commit-code

commit-code is a skill for Claude Code, Codex from JimmyPaolini/codebase. It costs 35 tokens per session (3,954 once invoked), scanned A, original, MIT.

A commit-message guide for this codebase. It defines the required format, including a change type, optional scope, Gitmoji emoji, and short subject.

In plain words
What is it for?
Use it when creating commits or checking how a commit message should be formatted.
Why use it?
It prevents commit messages from failing automated checks because they use the wrong format, type, length, or extra sections.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents); mentions AGENTS.md.

Good fit Use it when creating commits or checking how a commit message should be formatted.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jimmypaolini/codebase/commit-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.

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

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-code

README.md
[![agentmods](https://agentmods.dev/badge/skills/jimmypaolini/codebase/commit-code/github.svg)](https://agentmods.dev/skills/jimmypaolini/codebase/commit-code)
Your own site
<a href="https://agentmods.dev/skills/jimmypaolini/codebase/commit-code"><img src="https://agentmods.dev/badge/skills/jimmypaolini/codebase/commit-code/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-code

Your own site · 80×15
<a href="https://agentmods.dev/skills/jimmypaolini/codebase/commit-code"><img src="https://agentmods.dev/badge/skills/jimmypaolini/codebase/commit-code.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,954 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 $0.00035 $0.03954
Opus 5.5 $0.00014 $0.01582
Sonnet 5.5 $0.00007 $0.00791
Haiku 4.5 $0.00003 $0.00395

Measured 22d ago against content hash c12b740c75c5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

commit-code 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 22d 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.

.agents/skills/commit-code/SKILL.md · 336 lines

How it starts

The opening of the file, as written. The whole thing — 336 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Commit Message Conventions

This skill teaches how to write commit messages for this codebase. All commits must follow these rules to pass pre-commit checks and CI validation.

Format

<type>(<scope>): <gitmoji> <subject>

Note: Footer sections are forbidden by commitlint configuration. Body is forbidden unless every line is a Co-authored-by: trailer added by a coding agent. The casing is not checked — Co-authored-by: and Co-Authored-By: are the same trailer to git and to GitHub.

Structure Rules

  1. Header: <type>(<scope>): <gitmoji> <subject> (required)
    • Must start with gitmoji emoji (gitmoji-required, error level 2)
    • Max 128 characters (header-max-length: 128)
    • Subject must not be empty (subject-empty: never)
  2. Body: Forbidden unless every line is a Co-authored-by: trailer, in any casing (body-co-authored-only, error level 2)
  3. Footer: Forbidden (footer-empty: always, error level 2)

Type

Required. Must be one of the allowed types defined in conventional.config.cjs (enforced by type-enum rule, error level 2).

Case: Must be lowercase (type-case: lower-case, error level 2)

Type Description
feat A new feature or capability that adds value for users
fix A bug fix that addresses a specific issue or problem
docs Documentation, AGENTS.md, SKILL.md, README, and planning files
test Adding or correcting unit, integration, or end-to-end tests
refactor Code restructuring that neither fixes a bug nor adds a feature
style Formatting, whitespace, or code structure changes with no semantic effect
perf A code change that improves performance (caching, query optimization, etc.)
chore Housekeeping that doesn't modify src or test files (gitignore, editor config, etc.)
ci GitHub Actions workflows, composite actions, and CI/CD scripts
build Build system, Vite/Docker/Helm config, or external dependency integration
revert Reverts a previous commit

Read the full file on GitHub · 336 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. 22d ago Changed c12b740c75c5
  2. 26d ago Changed · +1 lines 41a70135205a
  3. 1mo ago Changed · -1 lines 5ba6181ffa8a
  4. 1mo ago Changed ccc189ea5df1
  5. 1mo ago First seen · 336 lines · 35 tokens per session scan A 33c7213ac5b4

Subscribe to this mod's changes

commit-code is a skill published in the GitHub repository JimmyPaolini/codebase (0 stars, last pushed 19d ago), licensed MIT. It adds 35 tokens to every session and 3,954 once invoked, about $0.0001 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.