sd0xdev/sd0x-harness

The verification harness that Claude Code should have shipped with

Steers Cursor and Claude Code agents with gates → follow-up → handoff → policy.

Write-time code quality enforcement system for Claude Code. Every file edit triggers automated formatting and linting through fast Rust-based linters and dedicated Claude instances that intelligently fix remaining violations

Professional context and harness engineering for Claude Code and OpenAI Codex. Build production-grade software with spec-driven development, TDD, persistent memory, quality gates, code intelligence, human oversight, and end-to-end verification.

Make Claude Code work like a disciplined engineer: OODA, multi-party adversarial review, tiered model routing, fail-then-pass — token-efficient by design (route heavy work to smaller models, isolate sub-agent context). Distilled from Fable to reinforce the Opus harness.

The harness for your harness. Local hooks, taste enforcement, and developer observability for AI coding agents (Claude Code, Codex, Cursor, Copilot CLI).

Enforced QA for Claude Code, Codex and Copilot. Draw the graph: code review, your own reviewers and test agents, any model per node. Slop goes back to repair, and the agent that wrote the code can't skip it.

🪝 Claude Code hooks + an installable plugin marketplace: safety, cost, observability, productivity.

Guard skills for coding agents, quality gates that catch AI-generated failure modes in code, tests, and docs