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 agentmods add skills/asmn-96/ai-agents-skills-toolkit/code-qualitynpx skills add ASMN-96/ai-agents-skills-toolkit --skill code-qualitygit clone --depth 1 https://github.com/ASMN-96/ai-agents-skills-toolkitWrote 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/asmn-96/ai-agents-skills-toolkit/code-quality)<a href="https://agentmods.dev/skills/asmn-96/ai-agents-skills-toolkit/code-quality"><img src="https://agentmods.dev/badge/skills/asmn-96/ai-agents-skills-toolkit/code-quality.svg" alt="Measured on agentmods" 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 | $0.00058 | $0.00812 |
| Opus 5 | $0.00029 | $0.00406 |
| Sonnet 5 | $0.00012 | $0.00162 |
| Haiku 4.5 | $0.00006 | $0.00081 |
Grade A, and why
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 5d 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Quality
Use this as the canonical final code-quality skill for web application changes.
This skill routes quality checks through project-owned scripts first. It does not authorize dependency changes, package-manager changes, broad rewrites, CI edits, MCP setup, global config writes, external tool activation, or duplicating Superpowers execution discipline.
Route Checks
Prefer available project-owned checks in this order: typecheck, lint, focused tests, build, then optional scanners only if already configured.
Measurable Quality Targets
- Changed behavior needs focused tests or a documented exception with residual risk.
- Coverage percentages count only when the project already measures coverage and the command actually ran.
- For critical business, auth, data, payment, release, or public API behavior, prefer branch/edge assertions over broad snapshot-only checks.
- Do not invent coverage numbers, pass rates, or quality gates from registry metadata, generated files, or recommended scripts.
Review Focus
- Type boundaries are explicit and stable.
- React hooks, async state, and rendering behavior are correct.
- Loading, error, empty, disabled, failure, and recovery states are handled.
- Tests cover changed behavior or critical regression risk.
- Generated or changed production code receives a guard pass for broad error swallowing, hardcoded success paths, invented APIs, copy-from-similar mistakes, unnecessary abstractions, and dead code introduced by the change.
- Generated or changed tests are reviewed for behavior assertions, justified system-boundary mocks, real state/value objects, data-driven variants where appropriate, preserved production regressions, and removal of tests that only verify framework guarantees.
- Existing TypeScript, typed ESLint, React Hooks, Vitest, Testing Library, and build scripts are used when project-owned.
- Dry-run, skipped, unavailable, metadata-only, or planned quality gates are not reported as real execution.
- Route React projects to React Doctor as
active-if-detectedwhen project-owned andowner-approved-installwhen absent; it supplements ESLint, React Hooks, tests, and browser evidence. - Treat Playwright, Oxlint, Semgrep, dependency-cruiser, Madge, jscpd, actionlint, zizmor, Gitleaks, and OSV Scanner as usable only when project-owned or owner-approved. Start new/noisy CI use as
ci-advisory; promote to blocking only after calibration and owner approval. - Route performance, scalability, and cache-sensitive changes through
.ai-toolkit/methods/performance/performance-scalability-cache-readiness.md. Canonical toolkit source:methods/performance/performance-scalability-cache-readiness.md. - Route cross-surface API/client compatibility through
.ai-toolkit/methods/architecture/cross-surface-client-contracts.mdwhen frontend changes affect multiple consumers. Canonical toolkit source:methods/architecture/cross-surface-client-contracts.md. Use.ai-toolkit/methods/api/api-contract-and-routing-readiness.mdfor explicit API route or contract readiness. Canonical toolkit source:methods/api/api-contract-and-routing-readiness.md.
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.
- 5d ago First seen · 46 lines · 58 tokens per session scan A 593bd52e3cc1
code-quality is a skill published in the GitHub repository ASMN-96/ai-agents-skills-toolkit (5 stars, last pushed 1mo ago), licensed MIT. It adds 58 tokens to every session and 812 once invoked, about $0.0003 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
opik-frontend
React frontend patterns for Opik. Use when working in apps/opik-frontend, on components, state, or data fetching.
frontend-patterns
Frontend development patterns for React, Next.js, state management, performance optimization, and UI best practices.
split-micro-app
Use when splitting a monorepo surface into a standalone micro app (React Router SSR on Cloudflare Workers), splitting a surface whose rendering code lives in the lobehub-cloud business overlay, fighting SSR bundle bloat from main-src imports, deploying its assets to CDN/R2, adding SEO/OG meta to an SSR page, adding a…
vercel-react-best-practices
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance…
design-prototype
Produce an interactive single-file HTML design prototype using the REAL LobeHub design system (@lobehub/ui + antd + antd-style tokens) with production-style React — no build step, opens directly in a browser. Use when asked for a design prototype / interactive mockup / 交互原型 / 出个原型 / 设计稿 HTML for a page or flow, or to…
react
LobeHub React component conventions. Use when editing TSX UI, choosing base-ui vs @lobehub/ui vs antd, styling with antd-style, component boundaries, local state, layouts, render performance, or memoization.