hjemmesidekongen/agent-reviewer
plugins/kronen/skills/agent-reviewer/SKILL.md
Review and validate Claude Code agents for frontmatter correctness, description quality, system prompt structure, tool scope appropriateness, and model tier justification. Use when reviewing agents after creation, auditing existing agents for compliance, validating agent changes before committing, checking triggering examples, or auditing all agents in a plugin for consistency.
tools
Updated Apr 5, 2026
$ install --global
skillsauthnpx skillsauth add hjemmesidekongen/ai agent-reviewerInstall 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-reviewer
- description:
- >
- user_invocable:
- false
- interactive:
- false
- writes:
- []
- type:
- data_validation
- - name:
- no_modifications
- verify:
- Reviewed files were not modified during review
- fail_action:
- Revert any changes — reviewers are read-only
- model_tier:
- senior
- origin:
- kronen
- inspired_by:
- validate-agent.sh (claude-code-templates, everything-claude-code) + skill-reviewer pattern
- ported_date:
- 2026-03-10
- iteration:
- 1
- changes:
- New skill mirroring skill-reviewer pattern for agent definition files. Review methodology derived from validate-agent.sh external references and the existing agent-reviewer agent's 5-dimension framework.
Agent Reviewer
Reviews Claude Code agent definition files for structure, quality, and correctness.
When to trigger
- Reviewing an agent after creation or modification
- Auditing all agents in a plugin for consistency
- Validating agent changes before committing
- Checking triggering examples and description quality
- Verifying ecosystem.json registration
Review methodology
| Step | Focus | |------|-------| | 1. Location | Correct directory, naming conventions | | 2. Frontmatter | Required fields, format, value constraints | | 3. Description | Trigger quality, examples, specificity | | 4. System prompt | Role, structure, output format, tone | | 5. Tool scope | Least privilege, read-only vs write alignment | | 6. Model tier | Tier matches agent complexity | | 7. Issue identification | Severity classification | | 8. Recommendations | Actionable improvement items |
Read-only — never modify reviewed files. Produce a YAML verdict only.
Process
See references/process.md for the full review methodology: 8-step process,
spec compliance checks, quality review dimensions, verdict format, and common findings.
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