commit-style

commit-style is a skill for Claude Code, Codex from karashiiro/agent-skills. It costs 63 tokens per session (611 once invoked), scanned A, original, Unlicense.

A commit-writing guide for creating Git commits in a specified conventional format, such as `fix(auth): ...`, after reviewing the changes.

In plain words
What is it for?
Use it when preparing a commit to inspect status and diffs, decide what to stage, draft the message, and follow the project’s formatting rules.
Why use it?
It keeps commit messages consistent and makes sure the proposed commit includes only the intended files and changes.

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

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-style

README.md
[![agentmods](https://agentmods.dev/badge/skills/karashiiro/agent-skills/commit-style.svg)](https://agentmods.dev/skills/karashiiro/agent-skills/commit-style)
Your own site
<a href="https://agentmods.dev/skills/karashiiro/agent-skills/commit-style"><img src="https://agentmods.dev/badge/skills/karashiiro/agent-skills/commit-style.svg" alt="Measured on agentmods" height="20"></a>
Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 611 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 $0.00063 $0.00611
Opus 5 $0.00032 $0.00305
Sonnet 5 $0.00013 $0.00122
Haiku 4.5 $0.00006 $0.00061

Measured 3d ago against content hash 94c8ba42b410, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

commit-style 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 3d 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.

commit-style/SKILL.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Commit Changes

Create a git commit using conventional commits format.

Commit Style

  • Format: type(scope): description or type: description
  • Types: feat, fix, docs, chore (minimal set)
  • Scope: Optional, use when it adds clarity (e.g., feat(auth):, fix(ipc):)
  • No AI attribution by default: Do not add "Generated with Claude Code" or Co-Authored-By lines unless required by the project standards (always check, first)
  • No emojis: Keep messages plain text

Verbosity Rules

  • Small changes (~1-4 files, simple modification): Title only, ~50-72 chars
  • Medium changes (5-7 files, related modifications): Title + 1-3 sentence body
  • Large changes (8+ files or significant feature): Title + bullet point list

Workflow

Note: For steps where it says to ask for directions, use your question tools, if available.

  1. Show current status: Run git status to see all changes
  2. Show diff summary: Run git diff --stat for overview, git diff for details if needed
  3. Interactive staging: Ask which files/changes to include in this commit
  4. Draft message: Based on staged changes, draft a conventional commit message
  5. Review: Show the proposed message and ask for approval or edits
  6. Commit: Execute the commit (without --no-verify unless requested)

Instructions

Follow this workflow step by step. Be concise in your communication. When showing diffs, summarize large changes rather than dumping everything.

For the commit message:

  • Use imperative mood ("Add feature" not "Added feature")
  • First line should be under 72 characters
  • If body is needed, separate from title with blank line
  • Body lines should wrap at 72 characters

Example small commit:

docs: add design documentation index

Example medium commit:

feat(auth): implement OAuth token refresh

Add automatic token refresh when access token expires within 5 minutes.
Tokens are persisted to OS keychain via frontend IPC.

Example large commit:

docs: overhaul documentation

- Add cross-platform backend path resolution to frontend-architecture.md
- Clarify multi-turn conversation status in backend-adapter.md
- Create ROADMAP.md with phase breakdown
- Add asset authoring timeline to animation-system.md
- Create design docs index page

Read the full file on GitHub · 68 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. 3d ago First seen · 68 lines · 63 tokens per session scan A 94c8ba42b410

Subscribe to this mod's changes

commit-style is a skill published in the GitHub repository karashiiro/agent-skills (2 stars, last pushed 4mo ago), licensed Unlicense. It adds 63 tokens to every session and 611 once invoked, about $0.0003 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 2026-08-31.

Related

Other skills, from other repositories

contributing

How to contribute to evlog, covering commit and PR conventions, changesets, the Definition of Done, testing rules, and the authored skills that walk through building a new adapter, enricher, framework integration, or map rule. Load this for any question about contributing, opening a PR, or adding something to the…

HugoRCD/evlog · 68 tokens

commit-push-pr

Commit selected local changes, push the branch, and create or update a GitHub pull request with BitFun attribution. Use when the user asks to 提交 PR、提代码、commit and push、开 PR、create a pull request, or wants a Claude Code-like one-command PR publishing flow from BitFun.

GCWing/BitFun · 68 tokens

git-commit

Creates git commits following Conventional Commits format with type/scope/subject and detailed markdown body. Use when user wants to commit changes, create commit, save work, or stage and commit. Enforces project-specific conventions from CLAUDE.md. Each change type gets its own markdown heading (# emoji + type), with…

redai-infra/Relax · 73 tokens

commit

Create a signed git commit following Conventional Commits, after running /pre-commit and /changelog when appropriate.

mihai-dinculescu/tapo · 24 tokens

commit

Read this skill before making git commits.

HazAT/pi-config · 9 tokens

et-git

ET git workflow for preparing commits and reviewing changes. Use when checking git status or diff, filtering unrelated files, staging task-scoped changes, writing Chinese commit messages, or synchronizing with remotes using rebase instead of merge.

FlameskyDexive/Legends-Of-Heroes · 50 tokens