Guides
Read it. Then understand it.
How to understand, review and keep a record of code AI agents write: methods, evidence, team policy, and hook tutorials for Claude Code, Copilot and Codex.
Understanding AI-written code
- How to understand code your AI agent wroteA hunk-by-hunk method for reading code Claude Code, Copilot or Codex wrote: predict it, trace it, find the bug, say why. With the evidence for why it works.
- Comprehension debt: what it is and how to pay it downComprehension debt is code in your repository that nobody on the team understands. What the research says, including Anthropic's 2026 study, and how to measure and reduce it.
- An AI code policy for pull requests, with a check that reads itA CONTRIBUTING.md paragraph for AI-written code, the same rules as a committed policy, and a free GitHub check that reads a review record on every pull request.
- Tools that check you understand AI-written code, comparedQuiz extensions, pull request gates, Claude Code learning modes, AI review bots and attribution tools: what each checks, which ones block, and where TypeBack fits.
Agent hook tutorials
- Claude Code hooks: capture every edit with PostToolUseA working Claude Code PostToolUse hook that sends every Edit and Write to another program, plus the turn hooks, the payloads, and the gotchas we hit with claude -p.
- VS Code agent hooks: capture every Copilot agent editHow VS Code's agent hooks (preview) report Copilot agent mode edits, the file they live in, what the PostToolUse payload does and doesn't contain, and how to recover the changed hunks.
- Codex CLI hooks: capture apply_patch editsA Codex CLI hooks.json that captures every apply_patch edit and each turn's start and end, with the trust prompts, timeouts and payload quirks of codex-cli 0.154.