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 andregusman-raiz/a-gusman-claude --skill ag-auditar-react-hooksgit clone --depth 1 https://github.com/andregusman-raiz/a-gusman-claudeWrote 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/andregusman-raiz/a-gusman-claude/ag-auditar-react-hooks)<a href="https://agentmods.dev/skills/andregusman-raiz/a-gusman-claude/ag-auditar-react-hooks"><img src="https://agentmods.dev/badge/skills/andregusman-raiz/a-gusman-claude/ag-auditar-react-hooks/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/andregusman-raiz/a-gusman-claude/ag-auditar-react-hooks"><img src="https://agentmods.dev/badge/skills/andregusman-raiz/a-gusman-claude/ag-auditar-react-hooks.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Excessive Agency · line 4 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
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 | $0.00057 | $0.02598 |
| Opus 5 | $0.00028 | $0.01299 |
| Sonnet 5 | $0.00011 | $0.00520 |
| Haiku 4.5 | $0.00006 | $0.00260 |
Grade A, and why
ag-auditar-react-hooks 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 11d 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 — 249 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ag-auditar-react-hooks — Audit de Hooks React
Auditor especializado em qualidade de Hooks React. Detecta os 4 problemas que o eslint-plugin-react-hooks sozinho nao cobre: heuristica de extracao de custom hook, useState complexo que deveria ser useReducer, deps redundantes, e padroes de uso anti-ergonomicos.
Invocacao
/ag-auditar-react-hooks # CWD, modo report-only
/ag-auditar-react-hooks ~/Claude/GitHub/x # path explicito
/ag-auditar-react-hooks --fix-safe # aplica fixes HIGH-confidence (exhaustive-deps + obvious memo)
/ag-auditar-react-hooks --deep # analise AST + heuristicas de refactor
O que faz (4 categorias)
1. Rules of Hooks (eslint-plugin-react-hooks strict)
Detecta violacoes que o lint padrao captura:
- Hook chamado dentro de
if/else/ternary - Hook dentro de
for/while/forEach/map - Hook depois de
returncondicional - Hook chamado em funcao que nao e component nem custom hook
- Ordem de chamada inconsistente entre renders
Tool: eslint --rule 'react-hooks/rules-of-hooks: error' --rule 'react-hooks/exhaustive-deps: warn'
2. Deps de useEffect/useMemo/useCallback
- Faltando: vars do closure usadas no body mas ausentes do array (cobertura
exhaustive-deps) - Excessivas: vars no array que NAO sao usadas no body (lint nao captura — AST custom)
- Stale closure: setter de state usado dentro de callback sem state estar nas deps
- Object/array literais inline:
useEffect(..., [{foo: 1}])re-cria objeto a cada render → loop infinito disfarcado - Funcao inline em deps:
useEffect(..., [() => x])re-cria a cada render - Deps com primitivos derivados:
[user.name]em vez de[user]quando so name e usado (otimizacao)
3. Candidatos a custom hook
Heuristica de extracao (sinais combinados):
useEffectcom body > 15 linhas E envolve fetch/subscribe/timer- 3+
useStatedeclarados juntos para a mesma feature (ex:loading,data,error) - Logica de setup + cleanup em useEffect aparece em 2+ componentes (duplicacao)
- Combinacao
useState + useEffectque poderia seruseQuery/useSWR/useResource - Imperativo: refs + observers + listeners no mesmo componente
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.
- 11d ago First seen · 249 lines · 57 tokens per session scan A 3308362bbf00
ag-auditar-react-hooks is a skill published in the GitHub repository andregusman-raiz/a-gusman-claude (19 stars, last pushed 3d ago), licensed MIT. It adds 57 tokens to every session and 2,598 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 2026-08-30.
Other skills, from other repositories
frontend-code-review
Trigger when the user requests a review of frontend files (e.g., .tsx, .ts, .js). Support both pending-change reviews and focused file reviews while applying the checklist rules.
react-component-development
Component patterns and best practices for React with TypeScript. Covers functional components, custom hooks, state management, composition patterns, error boundaries, server components, and form handling. Keywords: React component, hooks, state management, TypeScript component, custom hooks, Zustand, useReducer…
auth-flows
Authentication patterns for React apps — Auth.js (NextAuth), Clerk, Supabase Auth. Covers session management, protected routes, role-based access, and OAuth flows.
react-performance-optimization
Performance profiling and optimization for React applications. Covers React Profiler, bundle analysis, code splitting, memoization patterns, image optimization, Core Web Vitals, and server-side rendering performance. Keywords: performance, bundle size, code splitting, web vitals, profiling, React.memo, useMemo…
seo-metadata
SEO patterns for React apps — Next.js Metadata API, Open Graph, structured data (JSON-LD), sitemap generation, and Core Web Vitals optimization.
animation-motion
Animation patterns for React — Framer Motion, CSS transitions, page transitions, micro-interactions, scroll-driven animations, and reduced-motion accessibility.