contradictory-body/cc-sensei

*Inject every ounce of Claude Code's architectural wisdom into your AI's brain*
English | 中文
---
Sound familiar?
> 😩 **"I've already dug deep into Claude Code's source, but when I ask my AI to help me build an Agent, it has no idea what I'm talking about — what I read, it didn't."**
> 😫 **"I'd love to build a knowledge base so my AI can learn from Claude Code, but the moment I open it — 300K+ lines, 1,250 files — both my AI and I are scared off."**
> 😵 **"I've barely looked at Claude Code's source, but I still want an Agent just as powerful — where do I even begin?"**
If any of these hit home — **this project is built for you.**
---
What it does for you
**Agent Architecture Oracle distills Claude Code's 310K lines of source and 1,250 files into 32 core modules with 40K lines of structured analysis, and serves it directly to your AI through the MCP protocol.**
It covers every core capability of Claude Code:
> 🔁 Agent main loop · 🛠️ Tool system & execution pipeline · 🛡️ Permissions & security sandbox · 🌊 Model API & streaming
> 🧠 Context engineering & compaction · 📂 File / Shell / Git tools · 🔌 MCP protocol · 🎨 Ink rendering engine · 🧩 Skills/plugins
> 💾 Persistent memory · ⚡ Prompt cache break detection · 🤖 Sub-agents & task system … (22 core + 10 deep-dive supplements)
It establishes a complete index pipeline: **natural language → module → design decision → reusable pattern → corresponding source code**:
After plugging it into Claude Desktop / Cursor / Qoder / your own Agent, **your AI gains a "Chief Architect of Claude Code" as its consultant** — whether you're cloning the whole thing or just stealing one design, it tells you exactly **where to look, why it works, and how to copy it.**
In one night, your AI becomes a world-class Agent architect.
---
🚀 Quick Start (3 steps)
Option A — Try instantly via npx (zero install)
> This downloads and runs the server directly. Skip to Step 3 to connect your AI.
Option B — Clone for full control
Step 1 — Clone the project
Step 2 — Install and build
Copy-paste again:
> 💡 Don't have pnpm? Run npm install -g pnpm first.
> 💡 This step parses 32 module analyses, generates the knowledge index, and compiles the server. **One-time only.**
When done, you should see: ✅ module-registry.json (32 modules) and ✅ Build success.
Step 3 — Connect your AI
Add this snippet to your MCP client's configuration file (**replace the path with the one you just cloned to**):
Don't know where the config file is? Common locations:
| Client | Config file path |
|---|---|
| **Claude Desktop (macOS)** | ~/Library/Application Support/Claude/claude_desktop_config.json |
| **Claude Desktop (Windows)** | %APPDATA%\Claude\claude_desktop_config.json |
| **Cursor** | Settings → MCP → Add new server |
| **Qoder** | Settings → MCP → Edit mcpServers |
**Restart your client. Done!** Your AI just gained 6 new skills.
🎯 Try it out
Just say to your AI:
> *"Use cc-sensei to tell me how Claude Code optimizes prompt cache."*
It will call the tools on its own and return a complete analysis with source-code references. **That's it.**
---
Dive deeper
🛠️ What the 6 tools do
| Tool | One-line capability | When to use |
|---|---|---|
| **list_modules** | List all 32 modules and their concerns | "Which modules does Claude Code break down into?" |