agent-harness

Name: agent-harness
Author: alirezarezvani

alirezarezvani ★ 28593

agent-harness turns domain skill folders into a bounded agentic loop that compiles goals into verifiable task plans, executes and verifies tasks with retry caps, and escalates to humans when budgets exhaust rather than faking success. It ships a manifest builder, goal compiler, JSON-backed loop controller, 18 per-domain harness manifests, and a harness-runner agent with /cs-harness command, all using stdlib Python tools with no external dependencies.

Project Management Productivity No API key detected prompt pack

Install

> /plugin marketplace add alirezarezvani/claude-skills/tree/HEAD/engineering/agent-harness

> /plugin install agent-harness

Source: https://github.com/alirezarezvani/claude-skills/tree/HEAD/engineering/agent-harness

What it's made of

1 command · 1 agent · 1 skill

Commands: 1
Agents: 1
Skills: 1
MCP servers: 0
Hooks: 0

What it needs & plugs into

API keys: none
Paid services: none detected
External tools: none
Talks to: nothing external detected

Analyzed 2026-11-12. Facts extracted from the plugin's files. Prose generated by claude-haiku-4-5-20251001.

Is this your plugin?

Claim it to keep the card accurate and enter the weekly contest. Requires signing in as the GitHub owner (alirezarezvani).