commit

commit is a skill for Claude Code from bengous/claude-code-plugins. It costs 49 tokens per session (456 once invoked), scanned A, original, MIT.

A guided Git skill for committing the current work according to a repository's commit-message rules. It checks the branch and changes, protects secrets from being committed, and can add a line that closes a related issue.

In plain words
What is it for?
Use it when saving a completed change to Git history, especially when the branch or request identifies an issue to close.
Why use it?
It reduces mistakes such as committing unrelated files, exposing credentials, using the wrong message format, or forgetting the issue reference. It also leaves already staged work untouched when appropriate.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the git plugin — 3 skills shipped together

Good fit Use it when saving a completed change to Git history, especially when the branch or request identifies an issue to close.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/bengous/claude-code-plugins/commit
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.

Any agent
npx skills add bengous/claude-code-plugins --skill commit
Clone the repo
git clone --depth 1 https://github.com/bengous/claude-code-plugins

Made for: Claude Code.

Or install git, the plugin that ships this one along with the rest of its 3 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for commit

README.md
[![agentmods](https://agentmods.dev/badge/skills/bengous/claude-code-plugins/commit/github.svg)](https://agentmods.dev/skills/bengous/claude-code-plugins/commit)
Your own site
<a href="https://agentmods.dev/skills/bengous/claude-code-plugins/commit"><img src="https://agentmods.dev/badge/skills/bengous/claude-code-plugins/commit/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for commit

Your own site · 80×15
<a href="https://agentmods.dev/skills/bengous/claude-code-plugins/commit"><img src="https://agentmods.dev/badge/skills/bengous/claude-code-plugins/commit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 456 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00049 $0.00456
Opus 5 $0.00024 $0.00228
Sonnet 5 $0.00010 $0.00091
Haiku 4.5 $0.00005 $0.00046

Measured today against content hash 39853e4dde17, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, 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 today.

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.

git/skills/commit/SKILL.md · 24 lines

What it actually says

Commit

Context

  • Status: !git status --short
  • Diff, staged and unstaged: !git diff HEAD
  • Branch: !git branch --show-current
  • Recent commits: !git log --oneline -10

Task

  1. Scope. Something staged: commit that, leave the rest alone. Nothing staged: stage what forms one commit from the diff above, leave the rest. The diff omits untracked files; they appear as ?? in the status, and a new file that the diff's changes import belongs to the same commit. A file that carries a secret is never staged, whatever the diff shows: .env and its variants, a private key, a credentials or token file. Name it and stop.
  2. Issue. A number in $ARGUMENTS, else the leading number of the branch name (fix/123-popover is 123). --no-close, or no number in either place: no trailer, and no question. Otherwise the last line of the body is Closes #<n>.
  3. Message. Follow the convention visible in the recent commits above. Subject in the imperative, no trailing period. The body says why, never what the diff shows.
  4. One batch. Stage and commit in a single tool batch, with nothing in between.
  5. Report. The happy path says nothing beyond the commit. One line, when it applies: a file left unstaged on purpose, or a Closes trailer on a branch that is not the default, since GitHub closes the issue only when the commit reaches that default branch.
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. today First seen · 24 lines · 49 tokens per session scan A 39853e4dde17

Subscribe to this mod's changes

commit is a skill published in the GitHub repository bengous/claude-code-plugins (4 stars, last pushed today), licensed MIT. It adds 49 tokens to every session and 456 once invoked, about $0.0002 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 2026-09-11.