semantic-commit

semantic-commit is a skill for Claude Code from aiatelie/ai-atelie. It costs 84 tokens per session (1,942 once invoked), scanned A, original, MIT.

A commit-message guide for the AI Atelie repository. It formats messages according to Conventional Commits, a standard that labels changes so release tools can build a useful changelog.

In plain words
What is it for?
Use it before committing or amending changes in the AI Atelie repository. It helps classify the change, write the subject and body, and add relevant issue or breaking-change notes.
Why use it?
It prevents inconsistent commit messages and keeps them compatible with the repository's automated release process. It also limits messages to the scopes that this repository accepts.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths; mentions Claude Code.

Good fit Use it before committing or amending changes in the AI Atelie repository. It helps classify the change, write the subject and body, and add relevant issue or breaking-change notes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/aiatelie/ai-atelie/semantic-commit
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.

Any agent
npx skills add aiatelie/ai-atelie --skill semantic-commit
Clone the repo
git clone --depth 1 https://github.com/aiatelie/ai-atelie

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for semantic-commit

README.md
[![agentmods](https://agentmods.dev/badge/skills/aiatelie/ai-atelie/semantic-commit/github.svg)](https://agentmods.dev/skills/aiatelie/ai-atelie/semantic-commit)
Your own site
<a href="https://agentmods.dev/skills/aiatelie/ai-atelie/semantic-commit"><img src="https://agentmods.dev/badge/skills/aiatelie/ai-atelie/semantic-commit/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for semantic-commit

Your own site · 80×15
<a href="https://agentmods.dev/skills/aiatelie/ai-atelie/semantic-commit"><img src="https://agentmods.dev/badge/skills/aiatelie/ai-atelie/semantic-commit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 84 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,942 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00084 $0.01942
Opus 5.5 $0.00034 $0.00777
Sonnet 5.5 $0.00017 $0.00388
Haiku 4.5 $0.00008 $0.00194

Measured 1mo ago against content hash d8c072bb7fa5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

semantic-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 1mo 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.

.claude/skills/semantic-commit/SKILL.md · 187 lines

How it starts

The opening of the file, as written. The whole thing — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.

semantic-commit

A contributor workflow for AI Atelie. Drafts a Conventional Commits 1.0.0 message tailored to this repo's release pipeline (bun run release, powered by changelogen reading changelog.config.ts).

This skill is dev-time only. It does not load into adapter sessions spawned by the editor.

When to invoke

  • Before any git commit in this repo.
  • After staging changes if the user asks "commit this" / "ship it" / "make a commit".
  • When asked to amend the message of the most recent commit.

Do NOT invoke in unrelated repos — the scope set is specific to AI Atelie's workspace layout.

Workflow (paste this checklist into your reply and tick as you go)

  • Read git status and git diff --staged (or unstaged if nothing is staged).
  • Classify the change against the type taxonomy below.
  • Pick the correct scope from the closed set.
  • Draft the header (≤72 chars, imperative, lowercase after colon, no period).
  • Draft the body if the change is user-visible or non-obvious. Wrap at 72.
  • Add footers (Closes #N, Refs #N, BREAKING CHANGE:, Co-Authored-By:).
  • Show the full message to the user.
  • On confirm, create the commit using a HEREDOC.

Type taxonomy

The full set in changelog.config.ts. The three semver-bumping types come first because they're the ones that move version numbers.

Type Use when Bumps
feat New user-visible capability or surface minor
fix Corrects broken behaviour patch
perf Faster / lighter without behaviour change patch
refactor Internal restructuring, no behaviour change patch
docs README, CONTRIBUTING, code comments patch
chore Repo plumbing that isn't build/ci/docs —
test Adding or fixing tests —
build Build system or dependency tooling —
ci GitHub Actions, automation —
style Whitespace, formatting only —
revert Reverts a prior commit (include Refs:) —

Read the full file on GitHub · 187 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. 1mo ago First seen · 187 lines · 84 tokens per session scan A d8c072bb7fa5

Subscribe to this mod's changes

semantic-commit is a skill published in the GitHub repository aiatelie/ai-atelie (11 stars, last pushed 4mo ago), licensed MIT. It adds 84 tokens to every session and 1,942 once invoked, about $0.0003 per session on Opus 5.5. 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.