commit

commit is a skill for Claude Code from ruchernchong/claude-kit. It costs 10 tokens per session (736 once invoked), scanned A, original, MIT.

A helper for making Git commits, which record a set of changes in Git, with short messages. It also checks that GitLeaks is configured to detect secrets before committing.

In plain words
What is it for?
Use it to prepare a secure commit, configure a Husky pre-commit check when needed, scan staged files with GitLeaks, and commit the changes.
Why use it?
It encourages consistent commit messages and helps prevent passwords, tokens, or other secrets from entering the repository.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: positional $N argument.

Good fit Use it to prepare a secure commit, configure a Husky pre-commit check when needed, scan staged files with GitLeaks, and commit the changes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ruchernchong/claude-kit/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 ruchernchong/claude-kit --skill commit
Clone the repo
git clone --depth 1 https://github.com/ruchernchong/claude-kit

Made for: Claude Code.

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/ruchernchong/claude-kit/commit/github.svg)](https://agentmods.dev/skills/ruchernchong/claude-kit/commit)
Your own site
<a href="https://agentmods.dev/skills/ruchernchong/claude-kit/commit"><img src="https://agentmods.dev/badge/skills/ruchernchong/claude-kit/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/ruchernchong/claude-kit/commit"><img src="https://agentmods.dev/badge/skills/ruchernchong/claude-kit/commit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 10 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 736 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 $0.00010 $0.00736
Opus 5.5 $0.00004 $0.00294
Sonnet 5.5 $0.00002 $0.00147
Haiku 4.5 $0.00001 $0.00074

Measured 1mo ago against content hash bf57951d445b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 1mo 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.

skills/commit/SKILL.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pre-Commit Security Check

Before committing, ensure GitLeaks is configured in the project:

  1. Check for Husky setup: Look for .husky/pre-commit
  2. Verify GitLeaks integration: Check if gitleaks protect is in the pre-commit hook
  3. Auto-configure if missing:
    • If .husky/ exists but GitLeaks is missing, add gitleaks protect --staged --verbose before any lint-staged command
    • If .husky/ doesn't exist, run npx husky init first, then configure GitLeaks

Example .husky/pre-commit with GitLeaks:

#!/usr/bin/env sh
. "$(dirname -- "$0")/_/husky.sh"

# Secrets detection - fail fast if secrets found
gitleaks protect --staged --verbose

# Lint staged files (if present)
npx lint-staged

Only proceed with the commit after confirming GitLeaks is properly configured.


Language Conventions

Infer language style from the project:

  • Analyze existing commit messages, documentation, and code comments to detect the project's language variant (US English, UK English, etc.)
  • Match the spelling conventions found in the project (e.g., "organize" vs "organise", "color" vs "colour")
  • Maintain consistency with the project's established language style throughout commit messages

Create git commits with a balanced approach - keep related changes together, split only when potentially huge:

COMMIT MESSAGE RULE: ALWAYS use short messages (max 50 characters)

  1. Pull latest changes from remote to ensure branch is up to date (git pull)
  2. Show current git status and analyse all changes
  3. Check conversation context for GitHub issue references:
    • If a GitHub issue is mentioned in the conversation, determine if changes close the issue (complete implementation) or relate to it (partial work)
    • Add appropriate footer: "Closes #123" or "Relates to #123"
    • If no issue is mentioned in context, proceed without issue reference
  4. Assess the scope of changes:
    • Small to medium changes: Keep related changes in a single commit
    • Large changes: Only split when the changeset is potentially huge and mixing unrelated functionality
  5. For normal commits:
    • Stage all related changes together
    • Create ONE short, descriptive commit message (max 50 characters)
    • Focus on the main purpose of the change
    • Add GitHub issue footer if applicable (from step 3)
  6. For huge changesets only:
    • Group by major functional areas
    • Stage files by logical groups
    • Create separate commits for distinct features/fixes

Read the full file on GitHub · 74 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. 1mo ago First seen · 74 lines · 10 tokens per session scan A bf57951d445b

Subscribe to this mod's changes

commit is a skill published in the GitHub repository ruchernchong/claude-kit (0 stars, last pushed 5mo ago), licensed MIT. It adds 10 tokens to every session and 736 once invoked, about $0.0000 per session on Opus 5.5. 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 2026-09-01.