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 skills add hamzaPixl/pixl-ai --skill fullstack-appgit clone --depth 1 https://github.com/hamzaPixl/pixl-aiWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/hamzapixl/pixl-ai/fullstack-app)<a href="https://agentmods.dev/skills/hamzapixl/pixl-ai/fullstack-app"><img src="https://agentmods.dev/badge/skills/hamzapixl/pixl-ai/fullstack-app/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/hamzapixl/pixl-ai/fullstack-app"><img src="https://agentmods.dev/badge/skills/hamzapixl/pixl-ai/fullstack-app.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00048 | $0.00867 |
| Opus 5.5 | $0.00019 | $0.00347 |
| Sonnet 5.5 | $0.00010 | $0.00173 |
| Haiku 4.5 | $0.00005 | $0.00087 |
Grade A, and why
fullstack-app 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 1mo ago.
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.
How it starts
The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Overview
Combines the nextjs and saas studio stacks to build a complete fullstack application. Scaffolds both frontend and backend, implements the API contract between them, and verifies the end-to-end flow.
Studio Stacks
- Frontend:
studio/stacks/nextjs/(75 templates) - Backend:
studio/stacks/saas/(18 foundation packages + service template)
Suggested Team
- architect — System design, API contract, data model
- fullstack-engineer — Cross-boundary implementation
- qa-engineer — E2E testing, review loops
- devops-engineer — Docker, CI/CD for both services
Process
Phase 1: Architecture
- Define the domain model and API contract
- Decide on data flow (REST API, server actions, or tRPC)
- Plan authentication flow (JWT from backend, session on frontend)
Phase 1.5: API Contract Specification
3.5. Define shared Zod schemas for all request/response types
3.6. Document endpoints in OpenAPI format (method, path, body, response)
3.7. Agree on error response format: { error: { code, message } }
3.8. Write the API contract to .context/api-contract.json (type: architecture, see references/orchestration/context-packet.md)
3.9. Write architecture decisions and component tree to .context/architecture.md
Phase 2 + 3: Parallel Backend & Frontend Build
You MUST spawn the following 2 agents in parallel via the Task tool. Do NOT run these sequentially — the backend and frontend can be built simultaneously because both receive the API contract from Phase 1.5.
Pre-wave: Context Packet
Before spawning agents, compile a context packet containing:
- The full API contract from
.context/api-contract.json(Zod schemas, OpenAPI endpoint definitions, error format) - The domain model from Phase 1
- Authentication flow design (JWT structure, session strategy)
Parallel Wave — Backend + Frontend (2 parallel Task agents)
| Agent | Role | Directory | Responsibility |
|---|---|---|---|
| A | backend-engineer | <service-dir>/ |
Read .context/api-contract.json before scaffolding. Run /saas-microservice — scaffold and implement all backend endpoints from the API contract. Verify API endpoints are working and documented (Swagger). File ownership: the service directory ONLY. DO NOT create or modify any files in <frontend-dir>/. |
| B | frontend-engineer | <frontend-dir>/ |
Read .context/api-contract.json for API client generation. Run /website — scaffold the frontend, create typed fetch wrappers from the endpoint definitions, build pages that fetch and display data, add forms that create/update data through the API. File ownership: the frontend directory ONLY. DO NOT create or modify any files in <service-dir>/. |
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.
- 1mo ago First seen · 76 lines · 48 tokens per session scan A dd792242569f
fullstack-app is a skill published in the GitHub repository hamzaPixl/pixl-ai (2 stars, last pushed 6mo ago), licensed MIT. It adds 48 tokens to every session and 867 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
nextjs-pages-router
Set up tRPC in Next.js Pages Router with createNextApiHandler, createTRPCNext, withTRPC HOC, SSR via ssr option and ssrPrepass, SSG via createServerSideHelpers with getStaticProps, and server-side helpers for getServerSideProps prefetching.
subscriptions
Set up real-time event streams with async generator subscriptions using .subscription(async function() { yield }). SSE via httpSubscriptionLink is recommended over WebSocket. Use tracked(id, data) from @trpc/server for reconnection recovery with lastEventId. WebSocket via wsLink and createWSClient from @trpc/client…
non-json-content-types
Handle FormData, file uploads, Blob, Uint8Array, and ReadableStream inputs in tRPC mutations. Use octetInputParser from @trpc/server/http for binary data. Route non-JSON requests with splitLink and isNonJsonSerializable() from @trpc/client. FormData and binary inputs only work with mutations (POST).
server-side-calls
Call tRPC procedures directly from server code using t.createCallerFactory() and router.createCaller(context) for integration testing, internal server logic, and custom API endpoints. Catch TRPCError and extract HTTP status with getHTTPStatusCodeFromError(). Error handling via onError option.
service-oriented-architecture
Break a tRPC backend into multiple services with custom routing links that split on the first path segment (op.path.split('.')) to route to different backend service URLs. Define a faux gateway router that merges service routers for the AppRouter type without running them in the same process. Share procedure and…
adapter-standalone
Mount tRPC on Node.js built-in HTTP server with createHTTPServer() from @trpc/server/adapters/standalone, createHTTPHandler() for custom http.createServer, createHTTP2Handler() for HTTP/2 with TLS. Configure basePath to slice URL prefix, CORS via the cors npm package passed as middleware option.…