Skip to content
Back to skills

Create Hook

ASecurity

Scaffolds a new event-driven hook in a plugin. NOT for creating skills (use `create-skill`) and NOT for GitHub Actions agentic workflows (use `create-agentic-workflow`).

  • 7 stars
  • 0 votes
  • 0 copies
  • 2 views
  • Added September 2, 2026
ai-agentspythonbashtestinggitci/cd

Security analysis

A100/100

Pro scans all 20 files and shows the line behind each finding

Scanned October 3, 2026

npx -y skills add richfrem/agent-plugins-skills --skill create-hook --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Create Hook?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Create Hook
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/richfrem-create-hook-agent-plugins-skills/badge)](https://www.skillsdirectory.com/skills/richfrem-create-hook-agent-plugins-skills)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: create-hook
plugin: agent-scaffolders
description: >
  Scaffolds a new event-driven hook in a plugin. NOT for creating skills (use `create-skill`) and NOT for GitHub Actions agentic workflows (use `create-agentic-workflow`).
argument-hint: "[event-type or use case]"
allowed-tools: Bash, Read, Write
---

# Create Hook (create-hook)

Scaffolds event-driven lifecycle hooks (e.g. `PreToolUse`, `PostToolUse`, `Stop`, `PermissionRequest`) in plugin configuration or skill frontmatter.

## Contents
- [Critical Constraints](#critical-constraints)
- [Quick start](#quick-start)
- [Workflow](#workflow)
- [Verification](#verification)
- [References](#references)

## Critical Constraints
- **Event Scope**: Only for lifecycle hooks. For standalone skills, use `create-skill`. For CI/CD or agentic workflows, use `create-github-action` or `create-agentic-workflow`.
- **Cross-Platform Commands**: Hook commands must support macOS/Linux and Windows via `python3 ... || python ...` syntax with `${CLAUDE_PLUGIN_ROOT}` path anchors.
- **Project Context Guards**: Hook scripts must verify repository context on entry (e.g. check `.agent/` or `context/`) and exit silently (return code 0) if uninitialized.
- **Minimal Latency**: Keep synchronous hook handlers lean to prevent blocking the agent execution loop.

## Quick start

```bash
python3 plugins/agent-scaffolders/scripts/scaffold.py \
  --type hook \
  --name check-command \
  --path plugins/<plugin>/hooks \
  --event PreToolUse \
  --action command
```

## Workflow

1. **Phase 1: Event & Scope Selection**: Determine lifecycle trigger event (`PreToolUse`, `PostToolUse`, `Stop`), placement scope (global `hooks.json` vs skill frontmatter), and action type (`command`, `prompt`, `agent`).
2. **Phase 2: Hook Configuration**: Draft configuration entry with event identifier, target tool matcher pattern, and action parameters.
3. **Phase 3: Script Implementation**: For command hooks, author script with cross-platform fallback, silent project guards, and deterministic exit codes.
4. **Phase 4: Linting & Testing**: Execute `hook_linter.py` on created handler scripts and verify schema validity.

## Verification

```bash
# Lint the hook handler script
python3 plugins/agent-scaffolders/scripts/hook_linter.py plugins/<plugin>/hooks/<script>.py

# Audit skill compliance
python3 plugins/agent-scaffolders/scripts/audit_skill.py plugins/agent-scaffolders/skills/create-hook --mode source
```

## References
- [fallback-tree.md](references/fallback-tree.md) - Fallback tree for scaffolding failures.
- [references/patterns.md](references/patterns.md) - Common event-driven hook patterns.
- [references/advanced.md](references/advanced.md) - Advanced handler types and lifecycle nuances.
- [acceptance-criteria.md](references/acceptance-criteria.md) - Hook validation and acceptance criteria.

Files in this skill

  • SKILL.md2.5 KB
  • acceptance-criteria.md395 B
  • evals/evals.json876 B
  • evals/results.tsv417 B
  • fallback-tree.md1.4 KB
  • references/acceptance-criteria.md42 B
  • references/advanced.md31 B
  • references/fallback-tree.md36 B
  • references/hitl-interaction-design.md46 B
  • references/migration.md32 B
  • references/pattern-decision-matrix.md46 B
  • references/patterns.md31 B
  • references/patterns/action-forcing-output-with-deadline-attribution.md82 B
  • references/patterns/adversarial-objectivity-constraint.md69 B
  • references/patterns/anti-pattern-vaccination.md59 B
  • references/patterns/anti-symptom-triage.md54 B
  • references/patterns/artifact-embedded-execution-audit-trail.md74 B
  • references/patterns/artifact-generation-xss-compliance-gate.md74 B
  • references/patterns/artifact-lifecycle.md53 B
  • references/patterns/artifact-state-interrogative-routing.md71 B

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.