git-commit-helper

A workflow for making Git commits, saved checkpoints of code changes, in safe and meaningful groups.

In plain words
What is it for?
Use it to inspect staged and unstaged changes, split work into commits, write commit messages, and protect sensitive files.
Why use it?
It helps keep project history understandable while checking that passwords, keys, temporary files, and generated files are not included.

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/iofold/ainative-claude-plugins/git-commit-helper
Any agent
npx skills add iofold/ainative-claude-plugins --skill git-commit-helper
Clone the repo
git clone --depth 1 https://github.com/iofold/ainative-claude-plugins

Made for: Claude Code, Codex.

Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,093 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 $0.00071 $0.01093
Opus 5 $0.00036 $0.00547
Sonnet 5 $0.00014 $0.00219
Haiku 4.5 $0.00007 $0.00109

Measured yesterday against content hash da108aef99e5, 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-helper 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 yesterday.

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.

developer-workflow/skills/git-commit-helper/SKILL.md · 190 lines

How it starts

The opening of the file, as written. The whole thing — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Git Commit Helper

Safe, chunked commits with best practices and sensitive file protection.

Workflow

Step 1: Analyze Current State

# Full status
git status --porcelain

# Staged changes
git diff --staged --stat

# Unstaged changes
git diff --stat

Step 2: Detect Sensitive Files (CRITICAL)

Before ANY commit, check for files that should NEVER be committed:

Sensitive patterns:

  • .env, .env.* (except .env.example)
  • *.pem, *.key, *.p12, *.pfx, *.secret
  • credentials.json, secrets.json, secrets.yaml, token.json
  • service-account*.json, .npmrc, .pypirc

Temporary/Generated:

  • .tmp/, tmp/, *.log, *.cache, __pycache__/
  • node_modules/, dist/, build/, .next/
  • *.local (local config overrides)

Detection command:

git status --porcelain | grep -iE '\.(env|pem|key|secret|log|sqlite|db|local)$|credentials|secrets|token|\.tmp|node_modules|__pycache__|\.cache'

If sensitive files found:

  1. Unstage them: git reset HEAD <file>
  2. Check .gitignore: cat .gitignore 2>/dev/null
  3. Suggest additions:
    .env
    .env.*
    !.env.example
    *.pem
    *.key
    *.secret
    .tmp/
    *.log
    *.local
    
  4. DO NOT proceed until resolved

Step 3: Group Changes into Chunks

Group related changes for atomic commits:

By type:

  • Features: new files, new functions
  • Fixes: modifications to existing logic
  • Refactors: restructuring without behavior change
  • Docs: README, comments, docs/
  • Config: package.json, tsconfig, etc.
  • Tests: test files with their implementations

Commands:

git diff --name-status
git diff --name-only | grep -E 'test|spec'
git diff --name-only | grep -E 'config|\.json$|\.yaml$'

Step 4: Commit with Proper Messages

Format (conventional commits):

<type>(<scope>): <description>

[body - explain WHY not just WHAT]

[footer - breaking changes, issue refs]

Types:

  • feat: New feature
  • fix: Bug fix
  • docs: Documentation
  • style: Formatting only
  • refactor: Code restructure
  • test: Tests
  • chore: Maintenance, deps

Read the full file on GitHub · 190 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. yesterday First seen · 190 lines · 71 tokens per session scan A da108aef99e5

Subscribe to this mod's changes

git-commit-helper is a skill published in the GitHub repository iofold/ainative-claude-plugins (3 stars, last pushed 13d ago), licensed MIT. It adds 71 tokens to every session and 1,093 once invoked, about $0.0004 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens