AI Coding Agent Hooks

A hook is a shell script your AI coding agent runs automatically at a defined event — before a tool call, after a file edit, before a shell command executes. Used well, hooks enforce the policy you can't rely on a prompt alone to guarantee: block a secret before it's committed, log every tool call for an audit trail, or require a second check before a production command runs. Every hook below is real, copy-paste code — not a concept.

100 hooks · Written for Claude Code's documented hook contract

New to agent hooks? Read the security risks first →

5 results Clear filters →

🌳 Worktree & Git Safety

5 hooks

Isolated worktrees are supposed to make parallel agent work safer — these close the gaps around creating and tearing them down.

Block Worktree Removal With Uncommitted or Unpushed Changes

Blocks removing a worktree if it has uncommitted changes or commits not yet pushed anywhere.

WorktreeRemove · Claude Code

Block Worktree Creation From a Detached HEAD State

Blocks creating a worktree whose source is a detached HEAD rather than a named branch.

WorktreeCreate · Claude Code

Enforce a Mandatory Ticket-ID Prefix on Worktree Names

Blocks worktree creation unless the requested name starts with a recognized ticket-ID pattern.

WorktreeCreate · Claude Code

Log Every Worktree Created, With Parent Branch and Requester

A logging-only companion hook that records every worktree creation without blocking any of them.

WorktreeCreate · Claude Code

Require a Clean Working Tree Before Creating a Worktree

Blocks creating a new worktree if the parent repo's working tree has uncommitted changes.

WorktreeCreate · Claude Code

Need a hook that isn’t here?

Tell us what you want enforced automatically and we’ll build it — free and public.

Request a hook →

    FEEDBACK
  