claude-code-book (SCUTBrothers)

A second book-length Chinese treatment of Claude Code's source ('Understanding Claude Code In Depth') with a compiled PDF and LaTeX sources. Focuses on turning the complex system into reusable engineering knowledge: source structure, runtime mechanics, permissions and extension points, security and context strategy.

View source on GitHub

Key takeaways

• 01

  Dedicated chapters on the permission model and extension points

• 02

  Treats security and context strategy as first-class harness concerns

• 03

  Complements the Orange Book with a different chapter decomposition

Flows built on this research

Harness Engineering

Hook a Permission Layer onto Dangerous Tools

Intercept dangerous tool calls with a hook layer: pattern rules, approval gates, and blocks that the model cannot talk its way past.

4 steps · 60-90 minutes

Harness Engineering

Design the Permission Approval UX

Design approval prompts users actually read: diffs, risk framing, scoped grants, and pacing that prevents approval fatigue.

4 steps · 60-90 minutes

Harness Engineering

Sandbox Untrusted Code Execution

Contain what your agent runs: isolated execution environments with resource limits, network policy, and workspace mounting done right.

4 steps · 120-180 minutes