Topic
A Claude Code feature letting scripts intercept lifecycle events like PreToolUse or PreCompact to log, gate, or control agent tool calls.
Prompting an LLM to self-audit works some fraction of the time, so one developer moved the check into a Stop hook that parses the session transcript and refuses the end of a turn when the audit keywords are missing.
Reality
The hooks documentation says a matcher on an event without matcher support is ignored rather than rejected. A Bash-scoped guard on UserPromptSubmit therefore fires on every prompt, and nothing at startup or in --debug says so.
Reality
Allow and deny globs in settings.json cannot separate git status from git push --force, so the real enforcement moves into a PreToolUse hook that reads the command text, exits 2, and tells the model why it was refused.
Reality
Command substitution inside the echo reset the exit status to zero, so a Stop hook reported success for a full day while DM replies sat at zero on two platforms. The test that catches this takes a minute to write.
Reality
A Claude Code Stop hook appended 2,340 session rows that all said the session cost nothing, because it read fields the payload never carried. Flat-fee billing left no invoice to argue with it.
Reality
One operator's fix for 2 a.m. MCP outages is a hook that writes the verdict to a file, because compaction throws away whatever the model learned about a dead server.
Reality
A stuck rebase made force-pushing to main the locally correct move. Reviewing agent output scales with what the agent writes; a short list of things it must never do does not.
Reality
A developer leaked live keys into agent transcripts three times before replacing a polite memory note with a hook that denies the read outright.
Reality