commit

A controlled process for preparing a code commit, including checks for builds, types, tests, linting, and uncommitted changes.

In plain words
What is it for?
Use it to verify a change before committing, check version updates, review repository status, and prepare an approved commit message.
Why use it?
It reduces the chance of committing broken or incomplete work. The commit still requires explicit approval instead of happening automatically.

Command for Claude Code

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/qwickapps/ai-sdlc-workflows/commit
Clone the repo
git clone --depth 1 https://github.com/qwickapps/ai-sdlc-workflows

Made for: Claude Code.

Per session 7 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,283 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 $0.00007 $0.01283
Opus 5 $0.00003 $0.00642
Sonnet 5 $0.00001 $0.00257
Haiku 4.5 $0.00001 $0.00128

Measured yesterday against content hash 70f68847976f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

commit 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.

claude/.claude/commands/commit.md · 195 lines

How it starts

The opening of the file, as written. The whole thing — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Controlled Commit Workflow

You are now in Commit Mode. Use this for controlled, approved commits.

Input: $ARGUMENTS (optional suggested commit message or scope)

CRITICAL RULES

  1. NEVER auto-commit - always wait for explicit "approved"
  2. NO attributions - no "Generated with Claude Code", no "Co-Authored-By"
  3. Verify deliverables - tests, docs must be in order
  4. Check version bumps - verify against registry before committing

Commit Process

Step 1: Pre-Commit Verification (MANDATORY - see VALIDATION-GATES.md)

Run these checks before proposing commit:

# 1. Build/Compilation check
npm run build          # or pnpm build, yarn build
npm run build:prod     # if different production build exists

# 2. Type checking (for TypeScript)
tsc --noEmit           # verify types without emitting files

# 3. Run tests
npm run test
npm run test:coverage

# 4. Run linting (if applicable)
npm run lint

# 5. Check for uncommitted changes
git status

Validation Checklist:

  • Code compiles without errors
  • TypeScript type checks pass (if applicable)
  • All tests pass
  • Test coverage maintained/improved
  • Linting passes
  • Build produces expected artifacts

GATE: Do NOT proceed if any validation fails.

For deployment-related changes:

# Test actual deployment build
.github/scripts/build-workspace-package.sh   # or equivalent

# For Docker changes
docker build -t test-commit .
docker run -p 3000:3000 test-commit
# Verify startup and basic functionality

For database changes:

# Test migrations on CLEAN database
npm run migrate
# Verify migrations are idempotent
npm run migrate  # should run without errors

Step 2: Review Changes

  1. Show diff summary:

    • Files added/modified/deleted
    • Key changes in each file
  2. Verify completeness (see VALIDATION-GATES.md for details):

    • Implementation complete
    • Code compiles (dev and prod builds)
    • Tests written and passing
    • Tested in production-like environment
    • User's actual problem is solved
    • README updated (if needed)
    • CHANGELOG updated (if needed)
    • ARCHITECTURE updated (if needed)

Read the full file on GitHub · 195 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 · 195 lines · 7 tokens per session scan A 70f68847976f

Subscribe to this mod's changes

commit is a command published in the GitHub repository qwickapps/ai-sdlc-workflows (2 stars, last pushed 5mo ago), licensed MIT. It adds 7 tokens to every session and 1,283 once invoked, about $0.0000 per session on Opus 5. 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.