No description.
The harness layer for Claude Code — a reference implementation of harness engineering with hook-enforced dual review, state-machine gates that survive context compaction, and fail-closed safety where it counts. Quality gates that AI can't skip.
团队开发工作流Skills(Team Dev Workflow Skills)
Turn ad-hoc Claude Code / Codex / Cursor sessions into a repeatable loop — research → plan → wave-execute → close. Parallel sub-agents, inter-wave quality gates, dual GitHub+GitLab integration, F2 Memory + Persona-Panel + gsd-Pattern Adoption. 37 skills · 18 commands · 13 agents · 7360 tests.
Codex plugin: enforce formal, textbook-grade written register across all agent output
Agent orchestration harness for Claude Code. Four-tier routing (/do), campaign persistence across sessions, parallel agents in isolated worktrees, discovery relay between waves, lifecycle hooks, circuit breaker, and 6 production-quality skills. From solo developer to institutional scale.
From idea to shipped code — a praxis of engineering for AI agents.
1 capture since 2026-05-29
AI agent config detected
Key config paths
CLAUDE.md
docs/codex.md
evals/results/stress-3-2026-05-21/CLAUDE.md