git-commit-integrity

git-commit-integrity is a skill for Claude Code, Codex from irahardianto/awesome-agv. It costs 136 tokens per session (2,392 once invoked), scanned A, original, MIT.

A set of checks for making sure each Git commit is a complete, working snapshot on its own. Git is a system for tracking code history, and a commit is one recorded version of that code.

In plain words
What is it for?
Use it when splitting a large change into commits, reviewing Git hooks, or checking whether a commit series builds, passes tests, and supports reliable debugging.
Why use it?
A working directory can pass tests because of changes from other commits, while an individual commit fails when checked out alone; this addresses that gap.

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/irahardianto/awesome-agv/git-commit-integrity
Any agent
npx skills add irahardianto/awesome-agv --skill git-commit-integrity
Clone the repo
git clone --depth 1 https://github.com/irahardianto/awesome-agv

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 git-commit-integrity

README.md
[![agentmods](https://agentmods.dev/badge/skills/irahardianto/awesome-agv/git-commit-integrity.svg)](https://agentmods.dev/skills/irahardianto/awesome-agv/git-commit-integrity)
Your own site
<a href="https://agentmods.dev/skills/irahardianto/awesome-agv/git-commit-integrity"><img src="https://agentmods.dev/badge/skills/irahardianto/awesome-agv/git-commit-integrity.svg" alt="Measured on agentmods" height="20"></a>
Per session 136 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,392 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 $0.00136 $0.02392
Opus 5 $0.00068 $0.01196
Sonnet 5 $0.00027 $0.00478
Haiku 4.5 $0.00014 $0.00239

Measured 4d ago against content hash 15c5c05003a5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

git-commit-integrity 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 4d 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/git-commit-integrity/SKILL.md · 195 lines

How it starts

The opening of the file, as written. The whole thing — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Git Commit Integrity

Purpose

A commit records a tree snapshot. Nothing about git commit — or a hook that runs during it — guarantees that snapshot builds, lints, or tests cleanly on its own. The only thing most tooling actually checks is "does the working directory look okay right now", and those two questions are the same only in the ordinary one-change-at-a-time workflow. They diverge the moment more than one commit's worth of work exists in the working tree at once — which is exactly the situation whenever a large, already-finished diff is being organized into multiple readable commits after the fact.

This skill exists because that divergence is easy to miss: every gate can report green and the resulting history can still contain commits that don't build if checked out alone.

When to Invoke

  • Splitting a large, already-complete diff into multiple logical commits (a refactor, a big feature, an after-the-fact history cleanup).
  • Writing or reviewing a pre-commit / pre-push hook, in any language.
  • A user or reviewer asks "is this commit series bisectable?" or "does each commit build?"
  • Before claiming a multi-commit series is clean, complete, or ready for review — verify it, don't infer it from "the hook passed."

Core Principle: A Commit Is Its Snapshot, Not Your Working Directory

Compilers, linters, and test runners (cargo, go build, pytest, tsc, eslint, rspec, ...) read the filesystem. None of them know git's index exists. A tool invoked mid-commit checks whatever is on disk at that moment — staged changes, unstaged changes, and untracked files, all mixed together indiscriminately. git status/git diff --cached can tell you what will be committed; it takes a deliberate extra step to make what a tool checks match that.

Two consequences follow directly:

  1. A passing hook is not proof a commit is buildable in isolation unless you know the hook isolates the working tree to the index before running anything filesystem-based. Most hand-written hooks don't, because it isn't obvious the gap exists until you go looking for it.
  2. Splitting a finished diff into several commits by staging subsets is not, by itself, a safe operation. Each intermediate commit's actual recorded tree may reference symbols, fields, or files that don't exist yet at that point in history, even though the ambient working directory (with later batches still sitting unstaged) compiles fine.

Read the full file on GitHub · 195 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. 4d ago First seen · 195 lines · 136 tokens per session scan A 15c5c05003a5

Subscribe to this mod's changes

git-commit-integrity is a skill published in the GitHub repository irahardianto/awesome-agv (156 stars, last pushed 14d ago), licensed MIT. It adds 136 tokens to every session and 2,392 once invoked, about $0.0007 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 2026-08-30.

Related

Other skills, from other repositories

maintaining-windows-health

Hands-on playbook for Windows 11 disk cleanup, dev-machine optimization, and proactive health alerting. Use when the PC is full or slow, when a BSOD / Kernel-Power 41 / crash dump / commit-memory pressure happened, when the user asks to free disk space, audit storage, set up disk/memory alerts, or restore the same…

CodeAlive-AI/ai-driven-development · 191 tokens

prompt-engineering

Universal prompt engineering techniques for any LLM. Use when crafting, optimizing, or reviewing prompts for AI models. Triggers on requests like "improve this prompt", "write a system prompt", "optimize my instructions", "help me prompt engineer", "audit this prompt", "review my prompt", or when building agentic…

CodeAlive-AI/ai-driven-development · 76 tokens

plugins-management

Create, publish, delete, and submit plugins for coding agents (Claude Code, OpenCode). Use when user wants to (1) create a new plugin with proper structure, (2) create or configure a plugin marketplace, (3) publish plugins to GitHub/GitLab/npm, (4) delete/uninstall plugins, (5) validate plugin structure, or (6)…

CodeAlive-AI/ai-driven-development · 96 tokens

source-command-methodology-advisor

Analyzes your codebase and asks 3 targeted questions to recommend the right AI-assisted development methodology stack.

FlorianBruniaux/claude-code-ultimate-guide · 27 tokens

installing-cli-tools

Install, upgrade, configure, and verify developer CLI tools safely. Use when a user asks to install a new CLI, command-line app, SDK tool, package-manager binary, GitHub release binary, language runtime tool, or AI/vendor CLI; configure shell PATH/completions; run first login; set API keys, tokens, or env variables…

CodeAlive-AI/ai-driven-development · 94 tokens

repo-activity-summary

Summarize a repository's recent engineering activity from git history — technologies, work types, churn hotspots, contributor patterns, and velocity. Use when asking "what has this repo been working on", "is this project active", "who contributes what", "where are the hotspots", or before onboarding onto an unfamiliar…

CodeAlive-AI/ai-driven-development · 70 tokens