PostToolUse Hook - Claude Code

PostToolUse runs after a tool call completes successfully. Use it to provide feedback, run side effects, or kick off follow-up actions.

What it does

The hook receives the tool name, arguments, and result. It can log the call, inject a follow-up instruction into the conversation, run a linter after every edit, or push a notification. Unlike PreToolUse, it can't prevent the call - it reacts to what already happened.

When to use it

• Running a formatter or linter after every file edit.
• Auto-staging files in git after Claude writes them.
• Posting a Slack notification when deploys happen.
• Auditing tool outcomes to an observability pipeline.

Gotchas

• The hook runs on every success, which can be many times per turn. Stay fast.
• Post-hooks can't roll back the tool call. If something was dangerous, catch it in PreToolUse.
• Injecting too much context via the hook inflates the next turn's tokens.

Official docs: https://code.claude.com/docs/en/hooks.md#posttooluse