convez.ai
MCP ServerAutomaçãoAvançado
aimasteracc

Harness Kit

aimasteracc/harness-kit

Operacionaliza 5 padrões críticos de agentes autônomos sem falhas silenciosas

Ver no GitHub
InicialPluginScore · de 0 a 100

MCP server com cinco skills executáveis para construir harnesses de agentes autônomos que não falham silenciosamente. Inclui auditoria de modos de falha, arquitetura de CLAUDE.md orientada por constraints, briefing de sub-agentes, handoff de contexto e verificações pré-voo. Baseado em padrões battle-tested de engenharia de agentes.

Instalação

$npx convez-ai aimasteracc/harness-kit

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
1
Forks
0
Acompanhando
0
Saúde
42%
Último commit
há 5 meses
Versão
—
Issues abertas
0
Contribuidores
1

Casos de uso

  • Auditar planos de agentes contra 7 modos de falha conhecidos antes de execução longa
  • Gerar CLAUDE.md constraint-first para onboarding de repositórios em Claude Code
  • Escrever briefs de sub-agentes que sobrevivem assimetria de messaging
  • Capturar estado mínimo para resumir após reset ou compaction de contexto
  • Executar verificação pré-voo em 7 pontos antes de runs desatendidas

Veredito

Ferramenta altamente especializada para engenheiros de agentes que enfrentam falhas reais em produção. Operacionaliza padrões testados em combate, mas exige experiência prévia em agent engineering para máxima utilidade.

README

A tradução para o português deste README ainda está na fila.

🛠️ Harness Kit

Five executable skills for building autonomous agent harnesses that don't silently fail

From the author of Inside Claude Code — the reverse-engineering field guide to agent engineering.

The book teaches the patterns. This kit runs them.


What it is

A Claude Code plugin that turns the hard-won lessons of building autonomous agents into skills you invoke, not chapters you read. Each one operationalizes a failure you've probably already hit:

SkillInvoke it whenWhat it does
failure-mode-auditbefore a long run, or after one stallsAudits a plan or transcript against the 7 known agent failure modes and prescribes the verified fix for each
claude-md-architectonboarding a repo to Claude CodeInspects the project + interviews you, writes a lean constraint-first CLAUDE.md
subagent-briefspawning a sub-agent / swarm stepWrites a brief that survives the messaging asymmetry — so the sub-agent completes instead of silently aborting
context-handoffnearing the context limitCaptures the minimum state to resume cleanly after a reset or compaction
harness-preflightright before an unattended runA 7-point go/no-go check on your harness before you hand it hours of work

Plus /harness-init — scaffolds a sound harness (CLAUDE.md + handoff convention + pre-flight) into any repo in one command.

Why it exists

Most "agent frameworks" hand you more abstraction. The failures that actually waste your time are smaller and more specific: an agent that declares a half-finished task done, a sub-agent that aborts because it was told to "wait for a message" it can never receive, a run that panics near its context limit with capacity to spare. These have names and fixes — Harness Kit encodes them so you stop rediscovering them by hand.

Install

# In Claude Code:
/plugin marketplace add aimasteracc/harness-kit
/plugin install harness-kit

# Then, in any repo:
/harness-init

Skills auto-activate by description, or invoke directly (e.g. "run a failure-mode audit on this plan").

What you get

  • 5 skills + 1 command, all plain-text and inspectable — no black boxes, no runtime deps.
  • Works alongside any other plugins; nothing to configure.
  • Battle-tested framing from a full teardown of how a leading agentic coding tool behaves.

Go deeper

Harness Kit is the toolbox. Inside Claude Code is the manual — the five-layer prompt architecture, the request pipeline, all 12 patterns, and the full treatment of the 7 failure modes, in English / 简体中文 / 日本語.

License

See LICENSE.md. © 2026 aimasteracc. Independent work; not affiliated with Anthropic.

Ver o original no GitHub

Bom para

Relacionados