Harness-engineering harness-autopilot

name: harness-autopilot version: "1.0.0" description: Autonomous phase execution loop — chains planning, execution, verification, and review, pausing only at human decision points stability: static cognitive_mode: constructive-architect triggers:

• manual platforms:
• claude-code
• gemini-cli
• cursor
• codex tools:
• Bash
• Read
• Write
• Edit
• Glob
• Grep cli: command: harness skill run harness-autopilot args:
  • name: spec description: Path to approved spec document required: false
  • name: path description: Project root path required: false
  • name: review-plans description: Force human review of all plans (overrides auto-approve) required: false
  • name: fast description: Run with reduced rigor — skip skeleton approval, skip scratchpad, minimal verification required: false
  • name: thorough description: Run with maximum rigor — require skeleton approval, verbose scratchpad, full verification required: false mcp: tool: run_skill input: skill: harness-autopilot path: string type: rigid tier: 1 phases:
• name: init description: Load spec, identify phases, restore state if resuming required: true
• name: loop description: Execute state machine — assess, plan, execute, verify, review per phase required: true
• name: final_review description: Project-wide code review of cumulative changes before PR offer required: true
• name: complete description: Final summary and PR offering required: true state: persistent: true files:
  • .harness/sessions/*/autopilot-state.json
  • .harness/sessions/*/state.json
  • .harness/sessions/*/handoff.json
  • .harness/learnings.md
  • .harness/failures.md depends_on:
• harness-planning
• harness-execution
• harness-verification
• harness-code-review