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 alexeyshishin/as-skill --skill git-conventional-commitsgit clone --depth 1 https://github.com/alexeyshishin/as-skillWrote 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/alexeyshishin/as-skill/git-conventional-commits)<a href="https://agentmods.dev/skills/alexeyshishin/as-skill/git-conventional-commits"><img src="https://agentmods.dev/badge/skills/alexeyshishin/as-skill/git-conventional-commits/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/alexeyshishin/as-skill/git-conventional-commits"><img src="https://agentmods.dev/badge/skills/alexeyshishin/as-skill/git-conventional-commits.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 | $0.00089 | $0.01760 |
| Opus 5.5 | $0.00036 | $0.00704 |
| Sonnet 5.5 | $0.00018 | $0.00352 |
| Haiku 4.5 | $0.00009 | $0.00176 |
Grade A, and why
git-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 3d 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
git-conventional-commits — Conventional Commit message for the current diff
Goal: instead of the user writing the commit message themselves, you analyze the diff and build a message following the convention in references/rules/git-conventions.md.
Before starting, read references/rules/git-conventions.md — it has the full list of allowed type values, the scope format, and the principles.
Two assets ship with this skill:
references/commit-examples.md— the author's real commit corpus: observed type/scope distribution, clean examples per type, and the anti-patterns that actually recur in this history, ranked. Read it when choosing the type/scope or when a subject feels generic.scripts/lint-commit-msg.py— mechanical checker for the message you drafted (Step 5.5). Also audits an existing log:--history N.
Step 1. Gather context
Run:
git status --short— see what's changedgit diff --staged(if there's staged content) orgit diff(if not) — the content of the changesgit log --oneline -10— the style of previous commits in the project (especially the language: Russian/English)
If staged is empty and unstaged is also empty — tell the user and stop.
Step 2. Determine the type
Read the diff and decide:
| diff shows | type |
|---|---|
| a new file with functionality, a new endpoint, a new feature | feat |
| a logic fix so a bug no longer reproduces | fix |
| move/rename/simplify with no behavior change | refactor |
| performance improvement only | perf |
only .md, code comments |
docs |
| only tests added or fixed | test |
package.json, go.mod, requirements.txt, Dockerfile, CI configs |
build or ci |
| dependencies, tooling versions | chore(deps) |
| revert of a previous commit | revert |
If the diff is mixed (e.g. both fix and refactor) — stop and suggest the user split it into several commits. Don't write "feat: fixed a bug and refactored" — that's an anti-pattern.
What ships with it
4 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.
- 3d ago Changed 65f1b98afab3
- 9d ago Changed · +22 lines · +3 tokens per session 649a4de464bf
- 2mo ago First seen · 110 lines · 86 tokens per session scan A 7e83420f9456
git-conventional-commits is a skill published in the GitHub repository alexeyshishin/as-skill (6 stars, last pushed 2d ago), licensed MIT. It adds 89 tokens to every session and 1,760 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.
git-conventional-commits compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| git-conventional-commitsalexeyshishin/as-skill | Skill | 6 | 2d ago | MIT | A | 89 | Claude Code, Codex |
| pr-squash-messagescenario-labs/skills | Skill | 3.2k | yesterday | MIT | A | 73 | Codex |
| git-wrapupcyanheads/obsidian-mcp-server | Skill | 702 | 6d ago | Apache-2.0 | A | 109 | Claude Code |
| phx-pr-reviewoliver-kriska/claude-elixir-phoenix | Skill | 574 | yesterday | MIT | A | 61 | Claude Code, Codex |
| changelog-automationvibeeval/vibecosystem | Skill | 539 | 2d ago | MIT | A | 23 | Claude Code, Codex |
| commit-trailersvibeeval/vibecosystem | Skill | 539 | 2d ago | MIT | A | 43 | Claude Code, Codex |
| private-secret-scanningjamditis/claude-skills-journalism | Skill | 448 | 2d ago | MIT | A | 40 | Claude Code, Codex |