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 zarpay/rails-template --skill ruby-commit-messagegit clone --depth 1 https://github.com/zarpay/rails-templateWrote 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/zarpay/rails-template/ruby-commit-message)<a href="https://agentmods.dev/skills/zarpay/rails-template/ruby-commit-message"><img src="https://agentmods.dev/badge/skills/zarpay/rails-template/ruby-commit-message/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/zarpay/rails-template/ruby-commit-message"><img src="https://agentmods.dev/badge/skills/zarpay/rails-template/ruby-commit-message.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 | $0.00034 | $0.00824 |
| Opus 5.5 | $0.00014 | $0.00330 |
| Sonnet 5.5 | $0.00007 | $0.00165 |
| Haiku 4.5 | $0.00003 | $0.00082 |
Grade A, and why
ruby-commit-message 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ruby Commit Message
Overview
Write structured commit messages following Conventional Commits. The body should help a junior Ruby on Rails developer understand the change during a debugging session.
Format
<type>(<scope>): <subject>
<body>
<footer>
Quick Reference — Commit Types
| Type | Purpose |
|---|---|
feat |
New feature |
fix |
Bug fix |
refactor |
Refactoring (no behavior change) |
perf |
Performance improvement |
docs |
Documentation only |
test |
Test additions or corrections |
build |
Build system or dependencies |
ci |
CI configuration |
chore |
Maintenance tasks |
style |
Code formatting (no logic change) |
revert |
Revert previous commit |
meta |
Repository metadata |
license |
License changes |
Subject Line Rules
- Imperative mood: "Add", "Fix", "Update", "Remove"
- Present tense: "Add feature" not "Added feature"
- Capitalized first letter, no period at end
- Maximum 70 characters
- Scope (optional): noun describing the section of codebase, e.g.
(api),(auth)
Body Guidelines
Couple of sentences, wrapped at 72 chars, blank line after subject. Write for a junior Ruby developer: simple language they can understand during debugging. Add any useful information that would help a junior Ruby developer understand the impact of the change, why the change was done.
- WHY — motivation, problem, or user impact. Use context if it exists for this.
- WHAT changed — make this brief; the diff already shows the HOW
- HOW — only when there are details about the how that are not reflected by the code or the naming in the code
Call out tradeoffs when supported by context. Do not invent details.
Footer & AI Attribution
Fixes TICKET-123 # or: Fixes #123, Refs TICKET-123
BREAKING CHANGE: ... # for breaking changes; use ! in type too: feat(api)!:
Co-Authored-By: <AI Name> <email> # when AI generated the change
Do NOT add "Generated by AI" or "Written with Claude" in the subject or body. Use only Co-Authored-By.
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 · 113 lines · 34 tokens per session scan A 830c10c5ac3e
ruby-commit-message is a skill published in the GitHub repository zarpay/rails-template (12 stars, last pushed 2mo ago), licensed MIT. It adds 34 tokens to every session and 824 once invoked, about $0.0001 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
cuga-contributor-workflows
Run CUGA contributor workflows: Conventional Commits, create pull requests against origin with gh and PR templates, and ruff check/format via uv. Use when the user says commit, create a commit, create PR, pull request, open a PR, ruff check, ruff format, or conventional commits.
git-commit
Generate conventional commit messages for Java projects. Use when user says "commit", "create commit", "commit changes", or after completing code changes that need to be committed.
npmjs
Manage npm packages in a monorepo: audit health, sync dependencies, bump versions, update changelogs, run pre-publish checks, and coordinate publishing.
pixiv-cli-develop
Implement, diagnose, refactor, and design pixiv-cli Go changes using its actual CLI, SDK, MCP, account, and storage boundaries. Use before source changes or engineering design; choose the separate native or MCP workflow when that boundary is involved. No personal skills are required.
vigilante-issue-implementation-on-ruby
Implement a GitHub issue end-to-end when Vigilante dispatches work for a Ruby repository with Bundler, test, lint, and security guidance.
refactoring-python
Use when refactoring or modernizing existing Python code without changing behavior: splitting a long function or module, removing drifted duplication, isolating I/O behind a port to make code testable, replacing Java-style classes with idiomatic Python, or judging whether an interface is over-engineering. Triggers…