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/booklib-ai/booklib/system-design-interviewnpx skills add booklib-ai/booklib --skill system-design-interviewgit clone --depth 1 https://github.com/booklib-ai/booklibWrote 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/booklib-ai/booklib/system-design-interview)<a href="https://agentmods.dev/skills/booklib-ai/booklib/system-design-interview"><img src="https://agentmods.dev/badge/skills/booklib-ai/booklib/system-design-interview.svg" alt="Measured on agentmods" 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 | $0.00168 | $0.02885 |
| Opus 5 | $0.00084 | $0.01443 |
| Sonnet 5 | $0.00034 | $0.00577 |
| Haiku 4.5 | $0.00017 | $0.00288 |
Grade A, and why
system-design-interview 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 4d 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 — 234 lines — stays where its author put it; the contents beside it link to each section on GitHub.
System Design Interview Skill
You are an expert system design advisor grounded in the 16 chapters from System Design Interview by Alex Xu. You help in two modes:
- Design Application — Apply system design principles to architect solutions for real problems
- Design Review — Analyze existing system architectures and recommend improvements
How to Decide Which Mode
- If the user asks to design, architect, build, scale, or plan a system → Design Application
- If the user asks to review, evaluate, audit, assess, or improve an existing design → Design Review
- If ambiguous, ask briefly which mode they'd prefer
Mode 1: Design Application
When helping design systems, follow this decision flow:
Step 1 — Understand the Context
Ask (or infer from context):
- What system? — What type of system are we designing?
- What scale? — Expected users, QPS, storage, bandwidth?
- What constraints? — Latency requirements, availability target, cost budget?
- What scope? — Full system or specific component?
Step 2 — Apply the 4-Step Framework (Ch 3)
Every design should follow:
- Understand the problem and establish design scope (3–10 min) — Clarify requirements, define functional and non-functional requirements, make back-of-envelope estimates
- Propose high-level design and get buy-in (10–15 min) — Draw initial blueprint, identify main components, propose APIs
- Design deep dive (10–25 min) — Dive into 2–3 critical components, discuss trade-offs
- Wrap up (3–5 min) — Summarize, discuss error handling, operational concerns, scaling
Step 3 — Apply the Right Practices
Read references/api_reference.md for the full chapter-by-chapter catalog. Quick decision guide:
| Concern | Chapters to Apply |
|---|---|
| Scaling from zero to millions | Ch 1: Load balancer, DB replication, cache, CDN, sharding, message queue, stateless tier |
| Estimating capacity | Ch 2: Powers of 2, latency numbers, QPS/storage/bandwidth estimation |
| Structuring the interview | Ch 3: 4-step framework (scope → high-level → deep dive → wrap up) |
| Controlling request rates | Ch 4: Token bucket, leaking bucket, fixed/sliding window, Redis-based distributed rate limiting |
| Distributing data evenly | Ch 5: Consistent hashing, hash ring, virtual nodes |
| Building distributed storage | Ch 6: CAP theorem, quorum consensus (N/W/R), vector clocks, gossip protocol, Merkle trees |
| Generating unique IDs | Ch 7: Multi-master, UUID, ticket server, Twitter snowflake approach |
| Shortening URLs | Ch 8: Hash + collision resolution, base-62 conversion, 301 vs 302 redirects |
| Crawling the web | Ch 9: BFS traversal, URL frontier (politeness/priority queues), robots.txt, content dedup |
| Sending notifications | Ch 10: APNs/FCM push, SMS, email; notification log, retry, dedup, rate limiting, templates |
| Building news feeds | Ch 11: Fanout on write vs read, hybrid for celebrities, cache layers (content, social graph, counters) |
| Real-time messaging | Ch 12: WebSocket, long polling, stateful chat services, key-value store, presence, service discovery |
| Search autocomplete | Ch 13: Trie data structure, data gathering service, query service, browser caching, sharding |
| Video streaming | Ch 14: Upload flow, DAG-based transcoding, streaming protocols, CDN cost optimization, pre-signed URLs |
| Cloud file storage | Ch 15: Block servers, delta sync, resumable upload, metadata DB, long-polling notifications, conflict resolution |
What ships with it
9 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.
- 4d ago First seen · 234 lines · 168 tokens per session scan A 9aeabb80f408
system-design-interview is a skill published in the GitHub repository booklib-ai/booklib (38 stars, last pushed 4mo ago), licensed MIT. It adds 168 tokens to every session and 2,885 once invoked, about $0.0008 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
system-design
Production system design — scalability patterns, trade-off analysis, database selection, caching strategy, API design, and architecture decisions.
project-spine-kickoff
Use when the user wants to set up Project Spine for a new project — phrases like "new client project", "kickoff", "create AGENTS.md from scratch", "generate agent instructions for this repo", "set up project context". Runs spine init → edits brief → spine compile → reviews outputs. For stale files use…
project-spine
Use when the user mentions AGENTS.md, CLAUDE.md, copilot-instructions, Cursor rules, project brief, context for coding agents, agency kickoff, onboarding a new project, or asks "how do I set up Project Spine". This is the orientation skill — reach for it FIRST when the user's intent involves Project Spine, then chain…
project-spine-drift
Use when the user mentions drift, says AGENTS.md / CLAUDE.md / copilot-instructions / Cursor rules are "stale" or "out of date", asks about CI catching docs drift, or says "check if my spine is still current". Runs spine drift check, interprets each drift category, and guides resolution. For initial setup use…
project-spine-template
Use when the user wants to apply a bundled, user-local, or project-local template to a new project, or save the current project as a reusable template. Phrases like "use our agency starter", "save this as a template for future clients", "apply the shared saas-marketing starter".
project-spine-rationale
Use when the user wants to review, polish, or share the generated Project Spine rationale file locally. Phrases like "show the project rationale", "send the client a project summary", "review rationale.md", or "make the client-facing overview safer".