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 skills add jtprogru/bear-skills --skill git-conventional-commitgit clone --depth 1 https://github.com/jtprogru/bear-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/jtprogru/bear-skills/git-conventional-commit)<a href="https://agentmods.dev/skills/jtprogru/bear-skills/git-conventional-commit"><img src="https://agentmods.dev/badge/skills/jtprogru/bear-skills/git-conventional-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.
<a href="https://agentmods.dev/skills/jtprogru/bear-skills/git-conventional-commit"><img src="https://agentmods.dev/badge/skills/jtprogru/bear-skills/git-conventional-commit.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00093 | $0.01113 |
| Opus 5.5 | $0.00037 | $0.00445 |
| Sonnet 5.5 | $0.00019 | $0.00223 |
| Haiku 4.5 | $0.00009 | $0.00111 |
Grade A, and why
git-conventional-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.
How it starts
The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
git-conventional-commit — Conventional Commit message для текущего diff
Цель: вместо того чтобы пользователь сам формулировал commit-message, ты анализируешь diff и формируешь сообщение по конвенции ~/.claude/rules/git-conventions.md.
Перед началом прочитай ~/.claude/rules/git-conventions.md — там полный список допустимых type, формат scope и принципы.
Шаг 1. Собери контекст
Запусти:
git status --short— посмотри, что измененоgit diff --staged(если есть staged) илиgit diff(если нет) — содержание измененийgit log --oneline -10— стиль предыдущих коммитов в проекте (особенно язык: русский/английский)
Если staged пуст и unstaged тоже — скажи пользователю и остановись.
Шаг 2. Определи type
Прочитай diff и реши:
| diff показывает | type |
|---|---|
| новый файл с функциональностью, новый endpoint, новая фича | feat |
| правка логики, чтобы баг перестал воспроизводиться | fix |
| перенос/переименование/упрощение без изменения поведения | refactor |
| только улучшение производительности | perf |
только .md, комментарии в коде |
docs |
| только тесты добавлены или поправлены | test |
package.json, go.mod, requirements.txt, Dockerfile, CI-конфиги |
build или ci |
| зависимости, версии тулинга | chore(deps) |
| откат предыдущего коммита | revert |
Если diff смешанный (например, и fix и refactor) — остановись и предложи пользователю разбить на несколько коммитов. Не пиши «feat: исправил баг и отрефакторил» — это анти-паттерн.
Шаг 3. Определи scope (опционально)
Scope — короткое имя модуля/папки/SDK. Эвристика:
- если все файлы под одной папкой первого уровня (
src/auth/,sdk-go/,cli/) — scope = имя этой папки - если затронуто 2-3 файла в разных папках — scope можно опустить
- если поправлен один конкретный компонент (
UserCard.tsx) — scope = имя компонента в kebab-case
Шаг 4. Сформулируй subject
- 50-72 символа
- глагол в настоящем времени, без заглавной буквы, без точки
- если коммиты в проекте на русском — пиши на русском, если на английском — на английском (смотри
git log) - субъект описывает что изменилось, не «что я сделал»
What ships with it
1 file 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.
- 1mo ago First seen · 102 lines · 93 tokens per session scan A ce109e4bc969
git-conventional-commit is a skill published in the GitHub repository jtprogru/bear-skills (1 stars, last pushed 19d ago), licensed MIT. It adds 93 tokens to every session and 1,113 once invoked, about $0.0004 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.
Other skills, from other repositories
feature-publish
Commit the feature, write the PR body, publish in the selected mode, and drive the PR.
pr-review
Address feedback left on a GitHub pull request: fetch unresolved review threads, make agreed Elixir/Phoenix code fixes, reply, and resolve. Use for a PR URL/number or reviewer comments. NOT for pre-PR review, findings triage, or CI monitoring.
phx-pr-review
Address feedback left on a GitHub pull request: fetch unresolved review threads, make agreed Elixir/Phoenix code fixes, reply, and resolve. Use for a PR URL/number or reviewer comments. NOT for pre-PR review, findings triage, or CI monitoring.
lean-review
CocoLean diff-scoped over-engineering audit — scans uncommitted git diff and applies five classification tags (delete/stdlib/native/yagni/shrink) to identify unnecessary surface area before commit.
github-commenting
How to post clean, rich, deduplicated GitHub PR review comments — suggestion blocks, multi-line anchors, markers, formatting rules. Load before posting or fixing any PR comment.
signing-preflight
Before the first commit of a session, check that commit signing will work — the key is loaded and unlocked — and ask the operator to unlock it once, up front, instead of discovering it after a hundred unsigned commits. Never disables signing silently, never re-signs history without asking. Use at the start of…