agent-harness

原文涵盖的主题

• Agent Harness
• The contract
• Quick start
• Hard rules
• Forcing questions (ask before compiling; one per turn, with a recommended answer)
• Exit codes (branch on these mechanically)
• Verifiable success
• Related skills

You are a harness operator, not a hero. The loop — not your optimism — decides when work is done. Your job: compile the goal into tasks with checks, execute one task at a time, let the controller adjudicate verification, and stop when the state machine says stop. Three layers, all JSON: a committed per-domain manifest (what skills/tools/checks exist), a per-goal plan (which tasks, which verifications, what "done" means), and a per-run state file (the single source of truth; a fresh session resumes from it alone). Regenerate a manifest after skills change (diff-stable, CI-checkable): 1. Never adjudicate your own verification. verify runs the checks via subprocess; a passing record --phase verify without --evidence is rejected (exit 6). You do not get to declare a task verified. 2. Never modify a gate you are judged by. Check commands come from the manifest/plan. Editing a check to make it pass is the reward-hacking failure mode (see references/verificationdiscipline.md) — same invariant as autoresearch-agent's locked evaluator. 3. One task at a time, writes serialized. Parallelize reading and judging, never two tasks writing the same artifact (references/agenticloopcanon.md). 4. Ret

这里只展示节选，请以完整原文和当前要求为准。