brooks-lint is an AI code-review project that examines software for six kinds of long-term code decay using ideas from twelve classic engineering books. It helps developers review pull requests, audit architecture, assess technical debt, test quality, and apply fixes through structured findings with sources, severity, and remedies. Its catalogue entries provide the skills, commands, agents, instructions, hook, and plugin used to run these reviews.
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 hyhmrright/brooks-lint --skill releasegit clone --depth 1 https://github.com/hyhmrright/brooks-lintWrote 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/hyhmrright/brooks-lint/release)<a href="https://agentmods.dev/skills/hyhmrright/brooks-lint/release"><img src="https://agentmods.dev/badge/skills/hyhmrright/brooks-lint/release/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/hyhmrright/brooks-lint/release"><img src="https://agentmods.dev/badge/skills/hyhmrright/brooks-lint/release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00135 | $0.01160 |
| Opus 5.5 | $0.00054 | $0.00464 |
| Sonnet 5.5 | $0.00027 | $0.00232 |
| Haiku 4.5 | $0.00014 | $0.00116 |
Grade A, and why
release 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 6d 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
brooks-lint — Release
Target version comes from the user request (e.g. 1.4.0). If empty, ask the maintainer
for the semver bump before doing anything.
Before accepting that version, read the backlog. Run
npm run changelog:audit and look at what is actually unreleased — the bump is decided by the whole range, not by the change
that prompted the release. If the range contains a feature or a new platform and
the maintainer asked for a patch, stop and say so: v1.5.1 was published, then
deleted and re-cut as v1.6.0 because twenty unreleased commits (including a new
platform) had been swept into a patch.
Execute these steps in order. bump-version.mjs reads the version FROM
package.json and does NOT touch the changelog — so the version edit and the
CHANGELOG entry are manual; the script only fans the version out to the manifests
and every version-bearing text file.
-
Set the source of truth.
npm version <version> --no-git-tag-version(the--no-git-tag-versionflag is required — plainnpm versionwould create its own commit + tag and collide with the manual commit in step 5). -
Propagate.
npm run bump— writes the version into.claude-plugin/plugin.json,.claude-plugin/marketplace.json,.codex-plugin/plugin.json,gemini-extension.json, and every version-bearing text file discovered byscripts/version-refs.mjs(all six README badges and actionuses:pins, the JSON-LDsoftwareVersionon the docs landing page, anddocs/github-action-example.yml). Do not maintain a list here — the script's is authoritative. -
Write the changelog. Add a new section at the top of
CHANGELOG.mdwith categorized notes (Added / Fixed / Changed) summarizing the commits since the last release tag. The heading MUST be## [<version>] - YYYY-MM-DD—npm run validateparses that exact shape and fails on a bare## <version>. 3a. Audit the range — every commit, no sampling. Run:npm run changelog:auditIt derives the range from the last release tag, applies the only three exemptions (the release bump, a merge commit whose branch commits are listed separately, and the star-history refresh — a bot commit touching only the chart's own two files) and prints the rest as a checklist. Walk it: each line gets an entry you just wrote, or a reason it needs none. Nothing else is exempt — internal hardening with no user-visible change earns an entry, and so does an outside contributor's maintainer-facing fix, which also earns an
@handlecredit. AChangelog:trailer on a commit is surfaced as a flag; that commit's entry is the one you are writing now.The script exits non-zero on the gap it can prove — a pull request in the range whose
#Nthe section never cites. That same check runs insidenpm run validatewhile a release is in progress, so it cannot be skipped, and validate prints one line whenever it stands down. The rest of the checklist is judgment and is not enforced. A green audit is not proof of a complete changelog: a bare#Nanywhere in the section clears the gate, a rebase-merged PR leaves nothing to match, and anything staged into the release bump itself is never audited. See AGENTS.md's Release Process. -
Validate.
npm run validate— fails if any manifest, any version-bearing text file, or the CHANGELOG entry is out of sync. Fix and re-run until clean. Thennpm test. -
Commit & push. Stage everything
npm run bumprewrote plusCHANGELOG.md— readgit statusrather than naming files, because the version-bearing set is discovered from disk and is more than one README; commit with a conventional message (chore(release): bump version to <version>); push tomain(direct-to-main repo — no PR). -
Tag & publish. Create the GitHub release:
gh release create v<version> --title "v<version>" --notes "<changelog section>".
Report the released version and the GitHub release URL when done.
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.
- 6d ago Changed bfcdf2827295
- 1mo ago Changed · +31 lines 904410798e43
- 1mo ago First seen · 52 lines · 135 tokens per session scan A 9f98f4046fe2
release is a skill published in the GitHub repository hyhmrright/brooks-lint (1,540 stars, last pushed today), licensed MIT. It adds 135 tokens to every session and 1,160 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
bump-version
Bump the Logic-Lens version across all six metadata locations at once (package.json, the four plugin manifests, and the README badge), then validate. Use when cutting a release or when npm run validate reports a version mismatch.
release-docs
Diff-driven documentation sync after a release. Determines what source files changed, delegates changelog to zuvo:docs, updates only docs whose source changed. Flags: --dry-run, explicit range argument.
changelog
Add CHANGELOG.md entries, derive them from commits, or cut a Keep a Changelog and SemVer release.
han-release
Cut a Han release: update CHANGELOG.md with the changes since the last release, bump and tag every plugin that changed as {plugin-name}--v{version} so a version-constrained dependency can resolve, and publish a GitHub release crediting every merged pull request and closed issue to the people behind it. Use when…
release-habit-hooks
Cut a new release of the habit-hooks packages. Use when asked to release, publish, or bump the version. Reviews what lands, enforces the in-sync versioning rule, validates the changelog, and drives the tag-triggered PyPI publish.
pre-release-review
Run the pre-release gate for this multi-plugin monorepo: establish each plugin's release boundary from its last reachable tag to HEAD, audit every changed plugin's [Unreleased] changelog against the actual code diff, identify contract-surface and breaking changes, and, per the objective the user picks up front, either…