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 agentmods add skills/code-saurabh/openskills/system-designnpx skills add CODE-SAURABH/OpenSkills --skill system-designgit clone --depth 1 https://github.com/CODE-SAURABH/OpenSkillsWhat 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 | $0.00048 | $0.01755 |
| Opus 5 | $0.00024 | $0.00877 |
| Sonnet 5 | $0.00010 | $0.00351 |
| Haiku 4.5 | $0.00005 | $0.00176 |
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 yesterday.
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 — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
System Design
Approach every system design task as a principal engineer who has operated distributed systems at scale and learned what breaks. You are not designing for the demo — you are designing for the 18-month horizon when the team has tripled, traffic has grown 10x, and the original author has left. Every structural decision must be justifiable, reversible where possible, and honest about its trade-offs.
Step 0: Frame Before You Draw
Before any diagram or component list, answer these:
- What is the system's single job? One sentence. If it does two things, it may be two systems.
- Who are the consumers? Internal services, external clients, third-party integrations — each has different trust and latency requirements.
- What are the scale targets? Requests per second, data volume, geographic distribution, SLA. Design to real numbers, not hypothetical extremes.
- What are the failure tolerance requirements? Which parts must never go down? Which can degrade gracefully?
- What are the consistency requirements? Strong consistency, eventual consistency, or something in between — this drives almost every storage and communication choice.
State these explicitly. A system designed without answers to these questions is a guess wearing an architecture diagram.
Monolith vs Microservices
Start with the question: does the complexity of distribution justify itself here?
Choose a monolith when:
- The team is small (fewer than 3 squads owning distinct domains)
- The domain boundaries are not yet understood
- Operational maturity is low — distributed systems require mature CI/CD, observability, and on-call practices
- Latency between components matters and network hops are expensive
Choose microservices when:
- Independent deployment of components has clear business value
- Teams need to scale independently — both in engineering headcount and compute
- Domain boundaries are stable and well-understood
- The organisation has the operational maturity to run and observe many services
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.
- yesterday First seen · 152 lines · 48 tokens per session scan A 79de82d7aa2a
system-design is a skill published in the GitHub repository CODE-SAURABH/OpenSkills (2 stars, last pushed 1mo ago), licensed MIT. It adds 48 tokens to every session and 1,755 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 2026-08-31.
Other skills, from other repositories
ecommerce-landing-page
Audit and optimize e-commerce landing pages for conversion. CTA placement, trust signals, page structure, copy optimization, and A/B testing strategy for product pages, collection pages, and campaign landing pages.
customer-feedback-analysis
AI-powered customer feedback and review sentiment analysis skill. Extracts pain points, feature requests, and improvement priorities from customer reviews across e-commerce platforms.
ads-linkedin
Audit LinkedIn Ads measurement, Insight Tag and conversions, professional audiences, lead generation, ABM, creative, bidding, budgets, pacing, automation, and policy. Use for LinkedIn Ads, Campaign Manager, Insight Tag, Lead Gen Forms, Thought Leader Ads, ABM campaigns, or B2B paid media.
ads-launch
Draft or explicitly apply a paid-ad campaign launch through Claude Ads capability-gated adapters. Use for campaign creation, launch plans, publishing ads, activating campaigns, uploading creative, or requests to push a campaign live.
api-response-optimization
Optimizes API performance through payload reduction, caching strategies, and compression techniques. Use when improving API response times, reducing bandwidth usage, or implementing efficient caching.
ctx-insight
Open the context-mode Insight dashboard in your default browser. Insight is the hosted analytics layer for AI-assisted engineering teams — per-engineer productive rate, retry waste, blocker detection, role-narrowed views. Trigger: /context-mode:ctx-insight.