commit

commit is a skill for Claude Code, Codex from Taketo-Yoda/uv-sbom. It costs 12 tokens per session (1,355 once invoked), scanned A, original, MIT.

A guided Git commit workflow that checks the current branch, runs code-quality checks, and creates commits using conventional commit messages. It refuses direct commits to protected branches such as main and develop.

In plain words
What is it for?
Use it to validate the branch, create or select an allowed working branch, run checks, and prepare an English commit with the required format.
Why use it?
It prevents accidental changes to protected branches and makes commit history more consistent and readable. It also gives the work a suitable feature, bugfix, hotfix, documentation, or refactoring branch when needed.

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/taketo-yoda/uv-sbom/commit
Any agent
npx skills add Taketo-Yoda/uv-sbom --skill commit
Clone the repo
git clone --depth 1 https://github.com/Taketo-Yoda/uv-sbom

Made for: Claude Code, Codex.

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/taketo-yoda/uv-sbom/commit.svg)](https://agentmods.dev/skills/taketo-yoda/uv-sbom/commit)
Your own site
<a href="https://agentmods.dev/skills/taketo-yoda/uv-sbom/commit"><img src="https://agentmods.dev/badge/skills/taketo-yoda/uv-sbom/commit.svg" alt="Measured on agentmods" height="20"></a>
Per session 12 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,355 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 $0.00012 $0.01355
Opus 5 $0.00006 $0.00678
Sonnet 5 $0.00002 $0.00271
Haiku 4.5 $0.00001 $0.00136

Measured today against content hash 27ec0afff4c2, 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 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.

.claude/skills/commit/SKILL.md · 243 lines

How it starts

The opening of the file, as written. The whole thing — 243 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/commit - Commit Creation Skill

Create commits with proper code quality checks and conventional commit messages.

Language Requirement

IMPORTANT: All commit messages MUST be written in English.

Step 0: Verify Branch (MANDATORY)

CRITICAL: This step MUST be performed before any other step.

Check Current Branch

git branch --show-current

Branch Validation Rules

Current Branch Action
main STOP - Never commit directly to main
develop STOP - Never commit directly to develop
feature/* ✅ Proceed with commit
bugfix/* ✅ Proceed with commit
hotfix/* ✅ Proceed with commit
docs/* ✅ Proceed with commit
refactor/* ✅ Proceed with commit

If on develop or main

  1. STOP immediately - Do not proceed with commit
  2. Inform the user about the branch policy violation
  3. Create a feature branch:
    git fetch origin
    git checkout -b feature/<issue-number>-<description> origin/develop
    
  4. After branch creation, proceed with the commit workflow

Error Message Template

If on protected branch, display:

⚠️ ERROR: Cannot commit directly to '{branch_name}' branch.

This project uses Git Flow. Please create a feature branch first:
  git checkout -b feature/<issue>-<description> origin/develop

See .claude/instructions.md for branching guidelines.

Pre-flight Checks (MANDATORY)

Note: cargo fmt is handled automatically by the .githooks/pre-commit hook. cargo clippy and cargo test are handled by the .githooks/pre-push hook at push time. Run make setup once to activate these hooks if you haven't already.

1. Security Check

Verify no secrets in staged files:

  • No API keys
  • No passwords or credentials
  • No tokens or secret strings
  • No .env files with real values
  • No credentials.json or similar

Files to check: git diff --cached --name-only

If secrets are found:

Read the full file on GitHub · 243 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. today First seen · 243 lines · 12 tokens per session scan A 27ec0afff4c2

Subscribe to this mod's changes

commit is a skill published in the GitHub repository Taketo-Yoda/uv-sbom (5 stars, last pushed today), licensed MIT. It adds 12 tokens to every session and 1,355 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 2026-09-04.