Skills and hooks that make Claude Code finish what it starts

说明与用途

agent-harness 的脚本和钩子确保代理仅在验证证据后完成任务，并要求所有者批准敏感操作。

问题

Agents often report completion without verifying that all required steps, such as URL checks, request completions, or automated next steps, have actually been performed.

结果

Agents now only declare completion after verified evidence, reducing the risk of unfinished deployments and ensuring owner-controlled actions for sensitive tasks.

工作流

• 1. Clone the agent-harness repository and run the installer. 2. Configure AGENTS.md and ~/.agents/skills to include the harness. 3. Define owner approvals in OWNER.md (e.g., money caps, account usage). 4. Issue a request to the agent. 5. The harness interprets the request and selects the appropriate agent role. 6. The agent performs the task and records each step in a ledger. 7. The done‑check.py hook verifies completion evidence. 8. If evidence is missing, the hook returns a NEEDS YOU message. 9. The agent continues or stops based on the verification result. 10. A scheduled cron or launchd job runs continue every few hours to keep the agent active. 11. Weekly reviews test harness changes against current tasks before adoption.

证据

The harness reads what you asked and picks how to act:

来源

Every row in a ledger is verified only with evidence: a test run, phone and desktop screenshots, or a URL check.

来源

NEEDS YOU (1 of 3): Stripe -> create the account -> unblocks checkout

来源