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.
npx agentmods add skills/bestdeejay-design/agent-skills/commit-message-writernpx skills add bestdeejay-design/agent-skills --skill commit-message-writergit clone --depth 1 https://github.com/bestdeejay-design/agent-skillsWrote 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.
[](https://agentmods.dev/skills/bestdeejay-design/agent-skills/commit-message-writer)<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>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.
| Model | Per session | Once 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 |
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.
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.
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 addилиgit 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): анализируетgit 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 commitили в файлCOMMIT_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/**
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.
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.
- 4d ago First seen · 137 lines · 110 tokens per session scan A a5c94f65ed51
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.
Other skills, from other repositories
Vizra ADK Evaluation Framework
Test and evaluate AI agents with automated evaluations, assertions, and LLM-as-a-Judge patterns.
Vizra ADK Memory System
Implement persistent memory, session context, and vector memory (RAG) for AI agents.
Vizra ADK Workflows
Orchestrate complex multi-agent workflows - sequential, parallel, conditional, and loop patterns.
database-verification
Shell-based database connectivity and integrity checks. Verifies that databases are reachable, schemas match expectations, and data integrity constraints hold.
environment-diagnostics
Environment variable validation and configuration verification. Checks that required variables are set, config files parse correctly, ports are available, and system dependencies meet version requirements.
reply-composer
Draft context-aware email replies that match sender tone, reference thread history, and follow the user's style preferences. Presents drafts for review before sending.