Claude Code 高效开发工作流：低努力构建与高努力验证
Thariq from Anthropic's Claude Code team just published his tests on effort: tur…
这篇内容详细拆解了 Claude Code 的具体配置步骤和 Prompt 结构，不仅解释了原理，还直接给出了可复制的代码和工作流设置方法，对开发者优化 AI 编程体验有直接的实操参考价值。
Thariq from Anthropic's Claude Code team just published his tests on effort: turning effort up mostly buys 𝗺𝗼𝗿𝗲 𝘃𝗲𝗿𝗶𝗳𝗶𝗰𝗮𝘁𝗶𝗼𝗻 𝗮𝗻𝗱 𝗲𝗱𝗴𝗲-𝗰𝗮𝘀𝗲 𝘁𝗲𝘀𝘁𝗶𝗻𝗴. You can turn his approach into 𝘁𝘄𝗼 𝘀𝘂𝗯𝗮𝗴𝗲𝗻𝘁𝘀 and have Claude Code follow it.
Anthropic 的 Claude Code 团队的 Thariq 刚刚发布了关于“努力程度（effort）”的测试结果：提高努力程度主要能买到更多的验证和边缘情况测试。你可以将他的方法转化为两个子代理，让 Claude Code 遵循它。
For new features, he works in four steps: → Have Claude ask you questions first and fill in what the spec is missing → Build it on low. It's fast, and you can step in anytime → Look it over, and if it needs changes, stay on low → Switch to high at the end to verify and test
对于新功能，他分四步工作： → 先让 Claude 向你提问，并补全规范中缺失的内容 → 以低努力程度构建。这很快，你可以随时介入 → 检查一遍，如果需要修改，保持低努力程度 → 最后切换到高努力程度进行验证和测试
If you want to try it, send this image and the prompt below to Claude Code 👇
如果你想尝试，请将这张图片和下面的提示词发送给 Claude Code 👇
"Set up the workflow in this image in my Claude Code:
"在我的 Claude Code 中设置此图片中的工作流程：
1. Create two subagents in ~/.claude/agents: - builder: writes the code. model: opus, effort: low. It implements the spec I've approved and stops when it's done. - verifier: checks the work. model: opus, effort: high. It runs the feature first to see what it actually does, then adds tests, focusing on edge cases. It reports problems to me and doesn't change the code itself.
1. 在 ~/.claude/agents 中创建两个子代理： - builder：编写代码。模型：opus，努力程度：低。它实现我已批准的规范，完成后停止。 - verifier：检查工作。模型：opus，努力程度：高。它首先运行该功能以查看其实际行为，然后添加测试，重点关注边缘情况。它将问题报告给我，且不自行更改代码。
2. Add a rule to ~/.claude/CLAUDE.md: when I ask for a new feature, first ask me what the spec is missing; after I confirm, hand it to builder; after I've reviewed the result, hand it to verifier.
2. 向 ~/.claude/CLAUDE.md 添加一条规则：当我请求新功能时，先问我规范中缺失了什么；在我确认后，将其交给 builder；在我审查结果后，将其交给 verifier。
3. Check whether the environment variable CLAUDE_CODE_EFFORT_LEVEL is set. If it is, the effort settings on both subagents won't take effect. Just tell me; don't change it.
3. 检查环境变量 CLAUDE_CODE_EFFORT_LEVEL 是否已设置。如果已设置，两个子代理上的努力程度设置将不会生效。只需告诉我；不要更改它。
Show me the contents of the files you'll create or change, then explain the whole workflow in words a 10-year-old could follow. Don't write anything until I confirm."
展示你将创建或更改的文件内容，然后用一个 10 岁孩子也能理解的方式解释整个工作流程。在我确认之前，不要写任何东西。"
更进一步：量化金融体系
看懂新闻只是起点——沿量化金融路径，把它变成能交付的工程能力