hjemmesidekongen/hook-creator
plugins/kronen/skills/hook-creator/SKILL.md
Create, modify, or debug Claude Code hooks with correct event types, exit codes, JSON output formats, and shell best practices. Use when adding hooks to any plugin, fixing broken or silent hooks, blocking or allowing specific tools via PreToolUse, adding guards for SessionStart or Stop events, registering hooks in plugin.json, or converting hooks between types (command, prompt, HTTP, agent).
tools
Updated Apr 5, 2026
$ install --global
skillsauthnpx skillsauth add hjemmesidekongen/ai hook-creatorInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 5, 2026, 5:13 PM108.9s2 files scanned
SKILL.md
- name:
- hook-creator
- description:
- >
- user_invocable:
- false
- interactive:
- false
- depends_on:
- []
- writes:
- []
- type:
- data_validation
- - name:
- registered_in_plugin_json
- verify:
- Hook is registered in the target plugin's plugin.json
- fail_action:
- Add hook entry to plugin.json hooks section
- model_tier:
- senior
- origin:
- kronen
- inspired_by:
- https://docs.anthropic.com/en/docs/claude-code/hooks
- ported_date:
- 2026-03-09
- iteration:
- 2
- changes:
- v2: Added 9 events (18 total), HTTP and agent hook types, new handler fields (statusMessage, once, async), updated input fields, corrected tool_response naming and timeouts per official docs.
Hook Creator
Creates and validates Claude Code hooks for any plugin in this workspace.
When to trigger
- Creating a new hook for any event type
- Fixing a broken or misbehaving hook
- Converting between hook types (command, prompt, HTTP, agent)
- Adding hooks to plugin.json or skill/agent frontmatter
Hook types
| Type | Best for | Events supported | |------|----------|-----------------| | command | Deterministic checks, file I/O, logging | All events | | prompt | Context-aware LLM decisions | PreToolUse, Stop, SubagentStop, UserPromptSubmit | | http | External service integration, webhooks | All events | | agent | Multi-step autonomous tasks (50-turn limit) | All events |
Default to command hooks. Use prompt hooks only when the decision requires LLM reasoning. Use HTTP hooks for webhooks/external integrations. Use agent hooks for complex multi-step logic.
NEVER
- Create a hook without registering it in plugin.json
- Use prompt hooks for deterministic checks (use command hooks)
- Skip exit code testing — hooks fail silently on bad exit codes
- Hardcode file paths — use $HOOK_WORKING_DIR for portability
- Leave hooks unquoted when variables may contain spaces
Process
See references/process.md for the full specification: 18 event types, 4 hook types,
input/output schemas, exit codes, shell conventions, testing protocol, and registration.
Related Skills
hjemmesidekongen/brand-strategy
development
VerifiedTrustedCommunity
Creates a brand from scratch through market research and interactive sparring. Runs competitive research via Perplexity, then guides the user through positioning, audience, voice, values, and content pillars. Produces the full brand guideline set at .ai/brand/{name}/. Use when building a new brand, defining brand strategy for a product, or when /våbenskjold:create is invoked.
SKILL.mdUpdated Apr 5, 2026
hjemmesidekongen/brand-loader
testing
VerifiedTrustedCommunity
Loads brand guidelines from .ai/brand/{name}/ and makes them available to the current context. Progressive disclosure: L1 confirms brand exists, L2 loads summary, L3 loads specific files on demand. Use when a downstream skill or user needs brand context, or when /våbenskjold:apply is invoked.
SKILL.mdUpdated Apr 5, 2026
hjemmesidekongen/brand-evolve
documentation
VerifiedTrustedCommunity
Guided reinvention of an existing brand guideline. Loads current brand from .ai/brand/{name}/, identifies what to keep vs change, and walks the user through targeted evolution. Preserves brand equity while updating positioning, voice, or values. Use when refreshing a brand or when /våbenskjold:evolve is invoked.
SKILL.mdUpdated Apr 5, 2026
hjemmesidekongen/brand-audit
development
VerifiedTrustedCommunity
Codifies an existing brand from materials, samples, and references. Analyzes provided content to extract voice patterns, values, and positioning. Produces the same guideline format as brand-strategy. Use when a brand already exists but isn't documented, or when /våbenskjold:audit is invoked.
SKILL.mdUpdated Apr 5, 2026