Agent Harness

Agent Harness

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 o

Optimized workflow

This edition turns the source methodology into a repeatable agent workflow with explicit inputs, checkpoints and deliverables.

Quality standard

• Confirm scope and missing inputs before execution
• Ground decisions in available evidence and preserve source constraints
• Return an actionable result with assumptions, risks and next steps

Agent compatibility

The same core method is packaged for Claude, Codex, GPT, Gemini, Cursor and OpenCode.