conventional-commits

A writing guide for commit messages that follow Conventional Commits, a format such as `feat(auth): add passkey login` that tools can read consistently.

In plain words
What is it for?
It is for writing, reviewing, or automating commit messages, including feature, bug-fix, documentation, refactoring, testing, and breaking-change labels.
Why use it?
It makes code history easier to scan and allows tools to generate changelogs and decide version bumps from commit types.

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/phuonghx/aim-cli/conventional-commits
Any agent
npx skills add phuonghx/aim-cli --skill conventional-commits
Clone the repo
git clone --depth 1 https://github.com/phuonghx/aim-cli

Made for: Claude Code, Codex.

Per session 94 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,113 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 $0.00094 $0.01113
Opus 5 $0.00047 $0.00557
Sonnet 5 $0.00019 $0.00223
Haiku 4.5 $0.00009 $0.00111

Measured 2d ago against content hash 80edd89dc95e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

conventional-commits 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.

aim/templates/aim-agents/skills/conventional-commits/SKILL.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Conventional Commits

A structured commit history that humans skim and tools parse.

Conventional Commits 1.0 gives every commit a machine-readable prefix so changelogs and version bumps can be generated automatically.

Format

<type>[optional scope][!]: <subject>

[optional body]

[optional footer(s)]

Example:

feat(auth): add passkey login

Adds WebAuthn registration and assertion flows behind a feature flag.

Closes #142

Common types

Type Use for Version impact
feat A new feature MINOR
fix A bug fix PATCH
docs Docs only
refactor Code change, no behavior change
perf Performance improvement PATCH
test Adding / fixing tests
build Build system or dependencies
ci CI configuration
chore Maintenance, no src/test change
revert Reverts a previous commit
style Formatting / whitespace only
  • Scope (optional): the area touched, e.g. fix(parser):, feat(api):. Keep it a short noun; stay consistent across the repo.

Subject rules

  • Imperative mood: "add", "fix", "remove" — not "added" / "adds" / "fixing". (It should complete: "If applied, this commit will add passkey login".)
  • ≤ 72 characters, ideally ≤ 50.
  • No trailing period. Lowercase first word (unless a proper noun).
  • Describe what/why, not how. Put detail in the body, wrapped at ~72 cols.

Breaking changes

Two equivalent signals — use one or both:

feat(api)!: drop support for v1 tokens

and/or a footer (always uppercase, in the footer block):

BREAKING CHANGE: v1 tokens are rejected; clients must migrate to v2.

A breaking change triggers a MAJOR bump regardless of type.

Footers

  • BREAKING CHANGE: <description>
  • Issue refs: Closes #123, Refs #98
  • Co-Authored-By: Name <email>

Pre-commit sanity checklist

Run through this before every commit:

  • No leftover debug: no stray console.log, print, debugger, dd(), commented-out blocks.
  • No unresolved markers: no TODO / FIXME / XXX you intended to finish in this change.
  • No secrets: no keys, tokens, passwords, .env values, or private URLs in the diff.
  • Tests pass and lint/format/type checks are green.
  • Diff is focused: one logical change per commit; unrelated edits split out.
  • Type & scope are accurate; subject is imperative and ≤ 72 chars.
  • Breaking change flagged with ! and/or BREAKING CHANGE: if behavior or API changed incompatibly.

Read the full file on GitHub · 118 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 · 118 lines · 0 tokens per session scan A 80edd89dc95e

Subscribe to this mod's changes

conventional-commits is a skill published in the GitHub repository phuonghx/aim-cli (1 stars, last pushed 2mo ago), licensed MIT. It adds 94 tokens to every session and 1,113 once invoked, about $0.0005 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.