git-skills

A collection of Git workflow skills and a safety hook for common repository operations. Git is a tool for tracking code changes, branches, and shared history.

In plain words
What is it for?
Use it for commit planning, diff reviews, branch-based parallel work, rebasing, resetting, cleanup after merges, and combining review results. It is aimed at safer day-to-day Git work.
Why use it?
It adds structured procedures for commits, reviews, rebasing, resetting, and working in parallel branches. The safety hook helps prevent risky history-changing commands from running without the required safeguards.

Plugin for Claude 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.

Claude Code
/plugin marketplace add yasunori0418/skills
agentmods
npx agentmods add plugins/yasunori0418/skills/git
Clone the repo
git clone --depth 1 https://github.com/yasunori0418/skills

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

git-skills 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 2d 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.

skills/git/.claude-plugin/plugin.json · 26 lines

What it actually says

{
  "$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json",
  "name": "git-skills",
  "description": "git 運用スキル群(commit-flow / commit-plan / diff-review / rebase-flow / reset-flow / parallel-worktree / review-converge)と、rebase/reset を安全運用へ強制する git-guard hook。",
  "version": "0.4.0",
  "author": {
    "name": "yasunori0418"
  },
  "license": "MIT",
  "keywords": ["claude-code", "agentskills", "git"],
  "skills": [
    "./commit-flow",
    "./commit-plan",
    "./diff-review",
    "./parallel-worktree",
    "./post-merge-cleanup",
    "./rebase-flow",
    "./reset-flow",
    "./review-converge"
  ],
  "agents": [
    "./diff-review/agents/diff-reviewer.md",
    "./review-converge/agents/review-aggregator.md"
  ]
}
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. 2d ago First seen · 26 lines scan A a9b40c8c0dd6

Subscribe to this mod's changes

git-skills is a plugin published in the GitHub repository yasunori0418/skills (9 stars, last pushed 2d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.