From project-toolkit
Scans repository for golden principle violations (GP-001 to GP-008) with agent-readable remediation instructions. Use for compliance audits, PR preparation, garbage collection.
How this skill is triggered — by the user, by Claude, or both
Slash command
/project-toolkit:golden-principlesclaude-sonnet-4-6The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Scan the repository for violations of mechanically enforced golden principles.
Scan the repository for violations of mechanically enforced golden principles. Produces remediation instructions that agents can act on directly.
Inspired by OpenAI Harness Engineering:
"We started encoding what we call 'golden principles' directly into the repository and built a recurring cleanup process."
| Trigger Phrase | Operation |
|---|---|
scan golden principles | Full principle compliance scan |
check principle compliance | Scan with summary report |
golden principle violations | Scan and list violations |
run garbage collection | Deep scan with fix-up recommendations |
audit principles | Scan specific rules only |
Use this skill when:
Use taste-lints instead when:
Use quality-grades instead when:
python3 .claude/skills/golden-principles/scripts/scan_principles.py with target# Scan entire repository
python3 .claude/skills/golden-principles/scripts/scan_principles.py
# Scan specific directory
python3 .claude/skills/golden-principles/scripts/scan_principles.py --directory .claude/skills/
# Run specific rules only
python3 .claude/skills/golden-principles/scripts/scan_principles.py --rules script-language,skill-frontmatter
# JSON output for tooling
python3 .claude/skills/golden-principles/scripts/scan_principles.py --format json
# Write results to file
python3 .claude/skills/golden-principles/scripts/scan_principles.py --output scan-results.json --format json
| Rule | Principle | What it checks |
|---|---|---|
script-language | GP-001 | No new .sh/.bash files |
skill-frontmatter | GP-003 | SKILL.md has required frontmatter fields |
agent-definition | GP-004 | Agent .md files have required sections |
yaml-logic | GP-005 | No inline logic in workflow YAML |
actions-pinned | GP-006 | GitHub Actions pinned to SHA |
GP-002, GP-007, GP-008 are enforced by existing tools (git hooks, taste-lints).
| Code | Meaning |
|---|---|
| 0 | No violations found |
| 1 | Script error (bad arguments, file not found) |
| 10 | Violations detected |
Add a comment in the file header to suppress a specific rule:
# golden-principle: ignore script-language
Valid rules: script-language, skill-frontmatter, agent-definition, yaml-logic, actions-pinned
After execution:
npx claudepluginhub rjmurillo/ai-agents --plugin project-toolkitScans repository for golden principle violations (GP-001–GP-008) with agent-readable remediation instructions. Use for compliance audits, PR preparation, or garbage collection scans.
Generates tailored Development Principles for CLAUDE.md by auto-detecting project structure, monorepo setup, tech stack including TypeScript, React, Python, Django, and user preferences via interactive questions.
Enforces CLAUDE.md guidelines and project conventions via inheritance hierarchy and directory walk-up algorithm. Audits repositories for systematic compliance including rule parsing and verification.