分享一个 Claude Code 本地运行 ultraplan 的方法
- 内容介绍
- 文章标签
- 相关推荐
cc viewer 里能在本地直接运行原来只能在远端运行的 ultraplan
image1098×640 99.7 KB
看了下实现，结合泄漏的 2.1.88 的源码，其实就是一段提示词，使用 system-reminder 标签增强模型注意力
<system-reminder>
Produce an exceptionally thorough implementation plan using multi-agent exploration.
Instructions:
1. Use the Task tool to spawn parallel agents to explore different aspects of the codebase simultaneously:
- One agent to understand the relevant existing code and architecture
- One agent to find all files that will need modification
- One agent to identify potential risks, edge cases, and dependencies
2. Synthesize their findings into a detailed, step-by-step implementation plan.
3. Use the Task tool to spawn a critique agent to review the plan for missing steps, risks, and mitigations.
4. Incorporate the critique feedback, then call ExitPlanMode with your final plan.
Your final plan should include:
- A clear summary of the approach
- Ordered li
cc viewer 里能在本地直接运行原来只能在远端运行的 ultraplan
image1098×640 99.7 KB
看了下实现，结合泄漏的 2.1.88 的源码，其实就是一段提示词，使用 system-reminder 标签增强模型注意力
<system-reminder>
Produce an exceptionally thorough implementation plan using multi-agent exploration.
Instructions:
1. Use the Task tool to spawn parallel agents to explore different aspects of the codebase simultaneously:
- One agent to understand the relevant existing code and architecture
- One agent to find all files that will need modification
- One agent to identify potential risks, edge cases, and dependencies
2. Synthesize their findings into a detailed, step-by-step implementation plan.
3. Use the Task tool to spawn a critique agent to review the plan for missing steps, risks, and mitigations.
4. Incorporate the critique feedback, then call ExitPlanMode with your final plan.
Your final plan should include:
- A clear summary of the approach
- Ordered li