agent-rein

Operate and extend agent-rein, the AutoHarness post-training pipeline that RL-trains a small code model (via SkyRL GRPO on Google Cloud) to write browser action-verifier harnesses, measured by a before/after search-budget trace. Use when working in this repo on the w8-biayn CLI, the autoharness package (Harness interface, Thompson-sampling search, rewards, Daytona sandbox), SkyPilot/GCP launches, the harness-legality benchmark, the trace-shrinkage experiment, or the SkyRL/vLLM training config. Trigger terms include run the experiment, launch on GCP, trace shrinkage, steps_to_gold, harness reward, w8-biayn, autoharness, GRPO, SkyRL, Daytona sandbox, and gold-threshold.

Create, update, audit, install, and use portable Agent Skills/Claude Skills with SKILL.md folders for Claude Code, Gemini CLI, Codex, and compatible AI agents. Use when the user asks about skills, skill discovery paths, cross-tool symlinks, frontmatter, bundled scripts/references/assets, progressive disclosure, or making an AI agent understand a repeatable framework or workflow.