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 HoangNguyen0403/agent-skills-standard --skill system-design-case-cataloggit clone --depth 1 https://github.com/HoangNguyen0403/agent-skills-standardWrote 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/hoangnguyen0403/agent-skills-standard/system-design-case-catalog)<a href="https://agentmods.dev/skills/hoangnguyen0403/agent-skills-standard/system-design-case-catalog"><img src="https://agentmods.dev/badge/skills/hoangnguyen0403/agent-skills-standard/system-design-case-catalog/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/hoangnguyen0403/agent-skills-standard/system-design-case-catalog"><img src="https://agentmods.dev/badge/skills/hoangnguyen0403/agent-skills-standard/system-design-case-catalog.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00058 | $0.00702 |
| Opus 5 | $0.00029 | $0.00351 |
| Sonnet 5 | $0.00012 | $0.00140 |
| Haiku 4.5 | $0.00006 | $0.00070 |
Grade A, and why
system-design-case-catalog 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 12d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Case Catalog
Priority: P2 (MEDIUM)
Each classic problem has one defining constraint. Name it first; the rest of the design follows.
Defining Constraints
| Problem | Defining constraint | Decisions that follow |
|---|---|---|
| URL shortener | Read-heavy by ~100:1, key must be short and unique | Base62 of a distributed counter, cache-first read path, 301 vs 302 choice |
| Rate limiter | Decision must be cheap, shared, and correct under concurrency | Token bucket in a shared counter, fail-open or fail-closed rule, 429 plus Retry-After |
| News feed | Fan-out cost versus read latency, with celebrity skew | Push for normal accounts, pull for celebrities, hybrid merge at read |
| Chat | Delivery guarantees and presence at persistent-connection scale | WebSocket gateways, per-conversation ordering, offline queue, read receipts |
| Notification | Multi-channel delivery with retries and dedupe | Queue per channel, idempotency key, user preference and quiet hours |
| Autocomplete | Sub-100ms prefix lookup over a huge term space | Trie or prefix index in memory, precomputed top-k per prefix, async rebuild |
| Web crawler | Politeness and dedupe at scale, not raw fetching | Frontier queue per host, robots cache, URL fingerprint dedupe, freshness policy |
| Unique id | Ordered, unique, generated without a central lock | Snowflake-style timestamp plus node plus sequence; clock-skew handling |
Coaching Mode
- Restate the problem, then ask for scope: which use cases are in, which are out.
- Run the phases from
system-design-methodology; do not answer with a finished architecture. - Grade the candidate on: requirements first, numbers before components, one justification per component, awareness of the defining constraint, and honest trade-offs.
- Push on the weakest area with one concrete follow-up question rather than listing every gap.
- Give the model answer only after the candidate commits to an approach.
Reuse Rules
- Map a new problem to the nearest catalog shape, then re-derive the numbers. The shape transfers, the sizing never does.
- State where the analogy breaks before borrowing the design.
- A catalog answer is a starting hypothesis, not a substitute for intake and estimation.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 59 lines · 58 tokens per session scan A 48aa88ead3d9
system-design-case-catalog is a skill published in the GitHub repository HoangNguyen0403/agent-skills-standard (565 stars, last pushed 3d ago), licensed MIT. It adds 58 tokens to every session and 702 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
nextjs-app-router
Full end-to-end tRPC setup for Next.js App Router. Covers route handler with fetchRequestHandler (GET + POST exports), TRPCProvider with QueryClientProvider, createTRPCOptionsProxy for RSC prefetching, HydrateClient/HydrationBoundary for hydration, useSuspenseQuery for Suspense, and server-side callers.
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.
openapi
Generate OpenAPI 3.1 spec from a tRPC router with @trpc/openapi CLI or programmatic API. Generate typed REST client with @hey-api/openapi-ts and configureTRPCHeyApiClient(). Configure transformers (superjson, EJSON) for generated clients. Alpha status.
server-setup
Initialize tRPC with initTRPC.create(), define routers with t.router(), create procedures with .query()/.mutation()/.subscription(), configure context with createContext(), export AppRouter type, merge routers with t.mergeRouters(), lazy-load routers with lazy().
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…
client-setup
Create a vanilla tRPC client with createTRPCClient (), configure link chain with httpBatchLink/httpLink, dynamic headers for auth, transformer on links (not client constructor). Infer types with inferRouterInputs and inferRouterOutputs. AbortController signal support. TRPCClientError typing.