Harness-engineering harness-execution

name: harness-execution version: "1.0.0" description: Execute a planned set of tasks with harness validation and state tracking stability: static cognitive_mode: meticulous-implementer triggers:

• manual
• on_new_feature
• on_bug_fix platforms:
• claude-code
• gemini-cli
• cursor
• codex tools:
• Bash
• Read
• Write
• Edit
• Glob
• Grep
• emit_interaction cli: command: harness skill run harness-execution args:
  • name: path description: Project root path required: false
  • name: plan-path description: Path to approved plan (from planning output or orchestrator) required: false
  • name: session-slug description: Session slug for scoped state/handoff (passed by autopilot) required: false
  • name: fast description: Minimal rigor — skip scratchpad, checkpoint commits only required: false
  • name: thorough description: Maximum rigor — verbose scratchpad for all research required: false mcp: tool: run_skill input: skill: harness-execution path: string type: rigid tier: 1 phases:
• name: prepare description: Load state and verify prerequisites required: true
• name: execute description: Implement planned tasks required: true
• name: verify description: Validate each completed task required: true
• name: persist description: Save progress to state files required: true state: persistent: true files:
  • .harness/state.json
  • .harness/learnings.md depends_on:
• harness-verification