commit

A guide for deciding when to create Git commits and how to keep them focused. A commit is a saved set of related changes that should leave the codebase in a coherent state.

In plain words
What is it for?
Use it when deciding whether work is ready to commit, splitting unrelated changes, checking commit scope, and following repository hooks or timing rules.
Why use it?
It prevents incomplete or mixed-purpose commits and encourages verification before changes become shared checkpoints.

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

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 645 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 $0.00645
Opus 5 $0.00036 $0.00322
Sonnet 5 $0.00014 $0.00129
Haiku 4.5 $0.00007 $0.00064

Measured 2d ago against content hash 2177210c7760, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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.

skills/commit/SKILL.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Commit

When to Commit

Commit when a unit of work is done and verified.

A commit marks a checkpoint where:

  • The task is complete (not "mostly done")
  • Tests pass (or you've verified manually for untested code)
  • The change works as intended

Don't commit:

  • As a save point ("I'll fix it later")
  • Incomplete work (use branches/stash instead)
  • Before verifying the change works

One Concern per Commit

Each commit should have one clear intention. Ask: "What does this commit do?" If the answer uses "and", split it.

✓ One Concern ✗ Mixed Concerns
Add login endpoint Add login endpoint and fix typos
Extract helper function Refactor and add new feature
Update dependencies Update deps and fix bug they exposed
Format code (auto) Format code and change logic

What Belongs Together

A single concern often spans multiple files:

  • Feature: implementation + tests + docs for that feature
  • Bugfix: fix + regression test proving it's fixed
  • Refactoring: all files affected by the structural change

The test is: "Would reverting this commit leave the codebase in a coherent state?"

What Must Be Separate

Never bundle these with functional changes:

Change Type Why Separate
Formatting/linting Obscures real changes in diff
Dependency updates Separate risk, separate rollback
Unrelated fixes Different concerns, different tickets

If you discover an unrelated issue while working: stash it, finish your task, commit, then fix the other issue separately.

Git Hooks

Most projects use pre-commit hooks (often via Husky) that run linting, tests, or formatting.

When hooks fail: Fix the issue. Hooks exist to catch problems early.

Skipping hooks (--no-verify):

  • NEVER without explicit human approval
  • Ask: "Hooks are failing because [reason]. Should I skip them with --no-verify?"

Valid reasons to skip:

  • Rebasing/squashing where hooks will re-run on final commit
  • Emergency hotfix that must reach CI immediately
  • Infrastructure changes where hooks are incompatible (e.g., pre-push hook can't run without remote)

Read the full file on GitHub · 82 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 82 lines · 71 tokens per session scan A 2177210c7760

Subscribe to this mod's changes

commit is a skill published in the GitHub repository quatico-solutions/agent-skills (2 stars, last pushed 7d ago), licensed MIT. It adds 71 tokens to every session and 645 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

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

agent-host-chat-contributions

Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.

microsoft/vscode · 56 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens