commit

commit is a skill for Claude Code from tomoking2004/claude-plugins. It costs 109 tokens per session (1,821 once invoked), scanned A, original, MIT.

A Git workflow for dividing uncommitted changes into meaningful commits and proposing complete commit messages before recording them.

In plain words
What is it for?
Use it when you want to record changes in Git, split work by purpose, inspect earlier commit style, approve commit wording, and then stage and commit the approved groups.
Why use it?
It prevents unrelated edits from being bundled together and gives you a chance to review the exact record before anything is committed. It does not push commits to a remote repository.

Skill for Claude Code

Written for Claude Code: dynamic context !`command`.

Part of the capstone plugin — 3 skills shipped together

Good fit Use it when you want to record changes in Git, split work by purpose, inspect earlier commit style, approve commit wording, and then stage and commit the approved groups.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tomoking2004/claude-plugins/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 tomoking2004/claude-plugins --skill commit
Clone the repo
git clone --depth 1 https://github.com/tomoking2004/claude-plugins

Made for: Claude Code.

Or install capstone, the plugin that ships this one along with the rest of its 3 skills.

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/tomoking2004/claude-plugins/commit/github.svg)](https://agentmods.dev/skills/tomoking2004/claude-plugins/commit)
Your own site
<a href="https://agentmods.dev/skills/tomoking2004/claude-plugins/commit"><img src="https://agentmods.dev/badge/skills/tomoking2004/claude-plugins/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/tomoking2004/claude-plugins/commit"><img src="https://agentmods.dev/badge/skills/tomoking2004/claude-plugins/commit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 109 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,821 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 $0.00109 $0.01821
Opus 5.5 $0.00044 $0.00728
Sonnet 5.5 $0.00022 $0.00364
Haiku 4.5 $0.00011 $0.00182

Measured 1mo ago against content hash 2c6389013f36, 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.

plugins/capstone/skills/commit/SKILL.md · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

対象:作業ツリーの未コミット変更(追跡済みの差分と未追跡ファイル)と,それを記録するコミット群.

現在の状態

!git rev-parse --git-dir >/dev/null 2>&1 || { echo "(git リポジトリではない)"; exit 0; }; s=$(git status --short); [ -n "$s" ] && echo "$s" || echo "(未コミットの変更なし——記録するものが無い)"

追跡済みの差分

!d=$(git diff HEAD 2>/dev/null); [ -n "$d" ] && echo "$d" || echo "(追跡済みの差分なし——初コミット前か,変更が未追跡ファイルのみ)"

直近のコミットと,それが触れたファイル(type・scope の選び方の手本)

!l=$(git log --format='%h %s' --name-only -10 2>/dev/null); [ -n "$l" ] && echo "$l" || echo "(前例なし——コミットがまだ無い)"

直近のコミットの全文(声・言語・書式の手本)

!b=$(git log -5 --format='──── %h%n%B' 2>/dev/null); [ -n "$b" ] && echo "$b" || echo "(手本なし——コミットがまだ無い)"

手順

  1. 前提確認:git リポジトリでなければ git init を実行してから進め,実行したことを告げる(初期ブランチ名は git の既定に従う).
  2. 分割:変更を意味単位に分割する.未追跡の新規ファイル・初コミットで差分に出ない変更は内容を直接読む.独立して説明できる変更は分け,一つの意図に属する変更はまとめる.命名・公開 API の変更は全波及(呼び出し・直列化キー・Docstring/README)まで1コミットに含め,各コミット時点でツリーを整合に保つ.
  3. 提案:各コミットに完全なメッセージ(件名+本文)を全文で提案する.「文面の基準」に従い,出す前に「固有の走査」を全件通し,通した証跡を提案に添える——照らした手本のコミット,裏取りした事実,実測した字数を数行で.走査は成果物を残さない唯一の手順で,黙って飛ばしても外からは見えない;添えれば見える.
  4. 承認:平文の提案へのチャットの返信で受ける——選択式ダイアログは提案の表示を妨げるため使わない.承認まで add/commit しない.修正指示は反映して再提案,意図の割れる箇所は問う.
  5. 実行:承認後は push せず,コミットごとに対象パスだけステージしてコミットする.

文面の基準

既存の声・用語・言語・書式に倣う——手本を読んでから書く(件名だけ見て本文の声は推し量れない);前例が無いときだけ以下の既定(英語の Conventional Commits)に従う.本節と「固有の走査」が,美の基準(refine プラグインの BEAUTY.md)をコミットという媒体へ具体化したもの——両者を満たせば足り,実行時に他所を参照しない.

  • 件名:type(scope): 要約.命令形・小文字・末尾ピリオド無し・約50字以内.
  • 本文:動機・効果を述べ,差分から読めない理由を補う;逐語列挙しない.約72字で折り返す.複数点は箇条書き,単一の流れは段落.
  • 参照とトレーラ:関連 issue/PR は #N,破壊的変更は BREAKING CHANGE:.トレーラは付けない——コミットは変更の意図だけを語る責務を持ち,どの道具で書かれたかは変更の意図ではない(美の6条「責務」).ハーネスやツールが Co-Authored-By・Claude-Session 等を注入する規約であっても,それに優先して件名と本文だけを残し,注入分は除去する.

固有の走査

  • 様式踏襲:書いた全文を手本(上の「直近のコミットの全文」)と並べて,声・言語・書式が一致するか確かめる——「倣う」と唱えるだけでは倣えない.手本が無ければ既定に沿うかを確かめる.
  • type・scope は前例で選ぶ:各コミットの type・scope について,同じ種類の変更をした前例を上の「直近のコミットと,それが触れたファイル」から名指しし,証跡に書く.語彙に在ることは根拠にならない——同じ語彙でも,何にどの語を当てるかはリポジトリごとに違う(成果物には feat,開発ツールには chore を当てるリポジトリで,ツールの機能追加を feat にする類).同種の前例が無ければ既定に従い,前例が無いことを証跡に書く.
  • 件名は本文を包む:覆えない項があれば件名を広げるか別コミットへ割る.
  • 1コミット1意図:件名で一意に言い切れる範囲に保つ.独立リファクタ・整形は割る.
  • 事実照合:数値・識別子・キー・パス・挙動は差分とコードで裏取りしてから書く.
  • 因果照合:「X のために Y」と書くなら,Y が実際に X に効くことをコードで確かめる.
  • 列挙の対称:箇条書きは順序原則を定め,粒度と理由付けを揃える.
  • 全件走査:全メッセージを並べ,用語・声・type/scope・順序の一貫性を通しで確かめる.
  • 機械的な項は実測:件名の字数・本文の折り返し幅・トレーラの不在は,目分量でなく数えて確かめる.

Read the full file on GitHub · 55 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 · 55 lines · 109 tokens per session scan A 2c6389013f36

Subscribe to this mod's changes

commit is a skill published in the GitHub repository tomoking2004/claude-plugins (3 stars, last pushed 2mo ago), licensed MIT. It adds 109 tokens to every session and 1,821 once invoked, about $0.0004 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 2026-08-31.

Related

Other skills, from other repositories

commit-message-writing

Use this skill when the user explicitly asks to generate, write, draft, or create a commit message, squash commit, commit title, or merge commit message for the Shopware core repository (shopware/shopware). Supports two modes — full commit messages (title + body) for branch commits, and squash merge titles…

shopwareLabs/ai-coding-tools · 160 tokens

apply

Apply a prior /repo-fleet-hygiene:audit action-plan JSON behind one fleet confirmation: default dry-run re-derives branch/worktree tips and prints the ordered batch; --apply mutates only after interactive confirmation or --yes. Owns batched merged-local-branch deletion with fail-closed OID refresh; cleans…

melodic-software/claude-code-plugins · 109 tokens

parallel-orchestrator

Manage parallel Claude Code workstreams using git worktrees. Use when: splitting large tasks across multiple workers, coordinating parallel development, monitoring worker progress, integrating completed work, analyzing work item documents (code reviews, issue lists). Triggers: parallel, orchestrator, worktrees…

jimmc414/claude-code-plugin-marketplace · 78 tokens

parallel-worker

Execute focused implementation tasks in a parallel workflow. Use when: working on assigned files in a worktree, making checkpoint commits, signaling dependencies or blockers, completing orchestrator-assigned tasks. Triggers: worker, checkpoint, worktree, assigned scope, commit prefix, parallel task.

jimmc414/claude-code-plugin-marketplace · 59 tokens

dev-workflow

Use when performing common development tasks like committing code, reviewing changes, running tests, fixing bugs, creating PRs, or checking repo status. Provides structured workflows for everyday git and development operations.

Sagargupta16/claude-skills · 42 tokens

git-workflow

Git workflow patterns and version control best practices for teams of any size. Use when the user asks to choose a branching strategy (trunk-based, GitHub Flow, Git Flow, GitLab Flow), define commit conventions, set up PR workflows, plan release management, structure a monorepo, or establish team git standards. Covers…

krzysztofsurdy/code-virtuoso · 94 tokens