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 huuanh20/awesome-ai-agent-skills --skill ck-qualitygit clone --depth 1 https://github.com/huuanh20/awesome-ai-agent-skillsWrote 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/huuanh20/awesome-ai-agent-skills/ck-quality)<a href="https://agentmods.dev/skills/huuanh20/awesome-ai-agent-skills/ck-quality"><img src="https://agentmods.dev/badge/skills/huuanh20/awesome-ai-agent-skills/ck-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/huuanh20/awesome-ai-agent-skills/ck-quality"><img src="https://agentmods.dev/badge/skills/huuanh20/awesome-ai-agent-skills/ck-quality.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00102 | $0.01771 |
| Opus 5 | $0.00051 | $0.00886 |
| Sonnet 5 | $0.00020 | $0.00354 |
| Haiku 4.5 | $0.00010 | $0.00177 |
Grade A, and why
ck: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 12d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ck:quality — Independent Quality Gate & Auditor
ck:quality never fixes code and never writes tests. It evaluates a target against the shared Engineering Quality Contract and returns an evidence-based, structured report. Remediation is always ck:cook's or ck:fix's job — this skill has no --fix.
Modes
Exactly one of:
--gate <phase-file>— pipeline mode. Scope is the files the current phase created or modified.targetis the phase file's stem (e.g.phase-02-receipt-gate). Always writes a report toplans/{slug}/quality/{target}-quality-report.json. Hard-blocks the phase on any openBLOCKER/HIGHfinding, or aMEDIUMfinding introduced by the current change.--audit <path>— standalone mode on any file, directory, or whole repo. Report-only: prints the result, writes nothing to disk unless--save <path>is also given. Never blocks anything outside itself.--diff <ref>— audit only files changed versus<ref>(e.g.main).--changed— audit only the current working-tree diff (staged + unstaged).--verify <report-path>— re-evaluate exactly the findings in an existing report afterck:cook/ck:fixclaims they're resolved. Produces a new report of the same shape; does not re-scan unrelated code.
--save <path> is only meaningful with --audit/--diff/--changed.
Step 1 — Resolve Scope and Conventions
- Resolve the target file set:
--gate: the phase file's "Files" section, cross-checked againstgit diffsince the phase's last session-notes timestamp.--audit/--diff/--changed: the given path, diff range, or working tree respectively.--verify: thereviewed_fileslist from the report being verified, refreshed against currentgit diffin case scope grew.
- Detect the stack(s) present in scope (
package.json+.ts→ TypeScript/Node,pyproject.toml/*.py→ Python,*.csproj→ .NET, etc. — seereferences/adapters.md). - Read 2-3 sibling files outside the changed set to learn actual naming, constants/error, module-structure, and DI conventions already in use. Existing convention always outranks a generic rule.
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.
- 12d ago First seen · 100 lines · 102 tokens per session scan A 23d85f5f314b
ck:quality is a skill published in the GitHub repository huuanh20/awesome-ai-agent-skills (1 stars, last pushed 1mo ago), licensed MIT. It adds 102 tokens to every session and 1,771 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
check-mcp-json
Safely review, triage, repair, and merge ToolSDK MCP Registry package JSON pull requests. Use when an agent needs to validate files under packages/, detect duplicate registry keys, classify community PRs, make authorized fixes on contributor branches, close invalid or duplicate PRs, or squash-merge approved PRs.
review
Review Playwright tests for quality. Use when user says "review tests", "check test quality", "audit tests", "improve tests", "test code review", or "playwright best practices check".
skill-static-review
A checklist-based review skill for inspecting an agent skill's files, instructions, dependencies, and expected outputs before release. It produces a structured quality report rather than running the skill.
github-maintainer
Use this when the user wants maintainer-grade judgment over a GitHub project queue. The goal is not just to list issues or pull requests; it is to decide what each item means, what evidence exists, what is risky, and what should happen next.
jury
Standalone cross-family cascade-then-jury reviewer. Use when the user says "jury", "cross-family review", "judge this", "jury beats judge", or "review with a panel". Runs a free OAuth-local-CLI jury core: Gemini-Flash + GPT small-fish first, then one cross-family tiebreaker only when needed.
code-review-and-quality
Conducts multi-axis code review. Use before merging any change. Use when reviewing code written by yourself, another agent, or a human. Use when you need to assess code quality across multiple dimensions before it enters the main branch.