agentleFS
justineserna1zjustineserna1z/Dedalo/skills/module-audit/SKILL.md

module-audit

Skill2 starsChanged 4 months agoApache-2.0View on GitHub

Auditoría profunda de un módulo o dominio con subagentes en paralelo, informe consolidado, plan spec-driven en fases atómicas y checklist QA. Usar cuando el usuario diga "revisemos el módulo de X", "auditar X", "gaps en X", "explorar a fondo X", o quiera rehacer/revisar un dominio entero antes de codear. Complementa la skill flow — no reemplaza commit/verificación/documentación.

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. gufranco/claude-engineering-rules★ 3same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository2 other files it gives its agents.

The file

Files
SKILL.md

Module Audit — subagentes por arista + plan atómico

Patrón probado en Engram (auditoría de Proyectos, 2026-06-29). Rentable solo para trabajo que abarca un módulo entero — para tareas puntuales usar flow directamente (hallazgo HiveMind H3: multi-agente en tareas simples = misma calidad, 30× el tiempo).

1. AUDITAR — 3 a 5 subagentes Explore en paralelo, uno por arista

AristaPregunta guía
UI/UXFlujos, estados vacío/error/carga, mobile, permisos en pantalla
Backend APIEndpoints, DTOs, validaciones, reglas de negocio
Datos/MemoriaSchema, migraciones, embeddings/RAG, side effects de editar/borrar
Seguridad/tenantAislamiento por tenant, IDOR, roles, feature gates
IntegracionesMódulos que consumen o emiten eventos hacia este dominio

Cada subagente reporta hallazgos con archivo:línea (bugs CONFIRMADOS vs sospechas). La consolidación no se delega — la hace el agente principal.

2. CONSOLIDAR

Informe único: estado verificado, bugs confirmados, gaps priorizados por impacto/esfuerzo, decisiones de producto que requieren al humano (tabla para confirmar antes de planear).

3. PLANEAR — fases atómicas

Plan spec-driven: tareas de ≤2 h con criterio de aceptación verificable, clasificadas por la escalera de delegación (mecánica/estándar/crítica), con orden y dependencias. 1 fase = 1 commit; typecheck + tests verdes entre fases.

4. EJECUTAR — secuencial supervisado

Cada fase con su spec Localiza/Cambio/Verificación. Aplicar regulación: si F sube (rechazos, desvíos >2× estimado), subir tier o congelar (SPEC_REGULATION.md).

5. QA — checklist final

Verificación de comportamiento extremo a extremo (incluye caso de tenant cruzado → 403), typecheck y suite completa del área, telemetría registrada, y documentación (DECISIONS_LOG/INCIDENT_LOG/CLAUDE.md) actualizada.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.