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-depurar-errogit 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-depurar-erro)<a href="https://agentmods.dev/skills/andregusman-raiz/a-gusman-claude/ag-depurar-erro"><img src="https://agentmods.dev/badge/skills/andregusman-raiz/a-gusman-claude/ag-depurar-erro/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-depurar-erro"><img src="https://agentmods.dev/badge/skills/andregusman-raiz/a-gusman-claude/ag-depurar-erro.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 | $0.00060 | $0.02286 |
| Opus 5 | $0.00030 | $0.01143 |
| Sonnet 5 | $0.00012 | $0.00457 |
| Haiku 4.5 | $0.00006 | $0.00229 |
Grade B, and why
ag-depurar-erro scanned grade B with 2 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
> **Reasoning protocol (tier topo — Fable, equivalente a `reasoning_effort=xhigh` do Codex)**: ANTES de propor diagnostico, Exhaust 3+ hipoteses concorrentes → Verify cada uma com Read/Bash/grep → Falsify (o que refutari Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
[ ] curl -I <url> → headers mostram versao/timestamp atualizado? How it starts
The opening of the file, as written. The whole thing — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ag-depurar-erro — Depurar Erro
Reasoning protocol (tier topo — Fable, equivalente a
reasoning_effort=xhighdo Codex): ANTES de propor diagnostico, Exhaust 3+ hipoteses concorrentes → Verify cada uma com Read/Bash/grep → Falsify (o que refutaria?) → Connect cadeia causal sintoma→causa→fix → Report com confianca explicita (alta/media/baixa). Detalhes:.claude/rules/deep-reasoning-directive.md. NUNCA aceitar primeira hipotese plausivel sem listar concorrentes.
Spawn the ag-depurar-erro agent to diagnose and fix bugs using root cause analysis.
Invocation
Use the Agent tool with:
subagent_type:ag-depurar-erromode:bypassPermissionsrun_in_background:trueprompt: Compose from template below + $ARGUMENTS
Dynamic Context
- Errors known: !
head -30 docs/ai-state/errors-log.md 2>/dev/null || echo "none"
Prompt Template
Projeto: [CWD or user-provided path]
Erro: [error message or description from $ARGUMENTS]
Contexto: [when it happens, what changed, environment]
Fluxo: Reproduzir → Isolar → Diagnosticar → Corrigir → Verificar.
- Ler errors-log.md ANTES de comecar (nao repetir tentativas falhadas)
- Encontrar causa raiz, NAO apenas sintoma
- Verificar SEMPRE se existem multiplas causas independentes
- Max 2 tentativas de fix por causa — escalar ao usuario se nao resolver
- Registrar diagnostico e resolucao em errors-log.md
Important
- ALWAYS spawn as Agent subagent — do NOT execute inline
- After spawning, confirm to the user that the debug agent is running
- Reads errors-log.md to avoid repeating failed attempts
- Follows root-cause-debugging.md protocol
Decision Tree: Classifying the Bug
BUG REPORTADO
├── Fix aplicado mas bug persiste? → DEPLOY GAP
│ ├── Verificar: build atual reflete o codigo?
│ ├── Verificar: cache (CDN, browser, server) invalidado?
│ ├── Verificar: processo reiniciado apos deploy?
│ └── Verificar: deploy foi para o ambiente correto (prod vs staging)?
│
├── Bug aparece em camadas diferentes? → MULTI-LAYER BUG
│ ├── Frontend: componente renderiza dado errado?
│ ├── Backend: API retorna valor incorreto?
│ ├── Config: variavel de ambiente ausente ou errada?
│ └── → Rastrear da UI ate banco — corrigir TODAS as camadas
│
├── Funciona para alguns users mas nao outros? → PERMISSION/ACL BUG
│ ├── RLS policy inconsistente entre tabelas relacionadas?
│ ├── Role/claim ausente no JWT?
│ ├── Middleware valida permissao diferente da query?
│ └── → Auditar toda a cadeia: JWT → middleware → RLS → query
│
└── Bug unico e isolado? → SINGLE-CAUSE BUG
└── Fluxo padrao: Reproduzir → Root Cause → Fix → Verificar
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 · 215 lines · 60 tokens per session scan B ce2ecf3fb146
ag-depurar-erro is a skill published in the GitHub repository andregusman-raiz/a-gusman-claude (19 stars, last pushed 3d ago), licensed MIT. It adds 60 tokens to every session and 2,286 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
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.
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.
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"…
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…
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…
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.