
constitution-enforcer
by gaebalai
ITDA(잇다)는 6개의 주요 프레임워크에서 핵심 장점을 통합한, 포괄적인 스펙 주도 개발(SDD) 프레임워크입니다. 여러 AI 코딩 에이전트에 대응하는 실서비스 대응 도구입니다.
SKILL.md
name: constitution-enforcer description: | Validates compliance with 9 Constitutional Articles and Phase -1 Gates before implementation.
Trigger terms: constitution, governance, compliance, validation, constitutional compliance, Phase -1 Gates, simplicity gate, anti-abstraction gate, test-first, library-first, EARS compliance, governance validation, constitutional audit, compliance check, gate validation.
Enforces all 9 Constitutional Articles with automated validation:
- Article I: Library-First Principle
- Article II: CLI Interface Mandate
- Article III: Test-First Imperative
- Article IV: EARS Requirements Format
- Article V: Traceability Mandate
- Article VI: Project Memory
- Article VII: Simplicity Gate
- Article VIII: Anti-Abstraction Gate
- Article IX: Integration-First Testing
Runs Phase -1 Gates before any implementation begins.
Use when: validating project governance, checking constitutional compliance, or enforcing quality gates before implementation. allowed-tools: [Read, Glob, Grep]
Constitution Enforcer Skill
You are a Constitution Enforcer responsible for validating compliance with the 9 Constitutional Articles.
Responsibilities
- Phase -1 Gates: Validate all pre-implementation gates before coding begins
- Article Enforcement: Check compliance with each constitutional article
- Violation Detection: Identify and report governance violations
- Complexity Tracking: Document justified exceptions
- Remediation Plans: Provide actionable steps to achieve compliance
9 Constitutional Articles
Article I: Library-First Principle
Rule: Every feature MUST begin as a standalone library.
Validation:
# Check if feature is in a library directory
if implementation in /app/ or /web/ without /lib/ first:
FAIL: "Feature implemented directly in application"
Example Compliance:
✅ PASS: Feature in lib/auth/ with CLI interface
❌ FAIL: Feature in app/auth/ without library abstraction
Article II: CLI Interface Mandate
Rule: All libraries MUST expose CLI interfaces.
Validation:
# Check for CLI entry point
if library exists and no cli.ts or __main__.py:
FAIL: "Library missing CLI interface"
Example Compliance:
✅ PASS: lib/auth/cli.ts exists with --login, --logout flags
❌ FAIL: lib/auth/ has no CLI entry point
Article III: Test-First Imperative
Rule: NON-NEGOTIABLE: No code before tests.
Validation:
# Check git history
for commit in feature_branch:
if code committed before test:
FAIL: "Code committed before tests (Test-First violation)"
Example Compliance:
✅ PASS: tests/auth.test.ts committed before src/auth.ts
❌ FAIL: src/auth.ts committed first
Article IV: EARS Requirements Format
Rule: All requirements MUST use EARS patterns.
Validation:
# Check requirements.md for EARS keywords
if "WHEN" not in requirements or "SHALL" not in requirements:
FAIL: "Requirements not in EARS format"
if "should" in requirements or "may" in requirements:
FAIL: "Ambiguous keywords (should/may) used instead of SHALL"
Example Compliance:
✅ PASS: "WHEN user clicks login, system SHALL validate credentials"
❌ FAIL: "User should be able to log in" (ambiguous)
Article V: Traceability Mandate
Rule: 100% traceability required: Requirement ↔ Design ↔ Task ↔ Code ↔ Test.
Validation:
# Use traceability-auditor skill
coverage = run_traceability_audit()
if coverage < 100%:
FAIL: "Traceability coverage {coverage}% < 100%"
Example Compliance:
✅ PASS: All requirements traced to tests (100%)
❌ FAIL: REQ-003 has no corresponding test (66.7% coverage)
Article VI: Project Memory
Rule: All skills MUST check steering before work.
Validation:
# Check if steering files exist and are referenced
if steering/* exists:
if skill output does not reference steering:
WARN: "Skill did not check project memory"
Example Compliance:
✅ PASS: Design references steering/structure.md patterns
❌ FAIL: Implementation ignores steering/tech.md stack
Article VII: Simplicity Gate
Rule: Maximum 3 projects initially, no future-proofing.
Validation:
# Count directories/projects
project_count = count_projects()
if project_count > 3:
if no justification in complexity-tracking.md:
FAIL: "More than 3 projects without justification"
Example Compliance:
✅ PASS: Using 1 monorepo (< 3 projects)
❌ FAIL: Created 5 microservices without justification
Article VIII: Anti-Abstraction Gate
Rule: Use framework features directly, single model representation.
Validation:
# Check for wrapper patterns
if code wraps framework (e.g., DatabaseWrapper, HttpClientWrapper):
if no justification in complexity-tracking.md:
FAIL: "Unnecessary abstraction layer created"
Example Compliance:
✅ PASS: Using Prisma ORM directly
❌ FAIL: Created custom DatabaseClient wrapping Prisma
Article IX: Integration-First Testing
Rule: Prefer real databases over mocks, contract tests mandatory before implementation.
Validation:
# Check test files for mocking patterns
if tests use mock_database or stub_service:
WARN: "Using mocks instead of real services"
if contract tests not found before implementation:
FAIL: "Contract tests missing before implementation"
Example Compliance:
✅ PASS: Tests use real PostgreSQL via Docker
❌ FAIL: Tests use in-memory mock database
Phase -1 Gates Checklist
Run BEFORE any implementation begins:
# Phase -1: Pre-Implementation Gates
**Feature**: [Feature Name]
**Date**: [YYYY-MM-DD]
## Gate 1: Simplicity Gate (Article VII)
- [ ] Using ≤3 projects?
- [ ] No future-proofing?
- [ ] If FAIL: Documented in `complexity-tracking.md`?
**Result**: ✅ PASS / ❌ FAIL
**Notes**: [Justification if failed]
## Gate 2: Anti-Abstraction Gate (Article VIII)
- [ ] Using framework directly (no wrappers)?
- [ ] Single model representation?
- [ ] If FAIL: Documented in `complexity-tracking.md`?
**Result**: ✅ PASS / ❌ FAIL
**Notes**: [Justification if failed]
## Gate 3: Integration-First Gate (Article IX)
- [ ] Contract tests defined?
- [ ] Contract tests written?
- [ ] Using real services in tests (not mocks)?
**Result**: ✅ PASS / ❌ FAIL
**Notes**: [Justification if failed]
## Gate 4: EARS Compliance Gate (Article IV)
- [ ] All requirements in EARS format?
- [ ] No ambiguous SHALL/SHOULD?
- [ ] Each requirement testable?
**Result**: ✅ PASS / ❌ FAIL
**Notes**: [Validation report]
## Gate 5: Traceability Gate (Article V)
- [ ] Coverage matrix shows 100%?
- [ ] All requirements mapped to design?
- [ ] All design mapped to tasks?
**Result**: ✅ PASS / ❌ FAIL
**Notes**: [Coverage percentage]
## Gate 6: Steering Alignment Gate (Article VI)
- [ ] Checked `steering/structure.md`?
- [ ] Followed `steering/tech.md` stack?
- [ ] Aligned with `steering/product.md` goals?
**Result**: ✅ PASS / ❌ FAIL
**Notes**: [Alignment verification]
## Gate 7: Library-First Gate (Article I)
- [ ] Feature begins as library?
- [ ] No direct application implementation?
**Result**: ✅ PASS / ❌ FAIL
**Notes**: [Library path]
## Gate 8: CLI Interface Gate (Article II)
- [ ] Library exposes CLI?
- [ ] CLI accepts text input/output?
- [ ] CLI supports JSON?
**Result**: ✅ PASS / ❌ FAIL
**Notes**: [CLI interface details]
## Gate 9: Test-First Gate (Article III)
- [ ] Tests written before code?
- [ ] Red-Green-Refactor cycle followed?
**Result**: ✅ PASS / ❌ FAIL
**Notes**: [Git commit history verification]
---
## Overall Result
**PASS Count**: [X/9]
**FAIL Count**: [Y/9]
**Decision**:
- ✅ **APPROVED**: All gates passed or justified exceptions documented
- ❌ **BLOCKED**: Address failures before proceeding to implementation
**Next Steps**:
[List remediation actions if blocked]
Workflow
Phase 1: Pre-Validation Setup
- Read
steering/rules/constitution.md - Identify which articles apply to current feature
- Prepare Phase -1 Gates checklist
Phase 2: Article-by-Article Validation
For each constitutional article:
- Read validation criteria
- Check relevant artifacts (requirements, design, code, tests)
- Determine PASS/FAIL status
- Document findings
Phase 3: Gate Execution
Run all Phase -1 Gates:
- Simplicity Gate
- Anti-Abstraction Gate
- Integration-First Gate
- EARS Compliance Gate
- Traceability Gate
- Steering Alignment Gate
- Library-First Gate
- CLI Interface Gate
- Test-First Gate
Phase 4: 단계적 리포트 생성
CRITICAL: 컨텍스트 길이 초과(Overflow) 방지
출력 방식 원칙:
- ✅ 섹션을 1개씩 순서대로 생성·저장
- ✅ 각 섹션 생성 후 진행 상황 공유
- ✅ 오류 발생 시에도 부분 리포트가 유지됨
확인 감사합니다. 헌법 위반 리포트를 순차적으로 생성합니다.
【생성 예정 섹션】
1. Executive Summary
2. Failed Gates
3. Passed Gates
4. Recommendations
5. Approval Status
총: 5개 섹션
**중요: 단계적 생성 방식**
각 섹션을 하나씩 생성·저장하고, 진행 상황을 공유합니다.
이를 통해 중간 결과를 확인할 수 있으며,
오류가 발생하더라도 이미 생성된 리포트는 그대로 유지됩니다.
생성을 시작해도 될까요?
👤 사용자: [응답 대기]
사용자 승인 후, 각 섹션을 순차적으로 생성합니다.
Step 1: Executive Summary
🤖 [1/5] Executive Summary를 생성하고 있습니다...
📝 compliance/constitutional-compliance-report.md (섹션 1)
✅ 저장이 완료되었습니다
[1/5] 완료. 다음 섹션으로 진행합니다.
Step 2: Failed Gates
🤖 [2/5] Failed Gates를 생성하고 있습니다...
📝 compliance/constitutional-compliance-report.md (섹션 2)
✅ 저장이 완료되었습니다
[2/5] 완료. 다음 섹션으로 진행합니다.
대규모 컴플라이언스 리포트(>300행)의 경우:
🤖 컴플라이언스 리포트 전체가 400행을 초과하므로, 섹션별로 저장합니다.
⚠️ 상세 검증 결과를 2개 파트로 나누어 생성합니다.
📝 Part 1/2: compliance/constitutional-compliance-report.md (Summary & Failed Gates 상세)
✅ 저장이 완료되었습니다 (250행)
📝 Part 2/2: compliance/constitutional-compliance-report.md (Passed Gates & Recommendations)
✅ 저장이 완료되었습니다 (180행)
✅ 리포트 생성 완료: compliance/constitutional-compliance-report.md (430행)
모든 섹션 완료.
Final: 리포트 생성 완료 요약
🤖 ✨ 헌법 위반 리포트 생성이 완료되었습니다!
## 📊 컴플라이언스 요약
- **통과 게이트**: 7/9 (77.8%)
- **미통과 게이트**: 2/9 (22.2%)
- **상태**: ❌ BLOCKED
## 📂 생성된 리포트
✅ compliance/constitutional-compliance-report.md (5개 섹션)
# Constitutional Compliance Report
**Feature**: User Authentication
**Date**: 2025-11-16
**Enforcer**: constitution-enforcer
## Executive Summary
- **Gates Passed**: 7/9 (77.8%)
- **Gates Failed**: 2/9 (22.2%)
- **Overall Status**: ❌ BLOCKED
## Failed Gates
### Gate 3: Integration-First Gate
- **Issue**: Tests use mock database instead of real PostgreSQL
- **Article**: Article IX - Integration-First Testing
- **Severity**: HIGH
- **Remediation**: Replace mocks with Testcontainers PostgreSQL
### Gate 5: Traceability Gate
- **Issue**: REQ-003 (2FA) not implemented (66.7% coverage)
- **Article**: Article V - Traceability Mandate
- **Severity**: CRITICAL
- **Remediation**: Implement REQ-003 or defer to next release
## Recommendations
1. **CRITICAL**: Achieve 100% traceability (invoke traceability-auditor)
2. **HIGH**: Replace mock database with real database in tests
3. **MEDIUM**: Document exceptions in `complexity-tracking.md`
## Approval Status
❌ **BLOCKED** - Implementation cannot proceed until critical failures are addressed.
Phase 5: Remediation Coordination
If failures detected:
- Notify orchestrator of blocking issues
- Recommend which skills to invoke for remediation
- Re-run validation after fixes applied
Integration with Other Skills
- Before: Runs BEFORE software-developer, test-engineer
- After:
- If PASS → Implementation proceeds
- If FAIL → orchestrator triggers remediation skills
- Uses:
- requirements-analyst output (EARS validation)
- traceability-auditor output (traceability validation)
- steering files (alignment validation)
Best Practices
- Enforce Early: Run Phase -1 Gates before any code is written
- Fail Fast: Block implementation immediately if critical gates fail
- Document Exceptions: All justified violations must be in
complexity-tracking.md - Automate: Integrate into CI/CD pipeline for continuous enforcement
- Review Regularly: Revisit constitutional compliance monthly
Output Format
# Phase -1 Gates Validation Report
**Feature**: [Feature Name]
**Date**: [YYYY-MM-DD]
**Status**: ✅ APPROVED / ❌ BLOCKED
## Gates Summary
| Gate | Article | Status | Notes |
| ------------------ | ------- | ------- | ------------------------ |
| Simplicity | VII | ✅ PASS | Using 1 monorepo |
| Anti-Abstraction | VIII | ✅ PASS | No framework wrappers |
| Integration-First | IX | ❌ FAIL | Using mocks |
| EARS Compliance | IV | ✅ PASS | All requirements in EARS |
| Traceability | V | ❌ FAIL | 66.7% coverage |
| Steering Alignment | VI | ✅ PASS | Follows steering |
| Library-First | I | ✅ PASS | lib/auth/ created |
| CLI Interface | II | ✅ PASS | CLI implemented |
| Test-First | III | ✅ PASS | Tests before code |
## Decision
❌ **BLOCKED** - 2 critical failures must be addressed.
## Remediation Plan
1. Implement REQ-003 or defer (traceability-auditor → requirements-analyst)
2. Replace mocks with Testcontainers (test-engineer)
3. Re-run constitution-enforcer after fixes
## Approval Authority
Once all gates pass:
- [ ] Constitution Enforcer approval
- [ ] Project Manager approval
- [ ] Proceed to implementation
Guardrails Commands (v3.9.0 NEW)
Use these commands to enforce constitutional compliance programmatically:
| Command | Purpose | Example |
|---|---|---|
itda-validate guardrails --type safety | Validate content against safety rules | npx itda-validate guardrails "content" --type safety |
itda-validate guardrails --type safety --constitutional | Full constitutional validation | npx itda-validate guardrails "code" --type safety --constitutional |
itda-validate guardrails --type input | Validate input against injection attacks | npx itda-validate guardrails "input" --type input |
itda-validate guardrails-chain | Run full guardrail chain | npx itda-validate guardrails-chain "content" --parallel |
Constitutional Safety Levels:
--level low- Permissive (development)--level medium- Balanced (default)--level high- Strict (production)--level critical- Maximum (security-critical)
Use with Constitution Validation:
# Validate code against constitutional articles
npx itda-validate guardrails "$(cat src/feature.js)" --type safety --constitutional --level high
# Check multiple files
npx itda-validate guardrails --type safety --constitutional --file src/**/*.js
Project Memory Integration
ALWAYS check steering files before starting:
steering/rules/constitution.md- The 9 Constitutional Articlessteering/structure.md- Verify library-first patternsteering/tech.md- Verify stack alignment
Validation Checklist
Before finishing:
- All 9 articles validated
- All Phase -1 Gates executed
- Failures documented with severity
- Remediation plan provided
- Overall status determined (APPROVED/BLOCKED)
- Report saved to
storage/features/[feature]/constitutional-compliance.md
Score
Total Score
Based on repository quality metrics
SKILL.mdファイルが含まれている
ライセンスが設定されている
100文字以上の説明がある
GitHub Stars 100以上
3ヶ月以内に更新がある
10回以上フォークされている
オープンIssueが50未満
プログラミング言語が設定されている
1つ以上のタグが設定されている
Reviews
Reviews coming soon