Skill

create-hook

Design and scaffold an event-driven Claude Code hook

Install

Run in your terminal

npx claudepluginhub richfrem/agent-plugins-skills --plugin agent-scaffolders

Tool Access

This skill is limited to using the following tools:

BashReadWrite

Supporting Assets

View in Repository

acceptance-criteria.md

evals/evals.json

evals/results.tsv

fallback-tree.md

references/acceptance-criteria.md

references/advanced.md

references/fallback-tree.md

references/hitl-interaction-design.md

references/migration.md

references/pattern-decision-matrix.md

references/patterns.md

references/patterns/action-forcing-output-with-deadline-attribution.md

references/patterns/adversarial-objectivity-constraint.md

references/patterns/anti-pattern-vaccination.md

references/patterns/anti-symptom-triage.md

references/patterns/artifact-embedded-execution-audit-trail.md

references/patterns/artifact-generation-xss-compliance-gate.md

references/patterns/artifact-lifecycle.md

references/patterns/artifact-state-interrogative-routing.md

references/patterns/asynchronous-benchmark-metric-capture.md

Skill Content

Similar Skills

executing-plans

Executes pre-written implementation plans: critically reviews, follows bite-sized steps exactly, runs verifications, tracks progress with checkpoints, uses git worktrees, stops on blockers.

superpowers

134.2k

brainstorming

7 files

Guides idea refinement into designs: explores context, asks questions one-by-one, proposes approaches, presents sections for approval, writes/review specs before coding.

superpowers

134.2k

dispatching-parallel-agents

Dispatches parallel agents to independently tackle 2+ tasks like separate test failures or subsystems without shared state or dependencies.

superpowers

134.2k

Stats

Parent Repo Stars1

Parent Repo Forks1

Last CommitApr 5, 2026

Actions

View Source View Plugin View on GitHub View README

Steps

If $ARGUMENTS names an event or use case, use it to seed Phase 1 questions

Follow the create-hook phased workflow: select event, choose handler type (command / prompt / agent), design the matcher and logic, then write the hook entry

Validate with validate_hook_schema.py and test with test_hook.py

Report placement (global hooks.json vs skill-scoped frontmatter) and next steps

Edge Cases

If $ARGUMENTS is empty: begin with the event selection question in Phase 1

If the requested event is not in the 13 supported events: explain valid options

If the use case implies a skill-scoped hook (enforce invariant only during one skill): generate frontmatter syntax instead of a global hooks.json entry

If user wants to auto-approve subagent permissions: use PermissionRequest + prompt handler

Follow the create-hook skill workflow to design and generate a hook configuration.

Inputs

$ARGUMENTS — optional hook event type (e.g. PreToolUse, Stop, PermissionRequest) or a use-case description (e.g. "block dangerous bash commands"). Omit for discovery.

Steps

If $ARGUMENTS names an event or use case, use it to seed Phase 1 questions
Follow the create-hook phased workflow: select event, choose handler type (command / prompt / agent), design the matcher and logic, then write the hook entry
Validate with validate_hook_schema.py and test with test_hook.py
Report placement (global hooks.json vs skill-scoped frontmatter) and next steps

Output

hooks.json entry or SKILL.md frontmatter block with complete hook configuration (event, matcher, handler type, command/prompt body, output schema).

Edge Cases

If $ARGUMENTS is empty: begin with the event selection question in Phase 1
If the requested event is not in the 13 supported events: explain valid options
If the use case implies a skill-scoped hook (enforce invariant only during one skill): generate frontmatter syntax instead of a global hooks.json entry
If user wants to auto-approve subagent permissions: use PermissionRequest + prompt handler