Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/MichelKerkmeester/skilled-agent-harness_spec-driven-loopsnpx agentmods add skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/sk-code-qualityWrote 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/michelkerkmeester/skilled-agent-harness_spec-driven-loops/sk-code-quality)<a href="https://agentmods.dev/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/sk-code-quality"><img src="https://agentmods.dev/badge/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/sk-code-quality/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/michelkerkmeester/skilled-agent-harness_spec-driven-loops/sk-code-quality"><img src="https://agentmods.dev/badge/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/sk-code-quality.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
SkillSpector: 1 finding, up to low
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- low Excessive Agency · line 248 Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.Fix: Limit the skill's scope to its documented purpose. Remove instructions that enable the agent to perform actions outside its stated functionality.
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 | $0.00000 | $0.05145 |
| Opus 5 | $0.00000 | $0.02573 |
| Sonnet 5 | $0.00000 | $0.01029 |
| Haiku 4.5 | $0.00000 | $0.00515 |
Grade A, and why
sk-code-quality 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 — 324 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Quality (quality)
quality is the author-side quality gate MODE child of the sk-code family. It runs after the surface skill (code-webflow / code-opencode) implements changes and before the surface's verification workflow or done-claim. It consumes the shared surface router, loads the right checklist for the detected surface and target path, fixes quality-gate failures in place, and leaves findings-only output to code-review.
1. WHEN TO USE
Activation Triggers
Use this mode when the request involves:
- Running the post-implementation quality gate before a completion claim.
- Applying P0/P1/P2 author-side checks to changed code, scripts, skills, agents, commands, MCP servers, or spec docs.
- Checking comment hygiene on modified files and removing ephemeral artifact references from comments while preserving durable WHY.
- Loading an OpenCode authoring checklist for
.opencode/skills/,.opencode/agents/,.opencode/commands/,.opencode/specs/, MCP server source, or language-specific OpenCode files. - Applying Webflow/frontend quality standards after implementation and before runtime verification.
- Fixing quality-gate failures in place with
Editwhen the fix belongs to the already-authored file.
Keyword triggers: quality gate, code quality, comment hygiene, surface checklist, P0, P1, P2, authoring checklist, OpenCode checklist, skill authoring, agent authoring, command authoring, MCP server authoring, spec folder authoring, check before done.
When NOT to Use
Skip this mode when:
- The user needs code written, files scaffolded, or behavior implemented. Use the appropriate surface skill (
code-webflow/code-opencode) and its implementation workflow. - A failure needs symptom-to-root-cause investigation or a single-cause bug fix. Use the surface's debugging workflow (
workflow-debug.md). - The task is to collect final non-mutating verification evidence. Use the surface's verification workflow (
workflow-verify.md). - The user asks for findings-first review output, severity-ranked findings, or PR review. Use
code-review. - The task is documentation-only prose with no code-work contract. Use
sk-doc.
What ships with it
31 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.
- assets/code-quality-checklist/naming-init-formatting-and-css.md 7.5 KB
- assets/code-quality-checklist/overview-header-and-comments.md 9.5 KB
- assets/code-quality-checklist/verification-quick-reference-and-related.md 4.3 KB
- benchmark/reports/2026-07-10--live-mode-b--live/failed-runs.md 187 B
- benchmark/reports/2026-07-10--live-mode-b--live/findings-and-recommendations.md 235 B
- benchmark/reports/2026-07-10--live-mode-b--live/README.md 1.4 KB
- benchmark/reports/2026-07-10--live-mode-b--live/results.csv 197 B
- benchmark/reports/2026-07-10--live-mode-b--live/skill-benchmark-report.json 8.5 KB
- benchmark/reports/2026-07-10--live-mode-b--live/skill-benchmark-report.md 1.6 KB
- benchmark/reports/2026-07-10--live-mode-b--live/source.md 909 B
- benchmark/reports/2026-07-10--router-mode-a--router/failed-runs.md 189 B
- benchmark/reports/2026-07-10--router-mode-a--router/findings-and-recommendations.md 237 B
- benchmark/reports/2026-07-10--router-mode-a--router/README.md 1.4 KB
- benchmark/reports/2026-07-10--router-mode-a--router/results.csv 200 B
- benchmark/reports/2026-07-10--router-mode-a--router/skill-benchmark-report.json 8.2 KB
- benchmark/reports/2026-07-10--router-mode-a--router/skill-benchmark-report.md 1.6 KB
- benchmark/reports/2026-07-10--router-mode-a--router/source.md 920 B
- benchmark/reports/README.md 1.5 KB
- changelog/v1.0.0.0.md 1.7 KB
- changelog/v1.0.0.2.md 1.1 KB
- manual-testing-playbook/manual-testing-playbook.md 1.6 KB
- manual-testing-playbook/quality-gate/quality-checklist.md 5.6 KB
- README.md 7.8 KB
- scripts/check-comment-hygiene.sh 8.0 KB runs code
- scripts/check-comment-hygiene.test.sh 2.1 KB runs code
- scripts/check-dist-staleness.sh 6.8 KB runs code
- scripts/hooks/claude-posttooluse.sh 5.3 KB runs code
- scripts/hooks/claude-posttooluse.test.sh 690 B runs code
- scripts/hooks/README.md 1.5 KB
- scripts/lib/README.md 1.1 KB
- scripts/README.md 1.7 KB
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 First seen · 324 lines · 0 tokens per session scan A 7d2e61eb66ff
sk-code-quality is a skill published in the GitHub repository MichelKerkmeester/skilled-agent-harness_spec-driven-loops (35 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 5,145 tokens. 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 2026-09-03.
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.
gsd-ns-review
Route to the appropriate quality / review skill based on the user's intent. gsd-code-review-fix was absorbed by gsd-code-review --fix in #2790.
issue
Use when starting a chain from a GitHub issue — turning an issue URL or number into a triaged, planned, dispatched, and reviewed pull request. Classifies the thread (bug → root-cause discipline, feature → plan chain, question → drafted reply), synthesizes a spec from the issue's own acceptance criteria, then runs the…
gitnexus
A code-graph analysis add-on for examining an existing codebase, including symbols, call paths, execution flows, and effects across repositories. It can query GitNexus through its command-line or MCP interfaces.
cleanup-code-inspections
Reduce technical debt and improve code quality by systematically resolving static analysis warnings.
superlint
This skill describes the mandatory standard operating procedure for using our internal SuperLint tool. Use this when tasks require fixing code quality issues according to corporate standards.