Anthropic发布Opus 5.5成本指南
Anthropic just published its 𝗳𝘂𝗹𝗹 𝗰𝗼𝘀𝘁 𝗴𝘂𝗶𝗱𝗲 for Opus 5.5. You can ask Opus 5.5…
提供了一套可直接复用的结构化Prompt，将官方文档转化为具体的代码审查任务，逻辑清晰且具备实操性。
Anthropic just published its 𝗳𝘂𝗹𝗹 𝗰𝗼𝘀𝘁 𝗴𝘂𝗶𝗱𝗲 for Opus 5.5. You can ask Opus 5.5 to use it to review your Claude Code setup.
Anthropic 刚刚发布了 Opus 5.5 的完整成本指南。你可以让 Opus 5.5 使用它来审查你的 Claude Code 设置。
At the same effort level, Opus 5.5 thinks more per turn than Opus 5, most of all at xhigh and max. Thinking is billed as output, and an output token costs 𝟭𝟬𝟬 𝘁𝗶𝗺𝗲𝘀 𝗮 𝗰𝗮𝗰𝗵𝗲 𝗿𝗲𝗮𝗱. So don't carry over the level you set for Opus 5. Start at medium, and save xhigh and max for work where you've measured a gain.
在相同的努力级别下，Opus 5.5 每轮思考的内容比 Opus 5 更多，尤其是在 xhigh 和 max 级别。思考被计为输出，而一个输出 token 的成本是缓存读取的 100 倍。因此，不要沿用你为 Opus 5 设置的级别。从 medium 开始，并将 xhigh 和 max 保留在你已衡量出收益的工作中。
Send this prompt to Opus 5.5 👇
将此提示发送给 Opus 5.5 👇
"Read this guide: https://claude.dev/blog/what-a-task-costs-on-opus-5-5/
"阅读此指南：https://claude.dev/blog/what-a-task-costs-on-opus-5-5/"
Then review my Claude Code setup against it: my user and project settings, the subagents in ~/.claude/agents and .claude/agents, CLAUDE.md, and the MCP servers I have connected. Find three kinds of problems: 1. A default effort that doesn't fit the work. Use the guide's ladder: low for mechanical edits, medium for well-scoped daily work, high when medium stalls, and xhigh or max only for work where a gain was measured. Flag a default of xhigh or max, or a level I picked for Opus 5. Then look at this project's code and recent commits and tell me which kinds of work here fit which level. 2. Subagents that only search, read logs or run tests but set no model, so they run on my main model. 3. Setup that makes every turn cost more: MCP servers I don't use, or a CLAUDE.md well over 200 lines.
然后根据该指南审查我的 Claude Code 设置：包括我的用户和项目设置、~/.claude/agents 和 .claude/agents 中的子代理、CLAUDE.md 以及我连接的所有 MCP 服务器。找出三类问题： 1. 不适合工作的默认努力级别。使用指南中的阶梯标准：机械性编辑用 low，范围明确的日常工作用 medium，medium 停滞时用 high，仅对已衡量出收益的工作使用 xhigh 或 max。标记 xhigh 或 max 的默认值，或我为 Opus 5 选择的级别。然后查看此项目的代码和最近的提交，告诉我这里哪些类型的工作适合哪个级别。 2. 仅进行搜索、读取日志或运行测试但未设置模型的子代理，导致它们在我的主模型上运行。 3. 使每轮成本增加的设置：我不使用的 MCP 服务器，或超过 200 行的 CLAUDE.md。
For each issue, quote the setting or line, explain what it costs, and suggest the smallest change. Also tell me which three things to check in /usage at the end of a task.
对于每个问题，引用相应的设置或行，解释其成本，并建议最小的更改。同时告诉我任务结束后在 /usage 中应检查哪三件事。
Show me the recommendations first. Don't change anything yet."
先展示推荐建议。暂时不要做任何更改。
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