1. yesterday First seen · 92 lines · 0 tokens per session scan A 05adb07a0b29

Subscribe to this mod's changes

frenchie-method 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 1,285 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.