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-sessiongit 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-session)<a href="https://agentmods.dev/skills/hoangnguyen0403/agent-skills-standard/system-design-session"><img src="https://agentmods.dev/badge/skills/hoangnguyen0403/agent-skills-standard/system-design-session/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-session"><img src="https://agentmods.dev/badge/skills/hoangnguyen0403/agent-skills-standard/system-design-session.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 | $0.00038 | $0.01124 |
| Opus 5 | $0.00019 | $0.00562 |
| Sonnet 5 | $0.00008 | $0.00225 |
| Haiku 4.5 | $0.00004 | $0.00112 |
Grade A, and why
system-design-session 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 9d 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
System Design Session Skill
[!IMPORTANT] Run an interactive system design session that turns a product goal into a sized, justified architecture with diagrams, ADRs, a scorecard, and a machine-readable handoff.
Optional args: slug=, ticket=<id/url>, mode=interactive|autonomous|channel, channel=, auto_continue=true|false, profile=business|hybrid|technical.
Instructions
When the user asks to perform this workflow, execute the following steps:
System Design Workflow (Architecture / How Big)
Goal: Produce a capacity-justified architecture baseline that design-solution can turn into contracts.
Steps
- Load inputs:
- Load
system-design-methodologyplus matched siblings (estimation, building-blocks, data-architecture, resilience-ops, review, principles, diagramming). - Load PRD or ticket, existing architecture docs, and current traffic/incident data when reviewing an existing system.
- Load
- Classify and announce:
- Mode: new design | review existing | interview practice.
- Depth: quick sketch (defaults assumed, each labeled
ASSUMED) or full session (every gate confirmed). - Escalate quick to full when an irreversible or cross-team choice appears.
- Intake (gate):
- Ask max 3 blocking questions per turn from the intake checklist; supply a recommended default for each.
- Record functional requirements, NFR targets, out-of-scope fence, operating team, and every
ASSUMEDvalue. - Review-existing mode: map current state, measure real traffic and incidents, and name the binding constraint before proposing change.
- Estimate (gate):
- Compute average and peak QPS, storage over retention, bandwidth, working-set memory, and monthly cost at that scale.
- Name the shaping quantity and confirm the order of magnitude before any component is drawn.
- Design incrementally:
- Price the null option first (do nothing, buy, or extend an existing service); rejecting it needs a stated reason.
- Start from client, API, service, store; add one component at a time as
constraint -> component -> cost. - Fix API surface, data ownership, and consistency class per flow.
- Render diagrams only after the component set is agreed, per
system-design-diagramming: anarchitectureview plussequenceordataflowfor the critical path.
- Deep dive and decide:
- Dispatch the 2-3 riskiest components to
specialist-system-architect, one brief each with its numbers and consistency requirement. - Merge the returned options, failure modes, and irreversible decisions; state bottlenecks, SPOFs, and rejected alternatives with reasons.
- Write one ADR per irreversible decision, each with its reversal trigger; stage the plan as build now, enabling seam, and the metric threshold that triggers the next step.
- Save the design to
docs/design/system-design-[slug].mdwhen file writes are allowed.
- Dispatch the 2-3 riskiest components to
- Score and hand off:
- Run the nine-axis scorecard (including cost proportionality), record the risk register, and emit the handoff payload.
- Route to
design-solution; return toplan-featurewhen product scope is still undefined.
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.
- 9d ago First seen · 101 lines · 38 tokens per session scan A 86b5d2a0e332
system-design-session is a skill published in the GitHub repository HoangNguyen0403/agent-skills-standard (565 stars, last pushed 3d ago), licensed MIT. It adds 38 tokens to every session and 1,124 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 2026-09-03.
Other skills, from other repositories
elite-engineer
The operating system for elite software engineering in TypeScript, React, and Next.js. Enforces the cognitive models, architecture laws, type-level patterns, component design, visual standards, and performance mandates that separate exceptional software from the ordinary — grounded in named sources (Torvalds…
oma-frontend
Frontend specialist for React, Next.js, Angular, TypeScript with FSD-lite architecture, shadcn/ui, and design system alignment. Use for UI, component, page, layout, CSS, Tailwind, shadcn, Angular, and RxJS work.
design-patterns
Frontend design patterns with React 19.2 and TypeScript 6 examples (Composition, Compound Components, Custom Hooks, Render Props, HOC, State Machines). Use when user asks "implement pattern", "use composition", or when designing reusable components.
react-nextjs
React 19.2 + Next.js 16 development - Server Components, Cache Components, proxy.ts, View Transitions, App Router, TypeScript 6, and Tailwind CSS v4. Use when building frontend apps, creating components, or asking "how do I set up X?".
code-quality
Comprehensive frontend code review for TypeScript 6 and React 19.2 — clean code principles, component patterns, type safety, accessibility, and performance. Use when user says "review code", "refactor", "check this PR", or before merging changes.
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.