commit

A command for creating Git commits, which are saved checkpoints of changes in a code project. It can generate a message in Conventional Commits format, such as labeling a change as a feature, fix, or documentation update.

In plain words
What is it for?
Staging changes and creating quick or custom commits with structured messages, optional bodies, tests, and issue references.
Why use it?
It avoids manually staging files and deciding how to format the commit message. It can also include a detailed description, issue reference, and Claude Code attribution.

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/plipowczan/claude-piv-skeleton/commit
Clone the repo
git clone --depth 1 https://github.com/plipowczan/claude-piv-skeleton

Made for: Claude Code.

Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,895 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 $0.00016 $0.01895
Opus 5 $0.00008 $0.00948
Sonnet 5 $0.00003 $0.00379
Haiku 4.5 $0.00002 $0.00189

Measured 2d ago against content hash bef3f1faec2f, 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 2d ago.

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/commands/git/commit.md · 385 lines

How it starts

The opening of the file, as written. The whole thing — 385 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Commit: Create Git Commit

This command delegates to the official Anthropic commit-commands plugin.

Usage

Quick Commit (Auto-Generated Message)

/commit

The plugin will:

  • Stage all changes (git add .)
  • Generate conventional commit message from changes
  • Create commit with proper attribution
  • Include co-author tag for Claude Code

Commit with Custom Message

/commit feat(auth): add JWT token refresh

Creates commit with your specified message.

Commit with Body

/commit fix(api): resolve race condition

- Add mutex lock to shared resource
- Update error handling
- Add unit tests

Fixes #123

Creates commit with detailed body.

Commit Message Format

The plugin enforces Conventional Commits format:

type(scope): description

[optional body]

[optional footer]

Types

Type When to Use Example
feat New feature feat(auth): add JWT authentication
fix Bug fix fix(api): resolve race condition
docs Documentation docs(readme): update installation
style Code style (formatting) style(frontend): format with Prettier
refactor Refactoring refactor(service): extract validation
test Adding/updating tests test(api): add integration tests
chore Maintenance chore(deps): update dependencies
perf Performance perf(query): optimize database query

Good Examples

Simple:

feat(user): add email validation

With scope and body:

fix(auth): resolve token expiration issue

- Add refresh token rotation
- Update token validation logic
- Add unit tests for edge cases

Fixes #456

Multi-line:

feat(api): implement user search endpoint

- Add GET /api/users?search=query endpoint
- Implement case-insensitive search
- Add pagination support
- Include integration tests

Closes #789

Bad Examples

Too vague:

update stuff
fix bug
changes

Read the full file on GitHub · 385 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. 2d ago First seen · 385 lines · 16 tokens per session scan A bef3f1faec2f

Subscribe to this mod's changes

commit is a command published in the GitHub repository plipowczan/claude-piv-skeleton (4 stars, last pushed 7mo ago), licensed MIT. It adds 16 tokens to every session and 1,895 once invoked, about $0.0001 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.