hjemmesidekongen/agent-creator
plugins/kronen/skills/agent-creator/SKILL.md
Create autonomous Claude Code agents with correct frontmatter, triggering examples, system prompts, and tool restrictions. Use when adding agents to any plugin, defining agent behavior, writing system prompts, configuring model tier and tool access, setting up auto-triggering descriptions, or choosing between agent vs command for a task.
tools
Updated Apr 5, 2026
$ install --global
skillsauthnpx skillsauth add hjemmesidekongen/ai agent-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 24, 2026, 8:37 PM1.6s1 file scanned
SKILL.md
- name:
- agent-creator
- description:
- >
- user_invocable:
- false
- interactive:
- false
- depends_on:
- []
- writes:
- []
- type:
- data_validation
- - name:
- tools_least_privilege
- verify:
- Tool list is minimal — only what the agent needs
- fail_action:
- Remove unnecessary tools, scope to actual requirements
- model_tier:
- senior
- origin:
- kronen
- inspired_by:
- https://skills.sh/anthropics/claude-plugins-official/agent-development
- ported_date:
- 2026-03-09
- iteration:
- 1
- changes:
- Adapted from Anthropic agent-development skill. Added our <=80 line pattern, references/process.md overflow, our agent directory conventions, tier system, checkpoint verification.
Agent Creator
Creates and validates Claude Code agents for any plugin in this workspace.
When to trigger
- Adding a new autonomous agent to a plugin
- Defining agent behavior, model tier, or tool access
- Setting up agent triggering examples and system prompts
- Organizing agents into plugin directory structure
Agent vs command — quick reference
| Dimension | Agent | Command |
|-----------|-------|---------|
| Invocation | Auto-triggered by matching user intent | Explicit /plugin:command |
| Autonomy | Runs independently, makes decisions | Single action, returns result |
| Scope | Multi-step workflows | Focused operations |
| Model | Configurable per agent | Inherits session model |
Default to commands for deterministic operations. Use agents for autonomous multi-step work.
Process
See references/process.md for the full specification: frontmatter fields, triggering
examples format, system prompt structure, model/color selection, tool restrictions,
directory layout, tier system, testing protocol, and pre-commit checklist.
Quality gate
After writing the agent file, run agent-reviewer against the new file. It checks the 5
dimensions: frontmatter validity, description quality, system prompt quality, tool scope
appropriateness, and model tier justification. Fix any CRITICAL findings before registering
the agent in ecosystem.json.
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