agentleFS
Data-UnixData-Unix/MCP-MALTEGO/.claude/skills/add-machine/SKILL.md

add-machine

Skill1 starsChanged 14 days agoMITView on GitHub

Procedimiento para crear o modificar una Machine (secuencia automática de transforms con etapas, rondas y presupuestos) en maltego-mcp, predefinida en código o propia en el catálogo TOML. Úsala para automatizar un flujo de reconocimiento.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

Files
SKILL.md

Añadir una Machine

  • Semántica: cada etapa aplica sus transforms a todo lo descubierto en la ronda (accumulate=True); con varias rondas, la frontera siguiente son las entidades nuevas. Las cadenas ad hoc (transforms=[...]) aplican cada paso solo a lo del paso anterior.
  • Predefinida: añade Machine(nombre, descripción, input_types, stages) a BUILTIN_MACHINES en src/maltego_mcp/machines.py y, si es la natural para un tipo, a DEFAULT_MACHINE_BY_TYPE.
  • Propia del usuario (sin código; equivale a register_machine de otros MCP: semilla = input_types, transforms por etapa = stages, límite de expansión = rounds), en ~/.maltego-mcp/transforms.toml:
    [[machines]]
    name = "MiRecon"
    input_types = ["maltego.Domain"]
    stages = [["DNSToIP", "DomainToNS"], ["IPToAS"]]
    rounds = 1
  • Incluye transforms de proveedores sin miedo: si falta la clave se omiten y se informa en unavailable.
  • Tests: en tests/test_copilot.py con el Router simulado; comprueba etapas, que no se repite un transform sobre la misma entidad y el presupuesto max_total_entities.
  • Documenta la Machine en README.md, README.es.md, docs/USO.md y CHANGELOG.md.

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.