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-reviewgit 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-review)<a href="https://agentmods.dev/skills/hoangnguyen0403/agent-skills-standard/system-design-review"><img src="https://agentmods.dev/badge/skills/hoangnguyen0403/agent-skills-standard/system-design-review/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-review"><img src="https://agentmods.dev/badge/skills/hoangnguyen0403/agent-skills-standard/system-design-review.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 | $0.00055 | $0.00827 |
| Opus 5 | $0.00028 | $0.00413 |
| Sonnet 5 | $0.00011 | $0.00165 |
| Haiku 4.5 | $0.00006 | $0.00083 |
Grade A, and why
system-design-review 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
System Design Review
Priority: P1 (HIGH)
Score against evidence, not intent. A claim with no number or artifact scores zero.
Nine Axes (score each 0-10)
| Axis | Scores 10 when | Scores 0 when |
|---|---|---|
| Requirements | Functional, NFR, and out-of-scope written with owners | Only a feature description exists |
| Capacity evidence | Peak QPS, storage, and bandwidth computed and current | Numbers absent or older than the last traffic change |
| Redundancy | No SPOF; failover drilled with a measured RTO | Single instance or untested failover on a critical path |
| Data scaling | Access patterns mapped, ownership single, growth path stated | One shared store, no growth plan, unbounded tables |
| Caching | Hot read paths cached with TTL and invalidation defined | No cache on a proven hot path, or uninvalidatable cache |
| Async offload | Slow and bursty work queued with drain rate and DLQ | Everything synchronous on the request path |
| Observability | Traffic, error, latency, saturation instrumented with owned alerts | Logs only, or alerts with no runbook |
| Rollout | Canary or flag with metric rollback trigger and reversible migrations | Big-bang deploy, irreversible migration |
| Cost proportionality | Spend is sized to the traffic and the risk, and someone can state it | Topology bought for an imagined scale nobody measured |
Report each score with the evidence used, out of 90. Weight axes by the system's actual risk: a 100 RPS internal tool is not failed for lacking multi-region.
Review Method
- Establish ground truth first: current traffic, data volume, incident history, and the top pain the owner reports.
- Score the eight axes against artifacts and metrics; mark any unverifiable claim
UNVERIFIED. - Trace the hottest and the most critical path end to end; the worst hop is the real bottleneck.
- List findings as
severity - axis - evidence - consequence - smallest fix. - Convert findings into a roadmap: stop-the-bleeding now, structural next, optional later.
- Check operability: who runs this at 3am, which team owns which piece, and whether that team can actually operate it.
What ships with it
2 files 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 · 69 lines · 55 tokens per session scan A c7b824bff9dc
system-design-review is a skill published in the GitHub repository HoangNguyen0403/agent-skills-standard (565 stars, last pushed 3d ago), licensed MIT. It adds 55 tokens to every session and 827 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.