Individual skill

code-health-audit

Read-only AUDIT of code quality, performance, and running cost of an existing codebase: dead code and unused exports/dependencies, duplication, oversized client bundles, slow or chatty routes and queries, cold start, function CPU/memory, and observability volume. Use ONLY when the user explicitly asks for a quality, cleanup, performance, cost, or 'auditoria de qualidade/performance/custo' review of code that already exists. Produces measured, independently verified findings; never edits code. Do NOT use to implement or review a change (use ship-with-confidence), for security (use security-audit), or for a single known bug.

skills/code-health-audit/SKILL.md

Read pinned source

Source commit b0f612844e1aa7d1f2817454d1a5fb60457b8a52

What was checked

Matches the observed repository HEAD
Yes
Scanner rules are current
No
Repository scan complete
No
Skill scan complete
No
Observed behavior
Not checked yet
Last checked
Nov 6, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings)
3
Repository last updated
Nov 1, 2026
License
MIT

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files
Read excerpt

# Code Health Audit

Find where the existing code is dead, duplicated, slow, or expensive, prove each claim with a
measurement or a complete reachability trace, and hand the owner small, ordered changes. This
is the quality and performance counterpart of `security-audit`, with the same evidence bar:
an unproven candidate is not a finding.

The audit is read-only. Fixes are a separate task delivered through `ship-with-confidence`.

## Authority

1. The user's request sets scope and budget.
2. The repository's own instructions (`AGENTS.md`, `CLAUDE.md`, a project team skill) override
   anything generic here. Read them first; they usually hold measured lessons that a generic
Back to top