Keeps a coding agent on track through a repo-native harness: you set the goal and checkpoints, the agent explores and implements, and the work's specs, context maps and validation evidence are saved so a new chat can pick up where it left off.
@huisezhiyinGenerate, update, or drift-check agent-facing CodeMaps as progressive code terrain indexes for projects, features, capabilities,…
@huisezhiyinPrepare safe, compact new-chat handoffs when a user wants a fresh chat, resume pack, context reset, recovery, or agent handoff.…
@huisezhiyin将 SDD-RIPER 方法论落地为严格可执行流程的重型 Harness 技能。用于辅助用户澄清最终目标、生成 codemap/context、拆分最小混沌单元、维护完整 spec、执行 RIPER 阶段门禁、阻塞高风险动作和沉淀可 new chat…
@huisezhiyin面向 GPT-5.4 等强模型和熟练用户的轻量 AI Agent Harness / checkpoint-driven coding skill。默认用户已经把任务切到基本可执行的最小混沌单元；模型自行分解、探索与推进，人类通过最终目标、最小…
@huisezhiyinIs this you? Claim your profilePut a plugin at the top of Plugins, from $9
