prepare-feature

A feature-setup command that creates or resolves the working context for a development task.

In plain words
What is it for?
Use it to prepare feature, bug-fix, hotfix, documentation, refactoring, dependency, or other task folders and branches.
Why use it?
It gives the task a stable name, tracks its state and documents, and handles branch or worktree choices before work begins.

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/prepare-feature
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 525 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 $0.00525
Opus 5 $0.00000 $0.00262
Sonnet 5 $0.00000 $0.00105
Haiku 4.5 $0.00000 $0.00052

Measured yesterday against content hash 8d348857be2e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

prepare-feature 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/prepare-feature.md · 48 lines

How it starts

The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/prepare-feature

Create or resolve feature working context.

Responsibilities:

  • Choose a stable feature slug.
  • Create .frenchie/docs/feature/<feature>/ when the user confirms.
  • Initialize state.json with task type, current stage, branch/worktree metadata, and artifact map.
  • Recommend a git worktree when worktree.enabled is true.
  • Ask before destructive cleanup or overwriting stale state.

Alias: /frenchie-prepare-feature.

Worktree Edge Behavior

Default policy:

  • new-feature: branch prefix feature/
  • bug-fix: branch prefix fix/
  • hotfix: branch prefix hotfix/
  • documentation: branch prefix docs/
  • spike: branch prefix spike/
  • refactor: branch prefix refactor/
  • tech-debt: branch prefix chore/
  • dep-bump: branch prefix deps/

Branch defaults may be overridden by .frenchie/method.config.json, but the command must state the resolved branch before creating it.

Collision handling:

  • Use the configured pathPattern first.
  • If the target path already exists, choose a deterministic suffix collision strategy: -2, -3, etc. Do not use timestamps or random suffixes unless the user explicitly asks.
  • If the existing path is the intended worktree, reuse it only after confirming branch and repository alignment.

Repository/worktree detection:

  • Resolve the intended git repository root before generating artifact or worktree paths. In monorepos or nested repository setups, prefer the nearest git root that owns the files in scope and ask when ambiguous.
  • Detect nested worktree paths and warn when the proposed worktree would sit inside another worktree or inside the active repository.
  • If git worktree list contains stale entries whose paths no longer exist, warn and suggest git worktree prune. Do not run prune without explicit user approval.
  • If a listed worktree path exists but points at a different repository, stop and ask for a path/branch decision.

Failure and cleanup policy:

  • On filesystem failure, fall back to a no-worktree feature folder in the current checkout, record the caveat in state.json, and ask before retrying with a different path.
  • Ask before deleting directories, removing worktrees, pruning stale git worktree metadata, deleting branches, or overwriting existing Method state.
  • Worktree cleanup belongs near /job-done, not /prepare-feature, unless the user explicitly asked to repair setup.

Read the full file on GitHub · 48 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 · 48 lines · 0 tokens per session scan A 8d348857be2e

Subscribe to this mod's changes

prepare-feature 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 525 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.