Building with agents 0/15

Lesson 5 of 15

Inside the harness: context, tools and permissions

Instruction files, compaction, subagents, hooks, permission modes and the sandbox, and which of them the model is free to ignore.

2,077 words · 10 min read Ultra Premium

In this lesson

  1. Instructions the model reads and rules the harness enforces
  2. Instruction files: CLAUDE.md and AGENTS.md
  3. Compaction, clearing and loading on demand
  4. Subagents: work in a separate context window
  5. Hooks: rules the harness runs every time
  6. Permission modes, rules and the sandbox

Ultra Premium

Unlock this lesson

Ultra Premium opens the 6 premium lessons in Building with agents, along with the rest of WhiteBox's premium lessons and problems.

Not ready yet? Read the free lesson: What a coding agent actually is