hookify

Hookify — Create Hooks from Unwanted Behaviors

FIRST: Load the hookify-plus:writing-rules skill using the Skill tool to understand rule file format and syntax.

Create hook rules to prevent problematic behaviors by analyzing the conversation or acting on explicit user instructions.

Step 1: Gather Behavior Information

If $ARGUMENTS is provided:

• Parse the user's specific instructions from $ARGUMENTS.
• Also scan recent conversation (last 10-15 user messages) for additional context and examples of the behavior occurring.

If $ARGUMENTS is empty:

• Launch the hookify-plus:conversation-analyzer agent via the Agent tool to find problematic behaviors. The agent does not see this conversation - include the relevant user messages and tool calls, or the transcript path, in its prompt.

Step 2: Present Findings to the User

After gathering behaviors (from arguments or the agent), present findings using AskUserQuestion.

Question 1 — Which behaviors to hookify:

• Header: "Create Rules"
• multiSelect: true
• Options: List each detected behavior (max 4)
  • Label: Short description (e.g., "Block rm -rf")
  • Description: Why it is problematic

Question 2 — Action for each selected behavior:

• "Should this block the operation or just warn?"
• Options:
  • "Just warn" (action: warn — shows message but allows)
  • "Block operation" (action: block — prevents execution)

Question 3 — Pattern refinement:

• "What patterns should trigger this rule?"
• Show detected patterns and allow the user to refine or add more.

Step 3: Generate Rule Files

For each confirmed behavior, create a .claude/hookify-plus/{rule-name}.md file.

Rule naming convention:

• Use kebab-case.
• Be descriptive: block-dangerous-rm, warn-console-log, require-tests-before-stop.
• Start with an action verb: block, warn, prevent, require.

Basic rule format:

---
name: {rule-name}
enabled: true
event: {bash|file|stop|prompt|all}
pattern: {regex pattern}
action: {warn|block}
---

{Message to show Claude when rule triggers}