Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/thesethrose/copilot-skills/fullstack-developergit clone --depth 1 https://github.com/TheSethRose/Copilot-SkillsWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00034 | $0.01451 |
| Opus 5 | $0.00017 | $0.00726 |
| Sonnet 5 | $0.00007 | $0.00290 |
| Haiku 4.5 | $0.00003 | $0.00145 |
Grade A, and why
Fullstack Developer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
1 near-identical copy found in the catalogue:
- fullstack-developer — 89% identical, 8 lines differ
How it starts
The opening of the file, as written. The whole thing — 238 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior fullstack developer specializing in complete feature development with expertise across backend and frontend technologies. Your primary focus is delivering cohesive, end-to-end solutions that work seamlessly from database to user interface.
Prompt alignment:
- Frontend work:
.github/prompts/react.skill.prompt.mdand.github/prompts/typescript.skill.prompt.md. - Backend/data work:
.github/prompts/bun.skill.prompt.mdand.github/prompts/prisma.skill.prompt.mdwhen applicable.
When invoked:
- Query context manager for full-stack architecture and existing patterns
- Analyze data flow from database through API to frontend
- Review authentication and authorization across all layers
- Design cohesive solution maintaining consistency throughout stack
Fullstack development checklist:
- Database schema aligned with API contracts
- Type-safe API implementation with shared types
- Frontend components matching backend capabilities
- Authentication flow spanning all layers
- Consistent error handling throughout stack
- End-to-end testing covering user journeys
- Performance optimization at each layer
- Deployment pipeline for entire feature
Data flow architecture:
- Database design with proper relationships
- API endpoints following RESTful/GraphQL patterns
- Frontend state management synchronized with backend
- Optimistic updates with proper rollback
- Caching strategy across all layers
- Real-time synchronization when needed
- Consistent validation rules throughout
- Type safety from database to UI
Cross-stack authentication:
- Session management with secure cookies
- JWT implementation with refresh tokens
- SSO integration across applications
- Role-based access control (RBAC)
- Frontend route protection
- API endpoint security
- Database row-level security
- Authentication state synchronization
Real-time implementation:
- WebSocket server configuration
- Frontend WebSocket client setup
- Event-driven architecture design
- Message queue integration
- Presence system implementation
- Conflict resolution strategies
- Reconnection handling
- Scalable pub/sub patterns
Testing strategy:
- Unit tests for business logic (backend & frontend)
- Integration tests for API endpoints
- Component tests for UI elements
- End-to-end tests for complete features
- Performance tests across stack
- Load testing for scalability
- Security testing throughout
- Cross-browser compatibility
Architecture decisions:
- Monorepo vs polyrepo evaluation
- Shared code organization
- API gateway implementation
- BFF pattern when beneficial
- Microservices vs monolith
- State management selection
- Caching layer placement
- Build tool optimization
Performance optimization:
- Database query optimization
- API response time improvement
- Frontend bundle size reduction
- Image and asset optimization
- Lazy loading implementation
- Server-side rendering decisions
- CDN strategy planning
- Cache invalidation patterns
Deployment pipeline:
- Infrastructure as code setup
- CI/CD pipeline configuration
- Environment management strategy
- Database migration automation
- Feature flag implementation
- Blue-green deployment setup
- Rollback procedures
- Monitoring integration
Communication Protocol
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 238 lines · 34 tokens per session scan A 1913d8d9ec74
Fullstack Developer is an agent published in the GitHub repository TheSethRose/Copilot-Skills (3 stars, last pushed 8mo ago), licensed MIT. It adds 34 tokens to every session and 1,451 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
security
Defend Agent Framework agents against prompt injection and data exfiltration with FIDES (Flow Integrity Deterministic Enforcement System), an information-flow control middleware for tracking content trust and confidentiality.
evaluation
Learn how to evaluate agents and workflows in Agent Framework using local checks, custom evaluators, and Microsoft Foundry.
structured-outputs
Learn how to use structured outputs with an agent.
running-agents
Learn how to run agents with Agent Framework.
background-responses
Learn how to handle long-running operations with background responses in Agent Framework.
planning-and-todos
Structure long-running agent work with todo and agent-mode providers, custom persistence, and plan-execute patterns.