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 shahtuyakov/claude-setup --skill system-designgit clone --depth 1 https://github.com/shahtuyakov/claude-setupWrote 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/shahtuyakov/claude-setup/system-design)<a href="https://agentmods.dev/skills/shahtuyakov/claude-setup/system-design"><img src="https://agentmods.dev/badge/skills/shahtuyakov/claude-setup/system-design/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/shahtuyakov/claude-setup/system-design"><img src="https://agentmods.dev/badge/skills/shahtuyakov/claude-setup/system-design.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 | $0.00054 | $0.00451 |
| Opus 5.5 | $0.00022 | $0.00180 |
| Sonnet 5.5 | $0.00011 | $0.00090 |
| Haiku 4.5 | $0.00005 | $0.00045 |
Grade A, and why
system-design 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.
What it actually says
System Design
Architectural decision framework for web apps and iOS native applications with custom backends.
Decision Process
- Identify requirements (scale, platform, constraints)
- Load relevant reference file (see table below)
- Use comparison matrix to evaluate options
- Verify compatibility using MCP context7 for latest docs
- Document decision with rationale
Reference Navigation
| Decision Type | Load | Use When |
|---|---|---|
| API style | references/api-patterns.md |
Choosing REST vs GraphQL vs gRPC |
| Database | references/database-patterns.md |
Selecting primary database, caching layer |
| Authentication | references/auth-patterns.md |
Designing auth flow, token strategy |
| Real-time | references/realtime-patterns.md |
Adding live updates, push notifications |
| iOS architecture | references/ios-patterns.md |
Native iOS app structure, offline-first |
| Backend architecture | references/architecture-patterns.md |
Monolith vs microservices, serverless |
| File storage | references/storage-patterns.md |
Media uploads, CDN, cloud storage |
Decision Documentation
Record each decision in .agents/architect/decisions.md:
## [date] - [decision title]
Context: [what prompted this decision]
Options: [what was considered]
Decision: [what was chosen]
Rationale: [why]
Platform Considerations
Web + iOS Projects
- Design API with mobile constraints in mind (bandwidth, battery)
- Plan for offline-first on iOS with backend sync
- Consider BFF (Backend for Frontend) if needs diverge significantly
iOS-Specific
- Always check
references/ios-patterns.mdfor native patterns - Auth must include Keychain storage and biometrics
- Push notifications require APNs backend integration
What ships with it
7 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.
- 1mo ago First seen · 53 lines · 54 tokens per session scan A 6052ef04f9a6
system-design is a skill published in the GitHub repository shahtuyakov/claude-setup (13 stars, last pushed 9mo ago), licensed MIT. It adds 54 tokens to every session and 451 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 2026-08-30.
Other skills, from other repositories
octopus-architecture
Review system architecture, simplify boundaries, or compare interface designs from repository evidence.
touch-app
Produce a complete mobile app architecture design — platform choice, navigation structure, state management, data layer, key screens. Use when asked to "build a mobile app", "new app", "create iOS/Android app", "app architecture", or "cross-platform app".
spine-design
Produce a system design doc — components, data flow, decisions made, tradeoffs, failure modes. Not a list of options. An actual design with calls made. Use when asked for "system design for", "architect this", "how should we build", or "design the backend".
warden-harden
Produce a hardening spec and implement it — auth patterns, security headers, rate limiting, input validation, secrets management, dependency hygiene. Use when asked to "harden this", "add security to this service", "what security do I need", or "secure this before launch".
cortex-integrate
Design and implement an AI feature integration — model selection, architecture pattern, system prompt, data flow, error handling, cost estimate. Use when asked to "add AI to this", "LLM integration", "add Claude/GPT", or "AI-powered feature".
spine-api
Design and spec an API — endpoints, request/response shapes, error codes, auth pattern, pagination. Applies Stripe's consistency principles. Use when asked to "design an API", "build API endpoints", "create REST API", or "API for this feature".