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."

Triggers

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

When to Use

Use this skill when:

• Preparing a PR for submission (catch violations early)
• Running periodic garbage collection scans
• Auditing a domain or directory for compliance
• Adding new files to the repository

Use taste-lints instead when:

• Checking code-level invariants only (file size, naming, complexity)
• Running pre-commit checks on staged files

Use quality-grades instead when:

• Grading domains across architectural layers
• Producing quality trend reports

Process

1. Run python3 .claude/skills/golden-principles/scripts/scan_principles.py with target
2. Review AGENT_REMEDIATION blocks in output
3. Apply suggested fixes
4. Re-run to confirm compliance

Usage

# 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

Rules

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).

Exit Codes

Code	Meaning
0	No violations found
1	Script error (bad arguments, file not found)
10	Violations detected

Suppression

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

Verification

After execution:

• Report lists scanned file count
• Each violation includes principle ID and remediation
• Exit code matches violation state
• Output format matches --format flag

References

• Code Qualities - Five foundational qualities: cohesion, coupling, non-redundancy, encapsulation, testability
• SOLID Principles - SRP, OCP, LSP, ISP, DIP with violation signs and code examples
• Programming by Intention - Sergeant pattern for expressing intent over implementation
• Separation of Concerns - Decomposition at method, class, layer, and service levels
• DRY Principle - Single authoritative representation with scope, violations, and when NOT to DRY

Cross-References

• Golden Principles Document
• Taste Lints for GP-007, GP-008
• Quality Grades for domain-level grading