AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Ag Corrigir Bugs

skill-andregusman-raiz-a-gusman-claude-ag-corrigir-bugs · by andregusman-raiz

Bugfix unificado com auto-routing. Triage (classificar bugs), Fix (1 bug + 5 gates), Batch (2-5 bugs em sprints), Parallel (6+ bugs em Agent Teams). Substitui ag-corrigir-bugs/24/25/26.

No reviews yet
0 installs
27 views
0.0% view→install

Install

$ agentstack add skill-andregusman-raiz-a-gusman-claude-ag-corrigir-bugs

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-andregusman-raiz-a-gusman-claude-ag-corrigir-bugs)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
1mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Ag Corrigir Bugs? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

ag-corrigir-bugs — Bugfix

Spawn the ag-23-bugfix agent to handle any bugfix workflow — from triage to parallel execution.

Auto-Routing

The agent auto-selects the best mode based on input:

| Input | Mode | Behavior | |-------|------|----------| | Lista sem contexto / "triar" | --triage | Read-only classification + sprint plan | | 1 bug claro | --fix | Single fix with 5 quality gates | | 1 bug obscuro | ag-depurar-erro first | Then --fix | | 2-5 bugs | --batch | Sequential sprints, incremental commits | | 6+ independent bugs | --parallel | Agent Teams, exclusive ownership | | 6+ bugs with file overlap | --batch | Sequential for safety |

Invocation

Use the Agent tool with:

  • subagent_type: ag-23-bugfix
  • mode: bypassPermissions
  • run_in_background: true (except --fix which runs foreground)
  • prompt: Compose from template below + $ARGUMENTS

Prompt Template

Projeto: [CWD or user-provided path]
Modo: [--triage|--fix|--batch|--parallel] (ou auto-detect)
Bugs: [lista de bugs — IDs, descricoes, path para diagnostico, ou inline]
Branch: [branch atual ou nome para criar]
Diagnostico: [path para bug_triage.md gerado por mode triage, se disponivel]

Executar bugfix no modo indicado (ou auto-detect baseado na quantidade de bugs).
Seguir todas as quality gates do modo selecionado.

Important

  • ALWAYS spawn as Agent subagent — do NOT execute inline
  • After spawning, confirm to the user
  • For --triage: agent is READ-ONLY, does NOT fix bugs
  • For --fix: runs foreground (sequential quality gates, user needs result)
  • For --batch: uses worktree isolation
  • For --parallel: uses Agent Teams with exclusive file ownership
  • Gates are blocking: if any gate fails, fix before proceeding

Escalacao: Issues para Bugs Nao Resolvidos

Mode --triage

Apos classificar bugs, spawnar ag-registrar-issue para cada bug que NAO sera fixado nesta sessao:

Agent({
  subagent_type: "ag-registrar-issue",
  name: "issue-registrar",
  model: "haiku",
  run_in_background: true,
  prompt: "Repo: [detectar]\nOrigem: ag-corrigir-bugs --triage\nSeveridade: [P0-P3 da triagem]\nTitulo: [bug title]\nContexto: [descricao + classificacao + sprint sugerido]\nArquivos: [arquivos afetados]\nLabels: bug, triage"
})

Mode --fix / --batch / --parallel

Se um bug falha todas as tentativas de fix (gate nao passa):

  • Registrar via ag-registrar-issue com contexto das tentativas falhadas
  • Continuar com proximo bug (nao bloquear batch/parallel)

Migration Note

This agent replaces:

  • ag-B-25 (diagnosticar-bugs) → mode --triage
  • ag-corrigir-bugs (fix-verificar) → mode --fix
  • ag-corrigir-bugs-batch → mode --batch
  • ag-B-24 (bugfix-paralelo) → mode --parallel

All functionality, anti-patterns, quality gates, and workflows from the original agents are preserved in the merged agent definition.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.