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 mhylle/claude-skills-collection --skill code-quality-auditgit clone --depth 1 https://github.com/mhylle/claude-skills-collectionWrote 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/mhylle/claude-skills-collection/code-quality-audit)<a href="https://agentmods.dev/skills/mhylle/claude-skills-collection/code-quality-audit"><img src="https://agentmods.dev/badge/skills/mhylle/claude-skills-collection/code-quality-audit/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/mhylle/claude-skills-collection/code-quality-audit"><img src="https://agentmods.dev/badge/skills/mhylle/claude-skills-collection/code-quality-audit.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 | $0.00126 | $0.03192 |
| Opus 5 | $0.00063 | $0.01596 |
| Sonnet 5 | $0.00025 | $0.00638 |
| Haiku 4.5 | $0.00013 | $0.00319 |
Grade A, and why
code-quality-audit 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 10d 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 — 247 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Quality Audit
Systematic audit of a codebase along five axes: test coverage, cyclomatic complexity, module size, dependency structure, and mutation testing. Produces a single prioritized report and, when invoked as a gate, returns a pass/fail verdict.
Scope — what this audits and what it doesn't
This skill measures mechanical code-quality metrics on the current source tree. That's it. Keep this distinction sharp because many user prompts bundle unrelated questions under words like "gate" or "quality":
In scope:
- Test coverage (line + branch, measured by a coverage tool)
- Cyclomatic complexity per function (measured by a static analyzer)
- Module/file size in LOC
- Dependency graph cycles and fan-in/out
- Mutation score (tests actually kill injected mutations)
Out of scope — do not attempt:
- Plan-vs-code auditing ("is phase 3 of PLAN.md actually implemented?") — that's a different task, not this skill
- Architectural drift from design docs / ADRs
- Business-logic correctness review
- Security review (there's a separate
security-reviewskill) - Lint / type-check errors (there's
verification-loopfor that) - Whether tests pass — a 100%-failing test suite with 80% coverage still passes this audit's coverage axis. The gate is about measured metrics, not CI health.
If a user's prompt mixes scopes (e.g. "is phase 3 shippable?"), interpret it as: "are my five code-quality metrics within threshold for the code as it stands?" That's the only question this skill answers. Surface the narrow framing in the report's preamble if the prompt was broader, so the user knows what they did and didn't get.
Design Philosophy
Why these five axes?
Each catches a different class of problem that the others miss:
| Axis | Catches | Why it matters |
|---|---|---|
| Coverage | Untested code paths | You can't trust code you haven't exercised |
| Complexity | Hard-to-reason-about functions | Complex code hides bugs and resists change |
| Module size | Over-stuffed files | Large modules accrete responsibilities and become change-amplifiers |
| Dependencies | Cycles, tight coupling, god-modules | Structural debt is expensive to unwind later |
| Mutation | Tests that run code but don't assert meaningfully | High coverage with weak assertions is a false sense of safety |
What ships with it
5 files 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.
- 10d ago First seen · 247 lines · 126 tokens per session scan A 6b2d78651293
code-quality-audit is a skill published in the GitHub repository mhylle/claude-skills-collection (18 stars, last pushed 7d ago), licensed MIT. It adds 126 tokens to every session and 3,192 once invoked, about $0.0006 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
adversarial-reviewer
Adversarial code review that assumes bugs exist and hunts for them. Use when asked to review code, find bugs, audit for correctness, stress-test a PR, or when someone says "tear this apart" or "what's wrong with this". Give no benefit of the doubt — every line is guilty until proven innocent.
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
semgrep-rule-variant-creator
Creates language variants of existing Semgrep rules. Use when porting a Semgrep rule to specified target languages. Takes an existing rule and target languages as input, produces independent rule+test directories for each language.
brooks-sweep
Full-sweep mode: runs a unified analysis across all quality dimensions — code decay, architecture, tech debt, and test quality — then applies fixes directly to the codebase. Safe changes are auto-applied; risky changes are confirmed before execution. Drawing on twelve classic engineering books. Triggers when: user…
include-test-files-that-assert-on-behavior-being-changed-in-decl
When delegating a task affected by this skill, include.
plugin-review
Review plugin quality with tiered checks and dependency scoping. Use for PR and pre-release audits.