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/lee-w/maigo/commit-messagenpx skills add Lee-W/maigo --skill commit-messagegit clone --depth 1 https://github.com/Lee-W/maigoWhat 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 | $0.00080 | $0.02133 |
| Opus 5 | $0.00040 | $0.01066 |
| Sonnet 5 | $0.00016 | $0.00427 |
| Haiku 4.5 | $0.00008 | $0.00213 |
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 2d 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Commit Message
Consumers: any task that drafts a commit message — manual git commit, git commit --amend on an unreleased local-branch commit, squash messages, branch-rewrite scripts, agent-drafted commits.
Why this skill exists
Commit messages are the durable log a future bisecting engineer reads when something breaks years later. The reviewer reads the PR description; the future maintainer reads the commit log. They serve different audiences, and the failure mode of drafting agents is to conflate them.
Common failures:
- Body explains "why the problem existed" or "what alternatives we considered" — that is PR-description content (motivation + discussion), not durable log.
- Subject is internal-perspective (
"Initialize Dag bundles in CLI get_dag function") instead of user-impact ("Fix airflow dags test command failure without serialized Dags"). - Body forgets to leave forward pointers (newsfragment filename, related PR #, tracking issue URL) — the next reader has to do a network round-trip to recover them.
- Body bloats to 5+ lines that duplicate the PR
## Whyparagraph.git logbecomes harder to scan, not easier.
This skill encodes the short, durable style. It pairs with github-title-description: the PR body carries motivation and test plan; the commit body carries durable facts + pointers.
Inputs
- Staged / proposed diff —
git diff --staged, or the contents of the impending change if not yet staged. - Existing commit context (when amending) —
git log <base>..HEAD --pretty=format:'%h %s%n%b' --no-merges. Match the existing subject style on amend; do not change the framing just because a polish round happened. - Repo commit-style detection — does the repo enforce Conventional Commits?
pyproject.tomlhas[tool.commitizen]→ Conventional Commits expected..cz.toml/.cz.json/cz.yaml→ Conventional Commits expected.commitlint.config.js/.commitlintrc*→ usually Conventional Commits.- Repo has a documented convention that explicitly bans/avoids Conventional
Commits (e.g. apache/airflow's
AGENTS.mdbans CC-style prefixes on commit subjects and enforces it via acommit-msgprek hookcheck-no-conventional-commit-message) → follow that repo convention; stay freeform / plain-imperative there. - None of the above (no CC tooling signal, no documented ban) →
default to Conventional Commits (
<type>(<scope>): <description>). This is the maigo user's personal drafting preference for their own repos when the repo itself has no opinion either way.
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.
- 2d ago First seen · 125 lines · 80 tokens per session scan A c0a08702b729
commit-message is a skill published in the GitHub repository Lee-W/maigo (14 stars, last pushed 8d ago), licensed MIT. It adds 80 tokens to every session and 2,133 once invoked, about $0.0004 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 2026-08-30.
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…