git-commit

A workflow for making a local Git commit safely using Conventional Commits, a standard format such as `fix(auth): handle expired tokens`. It covers reviewing changes, staging them, checking tests and documentation, and choosing a commit type.

In plain words
What is it for?
Use it when committing completed changes or reviewing staged changes. It helps create commits for features, fixes, tests, documentation, refactoring, maintenance, formatting, and performance work.
Why use it?
It helps keep commits focused, consistently named, and based on reviewed changes. It also avoids using this workflow for history rewriting or interactive rebasing.

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/woliveiras/geremmyas/git-commit
Any agent
npx skills add woliveiras/geremmyas --skill git-commit
Clone the repo
git clone --depth 1 https://github.com/woliveiras/geremmyas

Made for: Claude Code, Codex.

Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 931 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 $0.00038 $0.00931
Opus 5 $0.00019 $0.00465
Sonnet 5 $0.00008 $0.00186
Haiku 4.5 $0.00004 $0.00093

Measured 2d ago against content hash 4d07fae84ac2, 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 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.

content/skills/git-commit/SKILL.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Git Commit

Local commits are the default after a coherent task-owned slice passes fresh tests, docs reconciliation, and independent review. This slice evidence is not the feature lifecycle state Verified; a feature may remain In Progress across several atomic commits. The primary agent owns staging and commits for integrated work; subagents do not run Git.

Format

type(scope): description

Types

  • feat — new feature or capability
  • fix — bug fix
  • docs — documentation changes only
  • test — adding or updating tests
  • refactor — code change that neither fixes a bug nor adds a feature
  • chore — maintenance tasks (deps, CI, configs)
  • style — formatting, whitespace (no code logic change)
  • perf — performance improvement

Rules

  • Use lowercase for type and description
  • Scope is optional but recommended (e.g., feat(auth): add login)
  • Description is imperative mood: "add", not "added" or "adds"
  • Keep the first line under 72 characters
  • Breaking changes: add ! after type — feat!: remove legacy API

Procedure

  1. Inspect staged and unstaged state separately with git status --short, git diff --cached, and git diff before touching the index. Record whether pre-existing staged state exists.
  2. Identify the exact task-owned files or hunks for the implementation, tests, documentation, and artifacts that form one verified slice. Exclude unrelated or ambiguous changes without asking the user to select them.
  3. Stage clean task-owned paths explicitly. For a mixed-hunk file, build and inspect a task-owned patch and apply only it with git apply --cached; never stage the whole path.
  4. If pre-existing staged state is unrelated or overlaps the slice, do not mutate or unstage it. Move the task-owned patch to an isolated worktree with its own branch and index, then verify the original index remains unchanged. An alternate index may prepare or inspect the patch, but must not advance the current branch while the original index is staged. If safe isolation is unavailable, leave the index untouched and report the blocker. Never use git add . or another repository-wide shortcut.
  5. Re-read git status --short, git diff --cached --stat, and git diff --cached after staging. Remove any unrelated, generated, local, secret-bearing, or unsafe change that this procedure staged without discarding working-tree content. Never unstage user-owned state.
  6. Derive the Conventional Commit type, scope, subject, and optional body from the complete cached diff. Re-read the cached diff after deriving the message and confirm the message still describes every staged change.
  7. Commit without asking the user to approve files, hunks, or the message.
  8. Show the created commit with git rev-parse --short HEAD and git show --stat --oneline --no-renames HEAD.
  9. If the commit fails, report the failure and leave the reviewed files staged safely for diagnosis. Do not broaden scope or mutate history to recover.

Read the full file on GitHub · 85 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. 2d ago First seen · 85 lines · 38 tokens per session scan A 4d07fae84ac2

Subscribe to this mod's changes

git-commit is a skill published in the GitHub repository woliveiras/geremmyas (10 stars, last pushed 29d ago), licensed MIT. It adds 38 tokens to every session and 931 once invoked, about $0.0002 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

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 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

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