commit

A procedure for making one focused Git commit with a conventional message. Git is a version-control system, and a commit records a selected set of changes in a project.

In plain words
What is it for?
Use it when saving changes to inspect the diff, stage only the intended files, choose the appropriate commit type, and write a concise message explaining unusual decisions.
Why use it?
It prevents unrelated files from being bundled together and makes the history easier to review and understand.

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/congchuanling-dot/cohort/commit
Any agent
npx skills add congchuanling-dot/Cohort --skill commit
Clone the repo
git clone --depth 1 https://github.com/congchuanling-dot/Cohort

Made for: Claude Code, Codex.

Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,019 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 $0.00059 $0.01019
Opus 5 $0.00030 $0.00509
Sonnet 5 $0.00012 $0.00204
Haiku 4.5 $0.00006 $0.00102

Measured 2d ago against content hash 2c96e34fa8bb, 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.

.cohort/skills/commit/SKILL.md · 133 lines

How it starts

The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior engineer enforcing atomic, FAANG-level commit discipline.

Rules

  • Atomic — one logical change per commit, never mix features with docs or refactors
  • Never use git add . or git add -A — always stage specific files
  • Conventional Commits format: type(scope): short imperative description
  • Body required when there are non-obvious decisions — explain the why, not the what
  • No body needed when the subject line is self-explanatory
  • Subject line: max 72 characters, imperative mood ("add" not "added")
  • Body: prose only — no bullets, no numbered lists, no dashes
  • Body: max 2 sentences — if you need more, the commit is too big
  • Body: wrap at 72 characters per line
  • No AI attribution — no Co-Authored-By, no Claude mentions

Commit types

Type When
feat New feature or test slice
fix Bug fix
refactor Code change with no behaviour change
test Adding or updating tests only
docs README, comments, ADRs
chore Config, dependencies, CI
perf Performance improvement

Process

Step 1 — Discover changes

Run git status and git diff to understand what changed. List the changed files and ask the user which ones to include if $ARGUMENTS is empty. If $ARGUMENTS specifies files, stage only those.

If there are no changes (clean working tree), tell the user and stop.

Step 2 — Analyse the changes

Read the staged files to understand what changed, why, and what type applies.

Split test — ask these three questions:

  1. Can I revert one change without losing the other? (e.g. config vs applying config)
  2. Would the diff make sense to a reviewer as a single unit?
  3. Does the subject line need "and"? If yes, it's two commits.

If any answer points to a split, recommend it with the specific grouping (e.g. "config files in commit 1, formatted code in commit 2").

Step 3 — Draft the commit message

Write subject line + body if needed.

Body is required when:

  • A non-obvious technical decision was made (e.g. returning Locator instead of string[])
  • A pattern was chosen over an alternative (e.g. guard assertion before removal)
  • A known pitfall was avoided (e.g. race condition, unfalsifiable test)

Read the full file on GitHub · 133 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 · 133 lines · 59 tokens per session scan A 2c96e34fa8bb

Subscribe to this mod's changes

commit is a skill published in the GitHub repository congchuanling-dot/Cohort (144 stars, last pushed 17d ago), licensed MIT. It adds 59 tokens to every session and 1,019 once invoked, about $0.0003 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.