THE AGENT PATTERN ================= User --> messages[] --> LLM --> response | stop_reason == "tool_use"? / \ yes no | | execute tools return text append results loop back -----------------> messages[] That's the minimal loop. Every AI coding agent needs this loop. Production agents add policy, permissions, and lifecycle layers.
12 progressive sessions, from a simple loop to isolated autonomous execution. Each session adds one mechanism. Each mechanism has one motto.
s01 "One loop & Bash is all you need" — one tool + one loop = an agent
s02 "Adding a tool means adding one handler" — the loop stays the same; new tools register into the dispatch map
s03 "An agent without a plan drifts" — list the steps first, then execute; completion doubles
s04 "Break big tasks down; each subtask gets a clean context" — subagents use independent messages[], keeping the main conversation clean
s05 "Load knowledge when you need it, not upfront" — inject via tool_result, not the system prompt
s06 "Context will fill up; you need a way to make room" — three-layer compression strategy for infinite sessions
s07 "Break big goals into small tasks, order them, persist to disk" — a file-based task graph with dependencies, laying the foundation for multi-agent collaboration
s08 "Run slow operations in the background; the agent keeps thinking" — daemon threads run commands, inject notifications on completion
s09 "When the task is too big for one, delegate to teammates" — persistent teammates + async mailboxes
s10 "Teammates need shared communication rules" — one request-response pattern drives all negotiation
s11 "Teammates scan the board and claim tasks themselves" — no need for the lead to assign each one
s12 "Each works in its own directory, no interference" — tasks manage goals, worktrees manage directories, bound by ID
def agent_loop(messages):
while True:
response = client.messages.create(
model=MODEL, system=SYSTEM,
messages=messages, tools=TOOLS,
)
messages.append({"role": "assistant",
"content": response.content})
if response.stop_reason != "tool_use":
return
results = []
for block in response.content:
if block.type == "tool_use":
output = TOOL_HANDLERS[block.name](**block.input)
results.append({
"type": "tool_result",
"tool_use_id": block.id,
"content": output,
})
messages.append({"role": "user", "content": results})
Every session layers one mechanism on top of this loop -- without changing the loop itself.
This repository is a 0->1 learning project for building a nano Claude Code-like agent. It intentionally simplifies or omits several production mechanisms:
- Full event/hook buses (for example PreToolUse, SessionStart/End, ConfigChange).
s12 includes only a minimal append-only lifecycle event stream for teaching. - Rule-based permission governance and trust workflows
- Session lifecycle controls (resume/fork) and advanced worktree lifecycle controls
- Full MCP runtime details (transport/OAuth/resource subscribe/polling)
Treat the team JSONL mailbox protocol in this repo as a teaching implementation, not a claim about any specific production internals.
git clone https://github.com/shareAI-lab/learn-claude-code
cd learn-claude-code
pip install -r requirements.txt
cp .env.example .env # Edit .env with your ANTHROPIC_API_KEY
python agents/s01_agent_loop.py # Start here
python agents/s12_worktree_task_isolation.py # Full progression endpoint
python agents/s_full.py # Capstone: all mechanisms combined
Interactive visualizations, step-through diagrams, source viewer, and documentation.
cd web && npm install && npm run dev # http://localhost:3000
Phase 1: THE LOOP Phase 2: PLANNING & KNOWLEDGE ================== ============================== s01 The Agent Loop [1] s03 TodoWrite [5] while + stop_reason TodoManager + nag reminder | | +-> s02 Tool Use [4] s04 Subagents [5] dispatch map: name->handler fresh messages[] per child | s05 Skills [5] SKILL.md via tool_result | s06 Context Compact [5] 3-layer compression Phase 3: PERSISTENCE Phase 4: TEAMS ================== ===================== s07 Tasks [8] s09 Agent Teams [9] file-based CRUD + deps graph teammates + JSONL mailboxes | | s08 Background Tasks [6] s10 Team Protocols [12] daemon threads + notify queue shutdown + plan approval FSM | s11 Autonomous Agents [14] idle cycle + auto-claim | s12 Worktree Isolation [16] task coordination + optional isolated execution lanes [N] = number of tools
learn-claude-code/ | |-- agents/ # Python reference implementations (s01-s12 + s_full capstone) |-- docs/{en,zh,ja}/ # Mental-model-first documentation (3 languages) |-- web/ # Interactive learning platform (Next.js) |-- skills/ # Skill files for s05 +-- .github/workflows/ci.yml # CI: typecheck + build
Mental-model-first: problem, solution, ASCII diagram, minimal code. Available in English | 中文 | 日本語.
| Session | Topic | Motto |
|---|---|---|
| s01 | The Agent Loop | One loop & Bash is all you need |
| s02 | Tool Use | Adding a tool means adding one handler |
| s03 | TodoWrite | An agent without a plan drifts |
| s04 | Subagents | Break big tasks down; each subtask gets a clean context |
| s05 | Skills | Load knowledge when you need it, not upfront |
| s06 | Context Compact | Context will fill up; you need a way to make room |
| s07 | Tasks | Break big goals into small tasks, order them, persist to disk |
| s08 | Background Tasks | Run slow operations in the background; the agent keeps thinking |
| s09 | Agent Teams | When the task is too big for one, delegate to teammates |
| s10 | Team Protocols | Teammates need shared communication rules |
| s11 | Autonomous Agents | Teammates scan the board and claim tasks themselves |
| s12 | Worktree + Task Isolation | Each works in its own directory, no interference |
After the 12 sessions you understand how an agent works inside out. Two ways to put that knowledge to work:
npm i -g @shareai-lab/kode
Skill & LSP support, Windows-ready, pluggable with GLM / MiniMax / DeepSeek and other open models. Install and go.
GitHub: shareAI-lab/Kode-cli
The official Claude Code Agent SDK communicates with a full CLI process under the hood -- each concurrent user means a separate terminal process. Kode SDK is a standalone library with no per-user process overhead, embeddable in backends, browser extensions, embedded devices, or any runtime.
GitHub: shareAI-lab/Kode-agent-sdk
The agent this repo teaches is use-and-discard -- open a terminal, give it a task, close when done, next session starts blank. That is the Claude Code model.
OpenClaw proved another possibility: on top of the same agent core, two mechanisms turn the agent from "poke it to make it move" into "it wakes up every 30 seconds to look for work":
- Heartbeat -- every 30s the system sends the agent a message to check if there is anything to do. Nothing? Go back to sleep. Something? Act immediately.
- Cron -- the agent can schedule its own future tasks, executed automatically when the time comes.
Add multi-channel IM routing (WhatsApp / Telegram / Slack / Discord, 13+ platforms), persistent context memory, and a Soul personality system, and the agent goes from a disposable tool to an always-on personal AI assistant.
claw0 is our companion teaching repo that deconstructs these mechanisms from scratch:
claw agent = agent core + heartbeat + cron + IM chat + memory + soul
learn-claude-code claw0 (agent runtime core: (proactive always-on assistant: loop, tools, planning, heartbeat, cron, IM channels, teams, worktree isolation) memory, soul personality)
MIT
The model is the agent. Our job is to give it tools and stay out of the way.
