Harness (Meta-skill)

Name: Harness (Meta-skill) (Claude Skill)
Author: revfactory

A meta-skill: tell it your domain, it designs the agent team for you (roles, prompts, hand-offs) and saves the specs for reuse.

Harness treats agent design as a first-class workflow: you describe your domain (incident response, content review, code triage); it asks the right questions, then emits a documented team — roles, system prompts, when each takes over, and shared memory boundaries.

▶ Ver demo 📦 Instalar 💡 Casos de uso

Por que usar

Principais recursos

Interview-driven team design
Outputs role specs as Markdown
Defines hand-off rules between agents
Specifies shared vs private memory
Versioned team definitions
Reuse across projects

Demo ao vivo

Como fica na prática

pronto

Instalação

Repositório do autor · Documentação oficial de Skills do Claude

Casos de uso

Usos do mundo real: Harness (Meta-skill)

Design an incident-response agent team

👤 Claude Code users ⏱ ~15 min intermediate

Quando usar: You want multiple agents (triage, comms, scribe) cooperating on real incidents instead of one big system prompt.

Fluxo

Brief

Tell harness: "incident response, B2B SaaS, 3 specialists please."✓ Copiado

→ Harness asks scope questions
Answer

Define escalation, channels, scribe duties.✓ Copiado

→ Spec drafts emerge
Save

Save specs into /agents/incident/.✓ Copiado

→ Reusable team def written

Resultado: Documented multi-agent team you can rerun next incident, not a one-off prompt.

Combinações

Combine com outros MCPs para 10× de alavancagem

harness-skill + filesystem

Save designed teams alongside your project

Combine harness-skill with filesystem: Save designed teams alongside your project✓ Copiado

Ferramentas

O que este MCP expõe

Ferramenta	Entradas	Quando chamar	Custo
design	(see docs)	Run the design interview	1 call
review	(see docs)	Critique an existing team for missing roles or unclear hand-offs	1 call

Custo e limites

O que custa rodar

Cota de API: N/A
Tokens por chamada: Interview is moderate
Monetário: Free skill
Dica: Reuse outputs as-is for next domain; don't redesign from scratch

Segurança

Permissões, segredos, alcance

Escopos mínimos: fs-read fs-write

Armazenamento de credenciais: None

Saída de dados: None

Solução de problemas

Erros comuns e correções

Output too generic

Provide concrete examples (real past incidents) during the interview

Alternativas

Harness (Meta-skill) vs. outros

Alternativa	Quando usar	Troca
Hand-rolled prompts	Single-agent flow	Doesn't scale to multi-agent

Mais

Recursos

📖 Leia o README oficial no GitHub

🐙 Ver issues abertas

🔍 Ver todos os 400+ servidores MCP e Skills