AI PROMPT · 122
Claude Code 多 Agent 配置提示词
请根据以下结构重建我的 Claude Code 配置： 1. 检查 ~/.claude/agents 和 .claude/agents 目录，查找已覆盖 explorer、worker 和 researcher 角色的子 Agent。仅为缺失的角色创建新的子 Agent。将每个子 Agent 设置为 model: opus, effort: medium。如果现有子 Agent 固定使用了其他模型，请列出但不要修改。 2. 在 ~/.claude/settings.json 中，将主会话的 effortLevel 设置为 high，并将 advisorModel 设置为 fable。 3. 检查是否有禁用顾问功能的设置：包括 CLAUDE_CODE_DISABLE_ADVISOR_TOOL、DISABLE_TELEMETRY、任何阻止获取功能标志的环境变量，以及会覆盖子 Agent effort 设置的 CLAUDE_CODE_EFFORT_LEVEL。报告发现的内容，暂时不要做任何更改。 4. 在 ~/.claude/CLAUDE.md 中添加一行说明：在制定大型计划前、错误重复出现时，以及在标记长时间任务完成之前，先咨询顾问。 请先以 diff 格式展示所有更改。在我确认之前不要应用任何修改。
VIDEO PREVIEW
视频预览
PROMPT
Rebuild my Claude Code setup around this tree: 1. Look in ~/.claude/agents and .claude/agents for subagents that already cover explorer, worker and researcher. Draft new ones only for roles that are missing. Set each to model: opus, effort: medium. If an existing subagent is pinned to a different model, list it, don't touch it. 2. Set the main session's effortLevel to high in ~/.claude/settings.json, and set advisorModel to fable. 3. Check for anything disabling the advisor: CLAUDE_CODE_DISABLE_ADVISOR_TOOL, DISABLE_TELEMETRY, any variable blocking feature-flag fetches, and CLAUDE_CODE_EFFORT_LEVEL, which overrides subagent effort. Report what you find. Change nothing yet. 4. Add one line to ~/.claude/CLAUDE.md: consult the advisor before a large plan, when an error repeats, and before marking a long task done. Show every change as a diff first. Don't touch anything until I say go.