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.
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.
Makes Agents produce staff-engineer-quality code
"OpenHarness: Open Agent Harness with a Built-in Personal Agent--Ohmo!"
From idea to shipped code — a praxis of engineering for AI agents.
One brain, many harnesses. Portable .agent/ folder (memory + skills + protocols) that plugs into Claude Code, Cursor, Windsurf, OpenCode, OpenClaw, Hermes, or DIY Python — and keeps its knowledge when you switch.
No description.
1 capture since 2026-05-26
AI agent config detected
Key config paths
.claude
CLAUDE.md
.claude
.claude/.sd0x-install-state.json
.claude/sd0x-dev-flow-lessons.md
CLAUDE.md