ag-cacar-bugs

ag-cacar-bugs is a skill for Claude Code from andregusman-raiz/a-gusman-claude. It costs 56 tokens per session (1,548 once invoked), scanned A, original, MIT.

A read-only code scan that looks for bugs before they appear in production. It checks for issues such as null references, race conditions, type mismatches, and weak error handling.

In plain words
What is it for?
Scanning a selected area or the whole project in quick or deep mode and producing a report of potential bugs.
Why use it?
It helps find hidden or intermittent problems before users encounter them, without changing the code during the scan.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter; mentions subagents.

Good fit Scanning a selected area or the whole project in quick or deep mode and producing a report of potential bugs.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/andregusman-raiz/a-gusman-claude/ag-cacar-bugs
Install

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.

Any agent
npx skills add andregusman-raiz/a-gusman-claude --skill ag-cacar-bugs
Clone the repo
git clone --depth 1 https://github.com/andregusman-raiz/a-gusman-claude

Made for: Claude Code.

Wrote 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.

agentmods badge for ag-cacar-bugs

README.md
[![agentmods](https://agentmods.dev/badge/skills/andregusman-raiz/a-gusman-claude/ag-cacar-bugs/github.svg)](https://agentmods.dev/skills/andregusman-raiz/a-gusman-claude/ag-cacar-bugs)
Your own site
<a href="https://agentmods.dev/skills/andregusman-raiz/a-gusman-claude/ag-cacar-bugs"><img src="https://agentmods.dev/badge/skills/andregusman-raiz/a-gusman-claude/ag-cacar-bugs/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.

agentmods 80×15 button for ag-cacar-bugs

Your own site · 80×15
<a href="https://agentmods.dev/skills/andregusman-raiz/a-gusman-claude/ag-cacar-bugs"><img src="https://agentmods.dev/badge/skills/andregusman-raiz/a-gusman-claude/ag-cacar-bugs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,548 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
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.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00056 $0.01548
Opus 5 $0.00028 $0.00774
Sonnet 5 $0.00011 $0.00310
Haiku 4.5 $0.00006 $0.00155

Measured 12d ago against content hash c01a83ebd2c2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

ag-cacar-bugs 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.

skills/ag-cacar-bugs/SKILL.md · 160 lines

How it starts

The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ag-cacar-bugs — Bug Hunter Proativo

Spawn the ag-cacar-bugs agent to proactively hunt for latent bugs before they manifest in production.

Diferenca vs ag-corrigir-bugs

ag-corrigir-bugs ag-cacar-bugs
Trigger Bug reportado Proativo / preventivo
Modo Reativo (fix) Scan (detect)
Output PR com fix Report com bugs potenciais
Modifica codigo Sim NAO (read-only)

Invocation

Use the Agent tool with:

  • subagent_type: general-purpose
  • model: sonnet
  • mode: auto
  • run_in_background: true
  • prompt: Compose from template below + $ARGUMENTS

Prompt Template

Projeto: [CWD or user-provided path]
Area: [path especifico ou "full scan"]
Modo: [--quick (top patterns) | --deep (analise completa)]

Voce e um bug hunter adversarial. Pense como um **QA senior que odeia falsos negativos**.
Voce assume que todo codigo tem bugs ate prova contraria. Encontre bugs LATENTES —
problemas que existem no codigo mas que ainda nao se manifestaram em producao
(ou se manifestam intermitentemente).

## Categorias de Bugs para Cacar

### 1. Null/Undefined Bombs
- Acesso a propriedade sem optional chaining onde o valor pode ser null
- Destructuring sem defaults em dados de API
- `.length` em arrays que podem ser undefined
- Grep: propriedades acessadas sem `?.` em dados vindos de fetch/API

### 2. Race Conditions
- useState + useEffect sem cleanup (stale closures)
- Promises nao canceladas em unmount
- Shared mutable state entre requests (module-level vars em serverless)
- Concurrent writes sem lock (Supabase upsert sem unique constraint)

### 3. Type Safety Gaps
- `as any` ou `as unknown as X` (type assertions perigosas)
- Zod schemas que nao matcham com tipos TypeScript
- API responses usadas sem validacao (trust blindly)
- Enum values hardcoded vs fonte de verdade

### 4. Error Handling Gaps
- try/catch com catch vazio (`catch {}` ou `catch(e) {}`)
- Promises sem .catch() (unhandled rejection)
- API routes sem error response padronizado
- Falta de error boundary em componentes criticos
- Error Boundary SEM retry (resetErrorBoundary nao implementado) — usuario fica preso em estado de erro
- console.error sem feedback ao usuario (erro silencioso visual)
- Async em useEffect sem cleanup de unmount (setState apos unmount)
- Toast/Alert de erro sem texto acionavel ("Algo deu errado" sem proximo passo)

### 5. Data Integrity
- Deletes sem cascade check (FK violations)
- Updates sem WHERE (mass update acidental)
- Timestamps sem timezone (comparacao incorreta)
- Numeros como strings (sorting lexicografico vs numerico)

### 6. Security Bugs
- IDOR (acesso a recurso sem verificar ownership)
- Mass assignment (spread de body direto no insert)
- Rate limiting ausente em endpoints criticos
- SSRF em URL handling (fetch de URL user-provided)

### 7. Performance Bombs
- useEffect sem deps array (re-render infinito)
- Map/filter/reduce encadeados em arrays grandes (O(n*m))
- Falta de pagination em queries que crescem
- Imports dinamicos sem Suspense boundary

### 8. Hook Correctness (Rules of Hooks + deps)
- Hook chamado dentro de if/else/ternary (BLOCKER)
- Hook dentro de for/while/forEach/map (BLOCKER)
- Hook depois de return condicional (BLOCKER)
- useEffect/useMemo/useCallback com deps faltando (closure stale)
- useEffect/useMemo/useCallback com deps redundantes (over-trigger)
- Object/array literal inline em array de deps (re-render infinito disfarcado)
- 4+ useState correlacionados (candidato a useReducer)
- useEffect > 15 linhas com fetch/subscribe (candidato a custom hook)

Para audit completo de Hooks: usar `/ag-auditar-react-hooks` (skill dedicada).

## Scoring

Cada bug encontrado recebe:
- **Severidade**: CRITICO (crash/data loss), ALTO (bug intermitente), MEDIO (edge case), BAIXO (code smell)
- **Confianca**: CERTO (reproduzivel), PROVAVEL (logica indica), POSSIVEL (depende de contexto)
- **Impacto**: PRODUCAO, DESENVOLVIMENTO, TESTES

Reportar apenas bugs com confianca >= PROVAVEL.

## Output

Escrever em `docs/bug-hunt-[data].md`:

```markdown

Read the full file on GitHub · 160 lines

Changes

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.

  1. 12d ago First seen · 160 lines · 56 tokens per session scan A c01a83ebd2c2

Subscribe to this mod's changes

ag-cacar-bugs is a skill published in the GitHub repository andregusman-raiz/a-gusman-claude (19 stars, last pushed 4d ago), licensed MIT. It adds 56 tokens to every session and 1,548 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.

Related

Other skills, from other repositories

manage-skills

A maintenance workflow for checking whether project verification skills still cover the code and rules that changed during a session.

sangrokjung/claude-forge · 54 tokens

systematic-debugging

Structured debugging methodology — use before proposing fixes for any error or failure. Covers: code bugs, build errors, deploy failures, config conflicts, dependency issues, infra problems. Also use when previous fix attempts failed or root cause is unclear.

sangrokjung/claude-forge · 53 tokens

review-loop

Run the adversarial verification loop — implement, then hand the change to a fresh checker that did not write it, fix what it finds, and re-dispatch until APPROVE. Use before claiming any behavioural change is done, and on requests like "review loop", "adversarial review", "independent review", "get this verified"…

sangrokjung/claude-forge · 100 tokens

docs-release-notes

Use when a change needs a user-visible release-note, changelog, or changeset entry — "add a release note", "add a changeset for this", "what goes in the changelog?", "write up what shipped", "note this for the next release" — or when finalizing a branch whose customer-visible features, bug fixes, or UI changes should…

The01Geek/prflow · 106 tokens

retrospective-audit

Stage B of /prflow:retrospective-weekly: given a most-recent-first subset of one recurring pattern's occurrence-PR context bundles (bounded by auditbundlecap), re-derive the root cause and return one JSON object carrying a ranked findings array (one to three sub-patterns) — no edits, no worktree. Invoked as a subagent…

The01Geek/prflow · 91 tokens

taiyi-health

A codebase health review process that samples recently changed production modules and test files, then checks for issues such as duplication, unused code, and unused dependencies.

Dong90/oh-my-taiyiforge · 23 tokens