Use when adding or fixing Formax tests (especially Ink UI tests) and you need deterministic synchronization in test interactions.
中文简介正在准备中。当前显示原文说明。
查看安装方法安装前可以查看交给 AI 代理的指令内容。
Wait for target state before next key (example: wait ❯ 3. before typing feedback).
Assert final behavior, not transient cursor frames (example: assert feedback aXb, not a▏b).
In multi-step input flows, wait for idle state between steps (example: placeholder/queue-hint settled).
Extract repeated sync steps into local helpers (example: selectFeedbackRow, queueMessageWhileLoading).
还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问，或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Use when a Formax repository task is non-trivial and you should analyze goals, non-goals, boundaries, data/type/interface impact, contract impact, test strategy, and whether an xhigh subagent is actually needed before writing a todo or code.
中文简介正在准备中。当前显示原文说明。
Use when adding or changing any Approval prompt/presenter.
中文简介正在准备中。当前显示原文说明。
Use when implementing or extending /config (storage, prompt injection, request params, UI-only toggles) with tests and strict UI parity.
中文简介正在准备中。当前显示原文说明。
Use when working on Formax code changes and you need a disciplined dev loop: keep a single mainline task, avoid scope drift, run only targeted tests (no coverage), avoid partial staging (MM), run mandatory review before commit, include an incremental optimization check, and keep commits small and reviewable.
中文简介正在准备中。当前显示原文说明。
Use when implementing/debugging Ctrl+O Expanded Transcript (second view) and thinking persistence in the REPL.
中文简介正在准备中。当前显示原文说明。
Use when implementing or debugging Formax permissions/policy/approval behavior and UI (allow/ask/deny rules, workspace boundaries, approval prompts, and /permissions overlay parity with Claude Code).
中文简介正在准备中。当前显示原文说明。