stometaverse

Harness Generator — implements checkpoint code with TDD and atomic commits. Use when harness orchestrator needs code generation for a checkpoint.

Cybernetics-based multi-agent orchestration for complex tasks. Coordinates a Planner → Generator → Evaluator → Retro pipeline with clean-context sub-agents, per-checkpoint drift prevention, and persistent retro learning. Recommended workflow: Claude Code plans the spec (Session 1), Codex executes autonomously (Session 2), Gemini reviews as cross-model peer via `review-loop`. Use when: "harness this task", "use harness", "orchestrate this", "harness plan", "harness continue", "harness execute <task-id>", "harness <spec-name>", or when a task requires structured multi-agent coordination.

Harness Spec Evaluator — reviews spec.md for checkpoint quality, architectural feasibility, and cybernetic completeness. Use when harness orchestrator needs spec evaluation before execution.

Harness Retro — post-task retrospective analysis, error pattern detection, and CLAUDE.md rule proposals. Use when harness orchestrator needs task retrospective.

Cross-LLM iterative code review loop. Spawns a peer reviewer (Codex or Gemini CLI) to review code changes, then iterates until both agents agree on the final code state. Code gets modified during the loop — the final output is improved code + consensus report. Use when: "review loop", "peer review", "cross review", "review with codex", "review with gemini", "让 codex review", "交叉 review", "peer review 这段代码", "code review loop", "iterative review"

Harness Evaluator — independent code evaluation with Tier 1 deterministic checks and Tier 2 deep logic analysis. Use when harness orchestrator needs checkpoint evaluation.