メニュー
Stage and commit with conventional message — pre-flight scan blocks risky files (.env, logs, keys, secrets, >1MB)
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
| name | fwd:git-commit |
| description | Stage and commit with conventional message — pre-flight scan blocks risky files (.env, logs, keys, secrets, >1MB) |
| context | fork |
| model | haiku |
| allowed-tools | Bash |
You are a fast, safety-aware commit agent.
!bash "${CLAUDE_SKILL_DIR}/scripts/pre-flight.sh" && echo "---DIFF---" && rtk git diff --staged
Inspect the Pre-Flight section (the lines before ---DIFF---) first:
First line risky-files: → do NOT commit. Respond with the block below and stop:
🛑 Pre-flight scan blocked the commit. The following look risky:
- <path> — <reasons>
- <path> — <reasons>
Reason codes: env-file, log-file, key-file, secret-name, large-file
Resolve by:
- Adding the file to .gitignore (if it should never be committed), OR
- Removing the file, OR
- Staging it manually with `rtk git add <path>` and committing directly with `rtk git commit -m "<msg>"` (skips this scan)
Re-run /fwd:git-commit after resolving.
First line no-changes → report "Nothing to commit — working tree clean." and stop.
First line starts with git-failed: → report "Git error: " and stop.
First line ok → files are staged; continue below.
Generate a conventional commit message from the diff section (after ---DIFF---):
Commit and get the hash:
rtk git commit -m "<type>(<scope>): <description>" && rtk git rev-parse --short HEAD
For large changes, add a body:
rtk git commit -m "<type>(<scope>): <description>" -m "<body>" && rtk git rev-parse --short HEAD
Return the commit message in this format:
Committed:
<type>(<scope>): <description>
<body if exists>
Setup wizard for HeadingFWD's optional Claude Code conventions. Runs unattended — zero prompts, always project-local scope: installs every convention in one batch — smartlint Stop-hook, lessons memory file, gitignore entries for fwd runtime artefacts, clear-context prompt on plan accept, and no-attribution (disables the Claude commit/PR byline). Copies bundled payload files into .claude/hooks/ or .claude/lessons/, merges JSON snippets into .claude/settings.local.json, injects an instructions section into CLAUDE.md (lessons), or appends a marker-bracketed block to .gitignore. Idempotent and modular — each feature lives in scripts/<feature>/. Prints a fixed-format Dutch summary from the bundled OUTPUT.md template, never free-form prose. Runs on Haiku. Use only when the user invokes /fwd:setup explicitly.
Voer een stappenplan van /fwd:steps-plan uit — attended, precies één stap per beurt. Per stap; falende test eerst (rood), minimale implementatie langs de Lazy Ladder (groen), volledige gate, vers oordeel door een read-only reviewer-subagent, en een stap-rapport van ±15 regels met "Stap N/M"-teller — daarna stopt de beurt en beslist de gebruiker (ok = commit & door, auto = autonoom afmaken, m = meer detail, stop = pauze, vrije tekst = correctie/vraag/planwijziging). Elke 4 goedgekeurde stappen een tussenbalans door twee doubt-subagents. Use when the user runs /fwd:steps-run <slug>, zegt "volgende stap", "ga door met het stappenplan", of "hervat <slug>". Zonder argument: lijst alle stappenplannen. Niet voor onbeheerd werk — dat is fwd:mission-run.
Plan een klus als een reeks kleine, toetsbare stappen voor attended uitvoering met /fwd:steps-run — de lichte tegenhanger van fwd:mission-plan. Scope het doel kort, pin een Definition of Done mét concreet eindbeeld (input→output-voorbeeld of ASCII-mockup), spreek de testplekken (seams) af, en lever een genummerde stappenlijst waarin elke stap één aantoonbaar gedrag is met een machinaal toetsbaar klaar-criterium. Use when the user zegt "plan dit in stappen", "maak een stappenplan", "steps-plan", of invokes /fwd:steps-plan. Niet voor onbeheerd/overnight werk — dat is fwd:mission-plan.
Plan a multi-agent "mission" — scope a software goal through conversation, write a PRD plus a validation contract (what "done" means, before any code), decompose into features and milestones, then create the mission branch and persist the plan on it. The interactive half of the fwd:mission-* orchestration layer (modelled on Factory.ai Missions); execution is handled afterwards by /fwd:mission-run. Use when the user wants to plan a larger feature as an orchestrated mission, says "plan a mission", "start a mission", "scope this as a mission", or invokes /fwd:mission-plan.
Execute a planned mission — the resident orchestrator of the fwd:mission-* layer (a Claude Code take on Factory.ai Missions). Reads the mission's state.json, drives features one at a time by spawning a fresh coder subagent each, runs adversarial validators (Scrutiny + User-Testing) at milestone boundaries, and records a checkpoint after every unit so the mission resumes from any worktree or clone. Runs autonomously — never prompts. Use when the user runs /fwd:mission-run <slug>, says "run/execute/resume mission <slug>", or wraps it in /loop for a long multi-day run. Pass `status` as a second argument for a read-only progress report.
Plan een implementatie — verzamel codebase-context, presenteer eerst een DoD-voorstel met numbered bullets (akkoord of corrigeer in plain text, géén AskUserQuestion), stel daarna 0-3 verdiepende keuzes via AskUserQuestion, en presenteer 1 of 3 plannen in visueel distincte boxen met spec-strip + TL;DR + Wijzigingen-tabel. Sluit af met (Recommended)-tag op het beste plan en een verdict-block, en legt na de plan-keuze een licht contract vast in `.claude/plan-contracts/<slug>.md`. `/fwd:plan check [<slug>]` toetst achteraf de diff en de DoD-bewijsregels tegen dat contract. Use when user wants to plan a feature, refactor, or change met meerdere opties op tafel, of invokes /fwd:plan.