commit-push

commit-push is a skill for Claude Code from minorun365/my-claude-code-settings. It costs 38 tokens per session (1,296 once invoked), scanned A, original, MIT.

A Japanese guide for reviewing all local Git changes, grouping them into sensible commits, and pushing them to the remote repository. Git is a tool for tracking code changes, while a remote repository is the shared copy hosted elsewhere.

In plain words
What is it for?
Use it to inspect repository status, plan logical commit groups, include untracked files, commit local changes, check for commits not yet on the remote, and push them when an origin remote is configured.
Why use it?
It reduces the risk of pushing an unclear mixture of changes or overlooking files that are staged, unstaged, new, or committed locally but not yet uploaded. It also adapts the review method to the size of the change set.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

Good fit Use it to inspect repository status, plan logical commit groups, include untracked files, commit local changes, check for commits not yet on the remote, and push them when an origin remote is configured.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/minorun365/my-claude-code-settings/commit-push
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 minorun365/my-claude-code-settings --skill commit-push
Clone the repo
git clone --depth 1 https://github.com/minorun365/my-claude-code-settings

Made for: Claude Code.

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-push

README.md
[![agentmods](https://agentmods.dev/badge/skills/minorun365/my-claude-code-settings/commit-push/github.svg)](https://agentmods.dev/skills/minorun365/my-claude-code-settings/commit-push)
Your own site
<a href="https://agentmods.dev/skills/minorun365/my-claude-code-settings/commit-push"><img src="https://agentmods.dev/badge/skills/minorun365/my-claude-code-settings/commit-push/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-push

Your own site · 80×15
<a href="https://agentmods.dev/skills/minorun365/my-claude-code-settings/commit-push"><img src="https://agentmods.dev/badge/skills/minorun365/my-claude-code-settings/commit-push.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,296 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 2 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Tool Misuse · line 89
    Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
    Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
  • medium Excessive Agency · line 5
    Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.
    Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
How audits are shown
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 $0.00038 $0.01296
Opus 5.5 $0.00015 $0.00518
Sonnet 5.5 $0.00008 $0.00259
Haiku 4.5 $0.00004 $0.00130

Measured 27d ago against content hash 7515cd37cf88, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

commit-push 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 27d 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.

claude/skills/commit-push/SKILL.md · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

未プッシュ変更の一括コミット&プッシュ

カレントディレクトリのGitリポジトリにある未プッシュの変更(unstaged、staged、untracked)をすべて確認し、論理的に適切な単位でコミットを分割してからプッシュします。

前提条件

  • カレントディレクトリがGitリポジトリであること
  • リモート(origin)が設定されていること

実行手順

Step 1: リポジトリの状態を確認

git status
git log --oneline origin/$(git branch --show-current)..HEAD 2>/dev/null

以下の3種類の変更を把握する:

  • 未コミットの変更: unstaged(変更済み)、staged(ステージ済み)、untracked(新規ファイル)
  • 未プッシュのコミット: ローカルにあってリモートにまだプッシュされていないコミット

未コミットの変更がない場合は Step 2・3 をスキップして Step 4 へ進む。 未コミットの変更も未プッシュのコミットもない場合は「プッシュする変更はありません」と伝えて終了する。

Step 2: 変更内容を分析してコミット分割案を作成

まず変更規模だけを確認する(生 diff を親コンテキストに取り込まない):

git diff --stat
git diff --cached --stat
git ls-files --others --exclude-standard
規模で処理を分岐する(重要:Prompt is too long 対策)

git diff --stat の合計行数 / ファイル数で処理方針を変える:

  • 小規模: 合計 500行未満 かつ ファイル数 20未満 → 親エージェントで処理。必要なら個別に git diff -- <path> で本文確認
  • 大規模: 上記を超える場合 → Agent ツール(subagent_type=general-purpose)に分割判定を委譲

大規模時のサブエージェント委譲プロンプトは自己完結で書く(親コンテキストを参照させない):

  • リポジトリの絶対パス
  • 「git status と git diff / git diff --cached を自分で実行して読み、下記の基準で論理単位のコミットに分割する計画を立ててほしい」
  • 下記の分割基準を再掲
  • 戻り値フォーマット: [{"message": "1行日本語メッセージ", "files": ["path1", "path2"]}, ...] の JSON のみ(diff本文は返さない)

親はサブエージェントが返した JSON だけを受け取り、Step 3 以降の git add / git commit は親が実行する。これにより親のコンテキストに生 diff が流入せず Prompt is too long を回避できる。

分割基準
  • 同じ機能・目的に関する変更はまとめる(例: 特定の機能追加に関するソース+テスト+設定)
  • 異なる目的の変更は分ける(例: バグ修正とリファクタリングは別コミット)
  • 設定ファイルの変更(.gitignore、package.json等)は関連する変更と一緒にするか、独立させる
  • ドキュメントの変更は内容に応じて関連コミットに含めるか独立させる
  • 判断に迷う場合は少なめに分割する(1つにまとめてOK)

Step 3: 分割案に従ってコミット

分析結果に基づき、各コミットを順番に自動実行する。

# コミット1
git add <ファイル群>
git commit -m "コミットメッセージ"

# コミット2
git add <ファイル群>
git commit -m "コミットメッセージ"
  • コミットメッセージは1行の日本語でシンプルに書く
  • ユーザーがコミットメッセージを指定した場合はそれを優先する

Step 4: プッシュ

すべてのコミットが完了したら(または既存の未プッシュコミットのみの場合)プッシュする。

git push
  • 上流ブランチが未設定の場合は git push -u origin $(git branch --show-current) を使う
  • プッシュ失敗時はエラー内容をユーザーに伝え、対処法を提案する

Read the full file on GitHub · 107 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. 27d ago Changed · -1 lines 7515cd37cf88
  2. 1mo ago First seen · 108 lines · 38 tokens per session scan A 7fd192378957

Subscribe to this mod's changes

commit-push is a skill published in the GitHub repository minorun365/my-claude-code-settings (142 stars, last pushed yesterday), licensed MIT. It adds 38 tokens to every session and 1,296 once invoked, about $0.0002 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 2026-08-30.