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/overclokk/agent-plugins/commit-messagenpx skills add overclokk/agent-plugins --skill commit-messagegit clone --depth 1 https://github.com/overclokk/agent-pluginsWhat 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 | $0.00047 | $0.01104 |
| Opus 5 | $0.00023 | $0.00552 |
| Sonnet 5 | $0.00009 | $0.00221 |
| Haiku 4.5 | $0.00005 | $0.00110 |
Grade A, and why
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 yesterday.
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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Commit Message
Generate a single commit message that follows the Conventional Commits v1.0.0 spec.
Format
<type>[optional scope][!]: <description>
[optional body]
[optional BREAKING CHANGE footer]
Refs: <issue id>
- type, one of:
feat,fix,docs,style,refactor,perf,test,build,ci,chore,revert. - scope, optional, in parentheses, e.g.
fix(auth):. Add it only when it adds real clarity. - description, max 50 characters, starts lowercase, imperative mood, no trailing period.
Examples:
fix: prevent fatal error in SomeClass.php
Refs: CLNT-123
feat(checkout): add guest checkout flow
Refs: CLNT-456
Description rules
- Use the imperative mood, as if giving an instruction. The description must complete this sentence: "If applied, this commit will <description>".
- Write
add guest checkout flow, notadds guest checkout floworadded guest checkout flow. - Write
extract validation logic, notextraction of validation logic.
- Write
- Keep it under 50 characters. If summarizing is hard, the commit is probably doing too much, say so and suggest splitting it.
- Start with a lowercase letter, unless the first word is a symbol or proper noun that is genuinely capitalized (
SomeClass,WordPress). - Never end with a period.
- Pick the
typefrom the actual nature of the change (a bug fix isfix, a new capability isfeat). - Filenames: include a filename in the description only when one or two files are touched. With three or more files, describe the change generally and do not list files, keep the description clean.
Body
- Default to no body. Most commits are the subject line plus the
Refs:footer. - Add a body only for deep code changes: architectural or structural refactors, non-obvious logic, a decision that needs its "why" recorded, or anything a reviewer cannot infer from the diff.
- Never add a body for a small fix, a typo, a dependency bump, a style-only change, or a one-file tweak.
- Always ask the user first before adding a body, even when the change looks deep. Propose the body and let them accept it.
- When a body is approved: blank line after the subject, wrap at 72 characters, explain what changed and why, not how.
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.
- yesterday First seen · 100 lines · 47 tokens per session scan A 28eec60daa87
commit-message is a skill published in the GitHub repository overclokk/agent-plugins (2 stars, last pushed 13d ago), licensed MIT. It adds 47 tokens to every session and 1,104 once invoked, about $0.0002 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…