adversarial-coachAdversarial implementation review based on Block's g3 dialectical autocoding research. Use when validating implementation completeness against requirements with fresh objectivity.
Install via ClawdBot CLI:
clawdbot install killerapp/adversarial-coach/coach [requirements-file]/coach - Infer requirements from context/coach requirements.md - Validate against specific fileYou orchestrate this dialectical loop between implementing agent (player) and reviewer (coach):
/coach invokes adversarial review with independent evaluation of compliance to requirementsIMPLEMENTATION_APPROVED or specific fixesCheck (in order):
requirements.md, REQUIREMENTS.md, SPEC.md, TODO.mdReview with fresh objectivity - discard prior knowledge, don't rationalize shortcuts.
| Check Category | Items |
|----------------|-------|
| Requirements | Each item: implemented or missing with specific gap |
| Compilation | Compiles? Tests pass? Runs? |
| Common Gaps | Auth on endpoints, token refresh endpoint, HTTPS, bcrypt for passwords, error handling, input validation |
| Functional | Test actual flows (not just compilation), verify edge cases work |
| Test Coverage | Auth error cases (401/403), token expiry, invalid inputs, rate limits |
If approved (>95% complete):
IMPLEMENTATION_APPROVED
- [Requirement 1]: Verified
- [Requirement 2]: Verified
- Compilation: Success
- Tests: All passingIf fixes needed:
REQUIREMENTS COMPLIANCE:
- [Requirement]: Implemented
- [Requirement]: Missing - [specific gap]
IMMEDIATE ACTIONS NEEDED:
1. [Specific fix with file/line if known]
2. [Specific fix]Rigorous but fair:
Concise:
Fresh context is your superpower:
IMPLEMENTATION_APPROVED = termination signal
Only use when: all requirements met, code compiles/runs, tests pass, no significant gaps.
If in doubt, don't approve.
User: /coach SPEC.md
Claude:
REQUIREMENTS COMPLIANCE:
- User registration endpoint (bcrypt hashing)
- Login with JWT tokens
- Logout endpoint - not implemented
- Token refresh - missing /auth/refresh endpoint
IMMEDIATE ACTIONS NEEDED:
1. Add POST /auth/logout endpoint
2. Add POST /auth/refresh for token renewal
3. Add tests for 401 on expired tokens
---
User: [fixes] /coach SPEC.md
Claude:
IMPLEMENTATION_APPROVED
- All auth endpoints verified (register, login, logout, refresh)
- 18 tests passing including auth error casesGenerated Mar 1, 2026
Ensures secure authentication endpoints, token refresh, and error handling are implemented correctly in financial APIs. Validates compliance with regulatory requirements like input validation and HTTPS.
Reviews new features such as payment processing or user account management against specifications. Checks for security gaps like bcrypt password hashing and functional edge cases.
Validates implementation of patient data handling features against HIPAA or other regulatory specs. Focuses on auth, error handling, and test coverage for sensitive data flows.
Assesses new integrations or modules in SaaS products for completeness against documented requirements. Ensures endpoints are functional, tests pass, and common gaps like token refresh are addressed.
Helps maintainers review pull requests by independently evaluating code against project specs. Catches missing features, compilation issues, and security flaws in contributions.
Offers monthly plans for developers to submit implementation reviews, ensuring code quality and compliance. Revenue comes from tiered subscriptions based on review frequency and project size.
Integrates with CI/CD pipelines to provide automated adversarial reviews for large organizations. Generates revenue through enterprise licensing and custom integration support.
Provides free basic reviews with paid upgrades for advanced features like detailed gap analysis and priority support. Monetizes via premium tiers and API usage fees.
💬 Integration Tip
Integrate into CI/CD pipelines to automate reviews on code commits, ensuring continuous compliance with requirements and reducing manual oversight.
AI-powered idea/problem/challenge manager with GitHub integration. Captures, categorizes, reviews, and helps ship ideas to repos.
Daily wisdom review applying Charlie Munger's mental models to your work and thinking. Use when asked to review decisions, analyze thinking patterns, detect biases, apply mental models, do a "Munger review", or run the Munger Observer. Triggers on scheduled daily reviews or manual requests like "run munger observer", "review my thinking", "check for blind spots", or "apply mental models".
AI language tutor for learning ANY language through conversation, vocab drills, grammar lessons, flashcards, and immersive practice. Use when the user wants to: learn a new language, practice vocabulary, study grammar, do flashcard drills, translate phrases, practice conversation, prepare for travel, learn slang/idioms, or improve pronunciation. Supports ALL languages including Spanish, French, German, Japanese, Chinese (Mandarin/Cantonese), Korean, Arabic, Hindi, Bengali/Bangla, Portuguese, Russian, Italian, Turkish, Vietnamese, Thai, Swahili, Hebrew, Polish, Dutch, Greek, and 100+ more.
Auto-learns how you learn best. Adapts teaching style, format, and depth to you.
Interactive Japanese learning assistant. Supports vocabulary, grammar, quizzes, roleplay, PDF/DOCX material parsing for study/homework help, and OCR translation.
Auto-analyze mistake and success patterns and reflect in skills