commit-message-writer

commit-message-writer is a skill for Claude Code, Codex from bestdeejay-design/agent-skills. It costs 110 tokens per session (1,283 once invoked), scanned A, original, MIT.

A tool that writes a Conventional Commit message from Git changes that have already been staged. Conventional Commits are a shared format such as feat or fix followed by a short description.

In plain words
What is it for?
Use it after git add to create a short commit title and, when useful, a body based only on the staged changes.
Why use it?
It avoids guessing the right commit type, scope, and wording while keeping commit history consistent for tools and teammates.

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/bestdeejay-design/agent-skills/commit-message-writer
Any agent
npx skills add bestdeejay-design/agent-skills --skill commit-message-writer
Clone the repo
git clone --depth 1 https://github.com/bestdeejay-design/agent-skills

Made for: Claude Code, Codex.

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 commit-message-writer

README.md
[![agentmods](https://agentmods.dev/badge/skills/bestdeejay-design/agent-skills/commit-message-writer.svg)](https://agentmods.dev/skills/bestdeejay-design/agent-skills/commit-message-writer)
Your own site
<a href="https://agentmods.dev/skills/bestdeejay-design/agent-skills/commit-message-writer"><img src="https://agentmods.dev/badge/skills/bestdeejay-design/agent-skills/commit-message-writer.svg" alt="Measured on agentmods" height="20"></a>
Per session 110 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,283 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 $0.00110 $0.01283
Opus 5 $0.00055 $0.00642
Sonnet 5 $0.00022 $0.00257
Haiku 4.5 $0.00011 $0.00128

Measured 4d ago against content hash a5c94f65ed51, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

commit-message-writer 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 4d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/suggest.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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-message-writer/SKILL.md · 137 lines

How it starts

The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Commit Message Writer

Conventional Commits из вашего staged-diff за один шаг.

Загружай этот скилл когда нужно написать сообщение коммита по уже застейдженным изменениям (git add уже сделан). Скилл анализирует diff, определяет тип и scope, выдаёт готовое сообщение в формате Conventional Commits.

When to use

Use this skill when:

  • Изменения уже застейджены (git add), нужно сообщение коммита
  • Нужно привести формат к Conventional Commits (CI требует commitlint)
  • Нужно автоматически определить scope по путям файлов
  • Нужен короткий заголовок + тезисный body (если diff большой)

Do NOT use when:

  • Изменения ещё не застейджены — сначала git add или git add -p
  • Требуется разбить изменения на несколько логических коммитов — сначала разбей, потом вызывай скилл для каждой части
  • Это squash/rebase/merge коммит — скажи об этом явно

What this skill does

Inputs

  • staged (default): анализирует git diff --cached (только staged)
  • --unstaged (опция): аналогично для unstaged (не рекомендуется)
  • --scope (опция): принудительный scope вместо автодетекта
  • --emoji (опция): добавить gitmoji-префикс перед типом (✨ feat: ...)

Outputs

  • Готовое сообщение коммита (1 строка заголовок + опциональный body), копируемое командой git commit или в файл COMMIT_EDITMSG.
  • Краткая справка: тип, scope, почему выбран именно этот тип.

How to use

Шаг 1: убедись, что изменения застейджены

git add <file1> <file2>
git diff --cached --stat   # проверить, что видит скилл

Шаг 2: сгенерировать сообщение

python3 scripts/suggest.py --cached

Пример вывода:

✨ feat(api): add GET /v1/health endpoint with liveness probe

- expose /v1/health via Fastify (src/routes/health.ts)
- add HealthService with process uptime + memory gauge
- wire route into router bootstrap (src/app.ts)

Type: feat — new endpoint, backwards-compatible addition
Scope: api — paths match src/api/** or src/routes/**

Read the full file on GitHub · 137 lines

Files

What ships with it

2 files 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. 4d ago First seen · 137 lines · 110 tokens per session scan A a5c94f65ed51

Subscribe to this mod's changes

commit-message-writer is a skill published in the GitHub repository bestdeejay-design/agent-skills (5 stars, last pushed yesterday), licensed MIT. It adds 110 tokens to every session and 1,283 once invoked, about $0.0006 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.