This release adds 2 notable features for engineering teams evaluating rollout.
✓ No known CVEs patched in this version
Topics
+14 more
Summary
AI summaryNew /brooks-sweep command unifies diagnosis and automated fixes for decay risks.
Full changelog
What's new
New skill: /brooks-sweep
A single command that both diagnoses and fixes. Instead of running five separate skills and manually applying remedies, /brooks-sweep does it all in one pass:
- Unified scan — production decay risks (R1–R6), test decay risks (T1–T6), and architecture analysis in a single pass
- Auto-fix — safe, local, reversible changes are applied immediately
- Confirm — multi-file or interface-touching changes are presented for user approval
- Manual — complex architectural decisions are flagged with full Iron Law entries for human judgment
- Sweep Report — Fix Log, Health Score delta (before → after), and residual items
/brooks-sweep # Claude Code (short form) / Gemini CLI
/brooks-lint:brooks-sweep # Claude Code (full form)
$brooks-sweep # Codex CLI
Internal: SKILL_GUIDES constant
validate-repo.mjs now derives all three skill-list arrays from a single SKILL_GUIDES constant, eliminating a three-way sync hazard. Future skill additions require only one array entry instead of three.
Upgrade
/plugin marketplace update
No migration required. All existing skill behavior is unchanged.
Weekly OSS security release digest.
The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.
No spam, unsubscribe anytime.
Share this release
About Brooks-Lint
All releases →Related context
Related tools
Beta — feedback welcome: [email protected]