Guides
Written against the current Claude Code documentation and verified in real sessions. Each guide is updated when Claude Code changes.
- Claude Code hooks: the practical guide (2026)Every hook event, what JSON your script receives, how to block a tool call with exit codes or a JSON decision, matchers, hook types, and a copy-paste guardrail — with the mistakes that bite.
- Claude Code plugin marketplaces: install, private repos, and updatesHow marketplaces work, the marketplace.json format, installing from GitHub, using a private repository as a paid or team-only marketplace, version pinning, and how updates propagate.
- Keeping secrets out of Claude Code: .env files, keys and transcriptsHow credentials leak through an AI coding session (reading .env, writing keys into code, dumping env), what the transcript retains, and a layered fix using Read/Edit/Bash hooks and a post-write scanner.
- Making Claude Code actually run the tests before it says doneWhy models declare victory without running tests, what CLAUDE.md can and cannot fix, and a Stop hook pattern that tracks edits and test runs to gate the end of a turn.
- How to stop Claude Code from running rm -rf, force pushes and DROP TABLEThe destructive commands agents actually run by accident, why deny-lists in settings.json are not enough, and a hook-based guardrail that blocks them with a reason the model can act on.