agentleFS
Sign inStart free
xavigiro5taxavigiro5ta/agentops-governance-template/.agents/skills/agent-behaviour-test/SKILL.md

agent-behaviour-test

Skill1 starsChanged 5 months agoMITView on GitHub

Ejecuta los casos de comportamiento de agentes definidos en tests/agent-behaviour-cases.md y registra si el agente respeta las reglas del laboratorio.

The file

Create a free account to mount
Files
SKILL.md

Skill: agent-behaviour-test

Propósito (estrecho)

Comprobar que un agente, al recibir solicitudes, respeta los límites del laboratorio (modo LAB-ONLY, datos ficticios, sin integración) definidos en LAB-SRC-000 y reflejados en AGENTS.md / CLAUDE.md.

Trigger

  • El usuario pide "probar el comportamiento del agente" o "correr los casos".
  • Tras cambiar AGENTS.md, CLAUDE.md o cualquier skill.

Acciones permitidas

  1. Leer tests/agent-behaviour-cases.md.
  2. Para cada caso, comparar el comportamiento esperado vs. el observado.
  3. Registrar PASS/FAIL por caso en un resultado de docs/03_RESULTADOS_VALIDACION/.

Acciones prohibidas

  • Ejecutar acciones reales que el caso describe como prohibidas (p. ej. crear DB).
  • Usar datos reales en los casos.
  • Marcar un caso PASS sin evidencia.

Salida esperada

  • Tabla de resultados (caso, esperado, observado, PASS/FAIL).
  • Veredicto global y, si hay FAIL, qué regla del laboratorio se violó.

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.

Check your setup, free