commit

A skill that stages relevant Git changes and creates one clear commit explaining why the change was made. Git is a tool for tracking changes to code, and a commit is a saved set of those changes.

In plain words
What is it for?
Use it to inspect current changes, select the right files, and create a focused Git commit.
Why use it?
It removes the guesswork from choosing files and writing a useful commit message when the working tree contains changes.

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

Made for: Claude Code, Codex.

Per session 14 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 476 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 $0.00014 $0.00476
Opus 5 $0.00007 $0.00238
Sonnet 5 $0.00003 $0.00095
Haiku 4.5 $0.00001 $0.00048

Measured 2d ago against content hash 778b300d0349, 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.

tests/_skills_builtin/commit/SKILL.md · 42 lines

What it actually says

Commit changes

Stage the relevant changes and write a single, well-scoped git commit that explains why the change was made, not just what changed.

Take any scope or message hint from the conversation; with none given, cover all uncommitted changes.

Steps

  1. See the current state. Run git_status to list modified, staged, and untracked files, then git_diff to read the actual hunks. If the user named a scope above, limit the commit to the matching files instead of everything.
  2. Understand the change before describing it. For any hunk that isn't self-evident, read the surrounding code so the message reflects the real intent rather than a literal restatement of the diff.
  3. Decide what belongs in this commit. Keep it to one logical, self-contained change. If the working tree mixes unrelated changes, stage only the files for this commit with shell_run (git add <paths>) and leave the rest for a separate commit.
  4. Draft the message:
    • Subject line: imperative mood, concise (aim for under ~72 chars), no trailing period — e.g. fix parser crash on empty input.
    • Body (when the change isn't trivial): wrap at ~72 cols and explain the motivation and any non-obvious trade-offs. Skip the body for one-line obvious changes.
    • Match this repo's existing commit conventions if it uses them (e.g. a type(scope): prefix) — check recent history with shell_run (git log --oneline -10) before choosing a style.
  5. Create the commit with shell_run (git commit -m "..." or a heredoc for multi-line messages). Then run git_status to confirm a clean result and report the final subject line.

Do not push, open a PR, or amend existing commits unless the user explicitly asks. Never invent changes you didn't make to pad the message.

(fork agent: main)

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 · 42 lines · 14 tokens per session scan A 778b300d0349

Subscribe to this mod's changes

commit is a skill published in the GitHub repository initxy/noeta (9 stars, last pushed 4d ago), licensed Apache-2.0. It adds 14 tokens to every session and 476 once invoked, about $0.0001 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.