Claude Code 本地全栈配置：Jev 承担微决策

the0xbt @the0xbt原推发布于 2026.10.20

在 X 上打开原推

It is becoming f*cking dangerous. Anthropic documented every piece of this separately and nobody noticed what they add up to. 1. Create a folder on your PC. This is the only world your agent will ever see. 2. Launch Claude Code inside it and drop a CLAUDE.md in the root with your rules. It loads into every session, you never paste context again. 3. Create a MEMORY folder and add one rule to CLAUDE.md: write every durable fact there, read it before planning anything. 4. Create .claude/agents/ and define three read-only Haiku 5.5 subagents. They explore the files, your main model never burns context on the search. 5. Give it a real browser: claude mcp add playwright -- npx -y @playwright/mcp@latest 6. Connect Gmail, Calendar and Drive at http://claude.ai/customize/connectors. They load into the CLI automatically on the same account. 7. Wrap the whole chain in .claude/skills/<name>/SKILL.md so the entire thing runs as one command: /<name> The whole setup takes around 20 minutes. Now the part nobody wires up. Every one of those steps has the same slow spot: a tiny fork that does not need a thinker. Which file. Which tool. Retry or stop. Keep this chunk or drop it. That is where Jev fits. It cannot write a word. It returns the choice with a probability in 70 to 500 milliseconds, at $0.042 per million input tokens, output free. Thousands of decisions for the cost of one LLM call. > Let Claude think. > Let Jev decide what deserves Claude. > Let code do the actual work. What you end up with: the full Anthropic stack on your own machine -> persistent memory, a swarm that explores in parallel, a real browser, your mail and drive, and Jev making the thousands of tiny calls in between. The step-by-step setup is in the article below. Save this before your next session ↓

这条是引用着另一条写的：x.com/slash1sol/status/2112227853811044574