agent-harness

v1.0.0

Turn any domain folder of skills into a bounded agentic loop: a manifest builder inventories a domain's skills/tools/checks, a goal compiler turns a goal into a verifiable task plan (refusing vague goals with forcing questions), and a JSON-backed loop controller drives execute->verify->close with retry caps, controller-run verification (no verification theater), human escalation on exhausted budgets, and a close gate that refuses while any task is unverified. Ships 3 stdlib Python tools, 18 committed per-domain harness manifests + JSON schema, 3 references citing the 2024-2026 agent-harness canon, harness-runner agent + /cs:harness command. Use when an agent should pick up a goal and drive it to a verified close across a domain.

Claude Code1 skill

by Alireza RezvaniMIT24.2kupdated 10 hours ago

Source

$ git clone https://github.com/alirezarezvani/claude-skills

Clone the source, then follow the repository's marketplace instructions for your runtime. The plugin root is engineering/agent-harness/ inside the repository.

Layout

engineering/agent-harness/

├── .claude-plugin/plugin.json
└── skills/agent-harness/SKILL.md

Skills1

agent-harnessskills/agent-harness/SKILL.md

Turn any domain folder of skills into a bounded agentic loop: compile a goal into a verifiable task plan, execute tasks with the domain's own tools, verify every task with machine-run checks, retry with caps, escalate to a human when budgets exhaust, and refuse to close until everything is verified or explicitly waived. Use when you want an agent or subagent to pick up a goal and drive it to a verified close across one of this repo's 18 domains ('run this goal through the engineering harness', 'set up an agentic loop for marketing work', 'make the finance domain self-verifying'). NOT for authoring Claude Code Workflow-tool .js scripts (workflow-builder), N-agent tournaments on one task (agenthub), single-file metric optimization (autoresearch-agent), or discovering published loop recipes (loop-library).

Manifests1

engineering/agent-harness/.claude-plugin/plugin.json

{
  "name": "agent-harness",
  "description": "Turn any domain folder of skills into a bounded agentic loop: a manifest builder inventories a domain's skills/tools/checks, a goal compiler turns a goal into a verifiable task plan (refusing vague goals with forcing questions), and a JSON-backed loop controller drives execute->verify->close with retry caps, controller-run verification (no verification theater), human escalation on exhausted budgets, and a close gate that refuses while any task is unverified. Ships 3 stdlib Python tools, 18 committed per-domain harness manifests + JSON schema, 3 references citing the 2024-2026 agent-harness canon, harness-runner agent + /cs:harness command. Use when an agent should pick up a goal and drive it to a verified close across a domain.",
  "version": "1.0.0",
  "author": {
    "name": "Alireza Rezvani",
    "url": "https://alirezarezvani.com"
  },
  "homepage": "https://github.com/alirezarezvani/claude-skills/tree/main/engineering/agent-harness",
  "repository": "https://github.com/alirezarezvani/claude-skills",
  "license": "MIT",
  "skills": [
    "./skills/agent-harness"
  ]
}