commit

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 CodeCodex

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 skills/ruchernchong/claude-kit/commit
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, Codex.

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. 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 $0.00010 $0.00736
Opus 5 $0.00005 $0.00368
Sonnet 5 $0.00002 $0.00147
Haiku 4.5 $0.00001 $0.00074

Measured yesterday against content hash bf57951d445b, 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.

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. yesterday 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 3mo ago), licensed MIT. It adds 10 tokens to every session and 736 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 2026-09-01.

Related

Other skills, from other repositories

agent-code-analyzer

Agent skill for code-analyzer - invoke with $agent-code-analyzer.

ruvnet/ruflo · 19 tokens

foundry-config-setup

Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.

microsoft/agent-framework · 65 tokens

haiku

When writing a haiku for this bot, follow these conventions.

agno-agi/agno · 0 tokens

deploy-docker-compose

Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack…

omnigent-ai/omnigent · 84 tokens

azure-mgmt-botservice-dotnet

Azure Resource Manager SDK for Bot Service in .NET. Management plane operations for creating and managing Azure Bot resources, channels (Teams, DirectLine, Slack), and connection settings. Triggers: "Bot Service", "BotResource", "Azure Bot", "DirectLine channel", "Teams channel", "bot management .NET", "create bot".

microsoft/skills · 78 tokens

dogfood

Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.

callstack/agent-device · 55 tokens