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/wewpellex21/code-sensei/architecturenpx skills add wewpellex21/code-sensei --skill architecturegit clone --depth 1 https://github.com/wewpellex21/code-senseiWhat 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 | $0.00026 | $0.00591 |
| Opus 5 | $0.00013 | $0.00296 |
| Sonnet 5 | $0.00005 | $0.00118 |
| Haiku 4.5 | $0.00003 | $0.00059 |
Grade A, and why
architecture 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 2d 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.
This is a copy
100% identical to architecture — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architecture — CodeSensei Teaching Module
What is Architecture?
- Analogy: Architecture is the floor plan of your application. Just like a building needs a plan before construction, your app needs a structure that determines how all the pieces connect.
- Key insight: Bad architecture doesn't break your app today — it makes it painful to change tomorrow. Good architecture makes change easy.
Client-Server Architecture
- The pattern: Frontend (client) ↔ API ↔ Backend (server) ↔ Database
- Why this split: Separation of concerns. The frontend handles display, the backend handles logic and data. They can change independently.
- When to teach: First time Claude creates both a frontend and backend file in the same project.
Monolith vs Microservices
- Monolith: Everything in one codebase. Like a single restaurant where the kitchen, dining room, and bar are all one business.
- Microservices: Each feature is its own mini-app. Like a food court where each stall is independent.
- Key insight for vibecoders: Start monolith. Always. Microservices are for when you have scaling problems, not before.
MVC Pattern
- Model — the data layer (what your app knows)
- View — the display layer (what the user sees)
- Controller — the logic layer (what happens when the user does something)
- Analogy: A restaurant. The menu (model) has the dishes. The table presentation (view) is what the customer sees. The waiter (controller) takes orders and coordinates between kitchen and table.
State Management
- The problem: As your app grows, keeping track of data that multiple components need becomes messy.
- Analogy: In a small office, everyone shouts across the room. In a big company, you need an organized messaging system (Slack, email).
- Solutions: React Context, Redux, Zustand — all solve the same problem differently.
Caching
- Analogy: Instead of cooking every meal from scratch, you prep common ingredients in advance. Caching stores frequently-used data closer to where it's needed so you don't have to fetch it every time.
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.
- 2d ago First seen · 46 lines · 26 tokens per session scan A 1f68150221ab
architecture is a skill published in the GitHub repository wewpellex21/code-sensei (3 stars, last pushed 4d ago), licensed MIT. It adds 26 tokens to every session and 591 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to architecture, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
agent-squad-python
Use when building or modifying a Python app that uses the agent-squad Python package — async multi-agent orchestration for Python 3.11+: orchestrator, agents (BedrockLLMAgent, AnthropicAgent, OpenAIAgent, SupervisorAgent, GroundedAgent, ChainAgent, and more), classifier routing (Bedrock, Anthropic, OpenAI), storage…
agent-squad-swift
Use when building or modifying a Swift app that uses the AgentSquad Swift framework — on-device multi-agent orchestration for iOS 16+ / macOS 14+: orchestrator, agents (Agent, GroundedAgent), classifier routing, LLM clients (OpenAI-compatible), tools (native + MCP), tool UIs/widgets, on-device storage, tracing, and…
agent-squad-typescript
Use when building or modifying a Node.js / TypeScript app that uses the agent-squad npm package — multi-agent orchestration: orchestrator, agents (all built-in types + GroundedAgent), classifier routing (Bedrock / Anthropic / OpenAI), storage (in-memory / DynamoDB / SQL), retrievers (Amazon KB / Dakera), and tools…
verify-pr
Comprehensive PR readiness check before merge. Run quality checks, tests, CI, documentation, AWS resource cleanup, and code review.
run-integ
Run integration tests (deploy + destroy) against real AWS. Use when you need to verify cdkd works end-to-end with actual AWS resources.
review-pr
Recommend the right reviewer count for a PR based on size + bias factors. Outputs a concrete plan (inline spot-check / 1 reviewer / 3-axis parallel) plus ready-to-paste Agent dispatch prompts when reviewers are warranted.