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.

▶ Voir la démo 📦 Installer 💡 Cas d'usage

Pourquoi l'utiliser

Fonctionnalités clés

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

Démo en direct

Aperçu en pratique

prêt

Installation

Dépôt de l’auteur · Documentation officielle des Skills Claude

Cas d'usage

Usages concrets : Harness (Meta-skill)

Design an incident-response agent team

👤 Claude Code users ⏱ ~15 min intermediate

Quand l'utiliser : You want multiple agents (triage, comms, scribe) cooperating on real incidents instead of one big system prompt.

Déroulement

Brief

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

→ Harness asks scope questions
Answer

Define escalation, channels, scribe duties.✓ Copié

→ Spec drafts emerge
Save

Save specs into /agents/incident/.✓ Copié

→ Reusable team def written

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

Combinaisons

Associez-le à d'autres MCPs pour un effet X10

harness-skill + filesystem

Save designed teams alongside your project

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

Outils

Ce que ce MCP expose

Outil	Entrées	Quand appeler	Coût
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

Coût et limites

Coût d'exécution

Quota d'API: N/A
Tokens par appel: Interview is moderate
Monétaire: Free skill
Astuce: Reuse outputs as-is for next domain; don't redesign from scratch

Sécurité

Permissions, secrets, portée

Portées minimales : fs-read fs-write

Stockage des identifiants : None

Sortie de données : None

Dépannage

Erreurs courantes et correctifs

Output too generic

Provide concrete examples (real past incidents) during the interview

Alternatives

Harness (Meta-skill) vs autres

Alternative	Quand l'utiliser	Compromis
Hand-rolled prompts	Single-agent flow	Doesn't scale to multi-agent

Plus

Ressources

📖 Lire le README officiel sur GitHub

🐙 Voir les issues ouvertes

🔍 Parcourir les 400+ serveurs MCP et Skills