Skip to content

Instantly share code, notes, and snippets.

@donbr
Created July 8, 2026 00:10
Show Gist options
  • Select an option

  • Save donbr/73d14fdac568c6f0f16f958d3da1f182 to your computer and use it in GitHub Desktop.

Select an option

Save donbr/73d14fdac568c6f0f16f958d3da1f182 to your computer and use it in GitHub Desktop.
Session 11 Cheat Sheet — Claude Code & the Claude Agent SDK

Session 11 Cheat Sheet — Claude Code & the Claude Agent SDK

A frame to help you reason through the assignment — concepts, diagrams, and the API map. It deliberately does not contain the answers or filled-in activity code. Instead it gives you the questions to ask yourself and the method to get there. The work — and the learning — is in building the app with Claude Code, reading the message stream, and writing your own conclusions.

Source: 11_Claude_Code/README.md (markdown-only session — no notebook; you write your Q1–Q4 answers directly in the README). Guides: 01_Installing…, 02_Using…, 03_Claude_Agent_SDK.md. Deliverable: your own chat-app/.

Quick Reference

You want to… Reach for One-liner
Start Claude Code in a project claude (CLI) Launches the agent loop in the current directory
Explore/scaffold before changing anything plan mode (Shift+Tab, or --permission-mode plan) Read-only recon; nothing executes until you approve
Give the agent durable project memory CLAUDE.md Auto-loaded into context at the start of every session
Trim / reset the context window /compact, /clear Manual context-budget control (the Session 3 middleware, by hand)
Run the SDK agent loop query(prompt=…, options=…) Returns an async stream of typed messages until done
Configure the agent ClaudeAgentOptions(…) allowed_tools · permission_mode · max_turns · cwd · resume · mcp_servers
Constrain what the agent can do allowed_tools=["Read","Glob","Grep"] A read-only allowlist = the server-side safety story
Read the loop's steps the message stream SystemMessage (init → session_id) · AssistantMessage · ResultMessage.result
Continue a conversation across messages resume=session_id Map each browser conversation_id → the SDK session_id
Add a custom tool @tool + create_sdk_mcp_server Wire via mcp_servers; allowlist as mcp__<server>__<tool>
Serve the agent to a browser FastAPI POST /api/chat The seam: one swappable function calls query()

Anchor: In the terminal, YOU are the permission gate. On a headless server there is no human to click "approve" — so the tool allowlist + permission mode ARE the gate. Safety comes from what the agent is allowed to do, not from trusting the input.

The Big Picture

flowchart LR
  subgraph Build["Build it WITH Claude Code (plan → implement → verify)"]
    You[You] -->|plan mode| CC[Claude Code]
    CC -->|scaffold| Skel[chat-app skeleton\nFastAPI + echo stub + CLAUDE.md]
  end
  subgraph Run["Run the agent BEHIND the app"]
    Browser[Browser chat UI] -->|fetch /api/chat| API[FastAPI /api/chat]
    API -->|query&#40;&#41;| SDK[Agent SDK loop]
    SDK --> Tools[Read / Glob / Grep + your custom tool]
    Tools --> SDK
    SDK -->|ResultMessage.result| API --> Browser
  end
  Skel -.->|replace the echo seam| API
Loading

ASCII fallback:

BUILD (with Claude Code):   you ─plan mode─► Claude Code ─► chat-app skeleton (echo stub + CLAUDE.md)
                                                                    │  replace the seam
                                                                    v
RUN (agent behind the app): browser ─fetch─► /api/chat ─query()─► Agent SDK loop ─► Read/Glob/Grep + custom tool
                                                  ▲                                          │
                                                  └────────────  ResultMessage.result  ◄─────┘

Why this shape? Two breakout rooms, one arc. First you build the app with Claude Code (the agent as your pair-programmer, gated by plan mode). Then you put an agent inside the app — the same loop that powers Claude Code, embedded via query(). The load-bearing design fact: the chat logic lives in one swappable function; /api/chat is the seam where the echo stub becomes a real agent.

Setup & roles

# Install Claude Code (pick one): native installer | brew install claude | winget | npm i -g @anthropic-ai/claude-code
claude            # first run → authenticate

# The chat app (built with Claude Code):
uv init chat-app && cd chat-app       # Python 3.12+, uv
uv add fastapi uvicorn claude-agent-sdk
export ANTHROPIC_API_KEY=...          # server-side only; STRIP before committing
uv run uvicorn app:app --reload       # serves http://localhost:8000
Component Role
Claude Code The builder — scaffolds + extends the app; you gate it with plan/permission modes
CLAUDE.md Curated project memory, auto-loaded every session
FastAPI /api/chat The server seam — one swappable function that calls the agent
Agent SDK query() The runtime — the agent loop embedded in your app
Tools Read/Glob/Grep (read-only built-ins) + ≥1 custom @tool

Core concepts

1. The permission system & plan mode

Claude Code runs real side-effecting tools (Bash/Edit/Write) and picks the next tool itself — so every action can change the world irreversibly. The permission system (default / acceptEdits / plan / bypassPermissions) is the human-in-the-loop gate. Plan mode is read-only: propose-before-act. Docs: https://code.claude.com/docs

2. CLAUDE.md as project memory

Auto-loaded into context every session → high value per line. Belongs: the run/test commands, the /api/chat seam, conventions, gotchas. Not: code-discoverable detail, transient state, secrets. It's the long-term-memory half of Session 3's finite-context discipline (/compact·/clear are the S3 summarization middleware, by hand).

3. The query() loop

from claude_agent_sdk import query, ClaudeAgentOptions
async for message in query(prompt="…", options=ClaudeAgentOptions(allowed_tools=["Read","Glob","Grep"])):
    ...   # the whole loop (call → tool → feed result back → repeat) in one call

Docs: https://docs.anthropic.com/en/api/agent-sdk/overview

4. The typed message stream

SystemMessage (init — carries session_id) · AssistantMessage (text + tool-use blocks) · UserMessage (tool results) · ResultMessage (.result + usage). This anatomy is what makes progress-streaming and grounded answers possible.

5. Wiring /api/chat (the seam)

POST /api/chat accepts {message, conversation_id}{reply}. The stub calls query() and returns ResultMessage.result. Read-only allowed_tools + permission_mode + max_turns are the server-side gate.

6. Conversation memory (resume=)

Each query() is a fresh conversation unless you resume it. Capture session_id from the init SystemMessage; keep a conversation_id → session_id dict; pass resume=session_id so follow-ups carry context.

7. Custom tools (@tool + SDK MCP server)

from claude_agent_sdk import tool, create_sdk_mcp_server
@tool("count_lines", "Count lines in a file", {"file_path": str})
async def count_lines(args): ...
server = create_sdk_mcp_server(name="concierge", version="1.0.0", tools=[count_lines])
# options: mcp_servers={"concierge": server}, allowed_tools=[..., "mcp__concierge__count_lines"]

8. The read-only allowlist = the safety story

On a server there's no human approver. allowed_tools=["Read","Glob","Grep"] means the agent structurally cannot modify the filesystem, no matter what a user types (prompt injection included). The allowlist is safety, not performance. max_turns caps runaway loops/cost.


Questions — think it through (write your own answers in the README)

These are the four questions you answer in the README. Below is the method and the questions to ask yourself — not the answers. Reason from the guides and your own build.

Q1 — Why does an agent that runs shell commands need a permission system, and why is plan mode valuable from an empty directory?

Ask yourself: what is the difference between a chat model that gets something wrong and an agent that gets something wrong? What could a tool like Bash or Edit actually do? When you started from an empty folder, what did plan mode let you see before anything ran — and why does "empty folder" raise the stakes versus editing an existing repo? (Revisit Guide 2's "Permission Modes".)

Q2 — What belongs in CLAUDE.md (and what doesn't); how does it relate to Session 3?

Ask yourself: this file is re-read at the start of every session — so what earns a permanent seat, and what's cheaper to let the agent rediscover? What would be actively dangerous to put here? Then connect it to Session 3: what did you learn about the context window as a budget, and which S3 tool do /compact and /clear echo?

Q3 — Agent SDK loop vs the LangGraph loops you hand-built in Sessions 2–4?

Ask yourself: list what you had to wire by hand in LangGraph that query() now hands you for free. Then flip it — name something you could do in a hand-built graph that the fixed SDK loop won't let you do. Is this a strict upgrade, or a trade? For a read-and-answer concierge, which side of the trade matters?

Q4 — Why route through query() vs a raw chat completion; what new risk, and how did your controls address it?

Ask yourself: what can the agent do that a plain chat completion can't? Now the flip side — those same tools are driven by whatever a stranger types into your chat box, and no human is at the server to approve. What could go wrong? Look at your own allowed_tools and permission_mode: what do they make impossible, regardless of the input? (Guide 3's "Why these controls matter (Question #4)" is your anchor.)

Activities — the deliverable + how to check yourself (no solution code)

Main build (Tasks 3–8) — the codebase concierge

Build a FastAPI app where POST /api/chat routes each message through the Agent SDK query(), configured with a read-only allowed_tools=["Read","Glob","Grep"] allowlist; add conversation memory (map conversation_id → SDK session_id, pass resume=) and at least one custom tool. Build it with Claude Code — plan → implement → verify. Check yourself: Does the chat answer real questions about a repo, and do the answers actually reflect the files (not a guess)? Ask a follow-up ("what are its dependencies?") — does context carry? Force your custom tool with a targeted question — does it fire? Is your key ever visible in the browser? Does chat-app/CLAUDE.md name the seam?

Activity #1 — Level Up the Chat App (do at least ONE)

Pick one: (a) live progress streaming (SSE) so users see tool calls instead of a spinner; (b) a multi-conversation sidebar, each thread its own SDK session; (c) a second custom tool useful for your target repo. Demo it in your Loom and explain the design decision in one paragraph. Check yourself: does the enhancement visibly work in your demo, and can you justify why you chose it? (Any one, working, is enough.)

Advanced Activity — Cat Shop Concierge (optional / UNSCORED)

If you're curious: connect your Session 8 cat-shop MCP server to your chat app via the SDK's mcp_servers option, so users can browse/cart/checkout in natural language. It's unscored — no bonus, no penalty — pure exploration; share findings + a demo in your Loom if you try it.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment