其他技能
Optim Plans
Human-in-the-loop planning plugin for Claude and Codex: turn ideas into reviewed Markdown plans, record decisions, enforce explicit execution gates, and provide tested controller primitives for safer agent workflows.
Optim-Agent · 已有 AI 审核记录
安装与使用
运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。
npx skills add Optim-Agent/optim-plans技能说明
all you need is a planning loop and an execution loop
both are elegantly featured in optim-plans
plans stay reviewable
execution stays gated
agents stay pointed at the work that matters
optim-plans turns "build me something" into a reviewed Markdown plan, records the decisions that shaped it, and keeps execution behind explicit approval. It gives Claude and Codex the two loops agentic coding actually needs: a planning-refining loop that keeps asking until the plan is real, and an execution loop that builds, verifies, and records what happened.