Awesome list for AI agent harness engineering: tools, patterns, evals, memory, MCP, permissions, observability, and orchestration.
Python agent-harnessagent-memoryagent-orchestrationai-agent-harnessai-agentsawesome-listcontext-engineeringharness-engineeringmcp
Add shadcn-ui/lint to Verification & CI Integration
ai-boost396366fa0ddf
diff --git a/README.md b/README.mdindex c97f7b0..9936110 100644--- a/README.md+++ b/README.md@@ -349,6 +349,7 @@ Harness components organized by the problem they solve, not by vendor.- [sentrux](https://github.com/sentrux/sentrux) — Real-time architectural sensor that closes the feedback loop for coding agents: scans codebases, scores structural health, and surfaces degradation via MCP so agents can self-correct before entropy compounds. The `gate --save` / `gate` pair makes architectural regression detection CI-friendly — filling the verification gap between linters (style) and tests (behavior) for code produced by autonomous harnesses. - [Driving the Agent Quality Flywheel from Your Coding Agent](https://developers.googleblog.com/en/driving-the-agent-quality-flywheel-from-your-coding-agent/) — Google's June 2026 account of automating the eval-optimize loop for coding agents: independent AutoRaters grade agent outputs so the optimizer cannot game its own metrics, and custom rubrics isolate specific behaviors like stale-message echoing that blended scores miss. Shows how to close the verification loop continuously against both synthetic dev scenarios and production traces.- [mcp-test-harness](https://github.com/vaquarkhan/mcp-test-harness) — Pytest-style testing framework for MCP servers with protocol-aware assertions, snapshot tests, and CI-ready reports across stdio/SSE/HTTP transports. Fills the gap between shipping an MCP server and trusting it in production by turning tool/schema regressions into ordinary test failures. +- [shadcn-ui/lint](https://github.com/shadcn-ui/lint) — September 2026 agent-first linter for Tailwind design systems: you encode design-system contracts as programmable lint rules, and the errors carry your components' sizes, variants, and theme file paths so agents self-correct in one round instead of guessing. Validated across 150+ task runs (published evals: nearly all tasks reach zero violations in a single correction round, and lint feedback costs 10–48% less than prompt-level rules alone). The clearest recent demonstration that *verifier error messages are harness output too* — deterministic checks only close the loop when they tell the agent what to do instead. Ships for both ESLint and Oxlint, shadcn/ui not required. ### Observability & Tracing