Learn Claude Code

Learning Path

s01 to s17: Progressive Agent Harness Design

Layer Legend

Tools & Execution
Planning & Control
Memory Management
Concurrency & Scheduling
Multi-Agent Platform
01
s01Minimal model/tool loop

The Agent LoopOne Loop Is All You Need

115 lines of code1 tools

“The smallest useful agent is a loop that calls the model, runs tools, and feeds results back.”

Learn More
02
s02Tool dispatch map

Tool UseAdd a Tool, Add Just One Line

158 lines of code5 tools

“The loop stays stable while capabilities register into a dispatch table.”

Learn More
03
s03Permission gate

PermissionCheck Permissions Before Execution

201 lines of code5 tools

“Dangerous actions need a harness decision point before the shell runs.”

Learn More
04
s04Lifecycle hooks

HooksHang on the Loop, Don't Write into It

224 lines of code5 tools

“Cross-cutting behavior belongs around the loop, not tangled inside it.”

Learn More
05
s05Todo manager

TodoWriteAn Agent Without a Plan Drifts Off Course

297 lines of code6 tools

“Explicit plans keep long-running work visible and correctable.”

Learn More
06
s06Isolated subtask context

SubagentBreak Large Tasks into Small Ones with Clean Context

304 lines of code6 tools

“Subagents give each subtask a clean message history while preserving the main thread.”

Learn More
07
s07On-demand skill loader

Skill LoadingLoad Only When Needed

320 lines of code6 tools

“Inject specialized knowledge only when the task actually needs it.”

Learn More
08
s08Context compaction

Context CompactContext Will Fill Up

517 lines of code5 tools

“Compression keeps the conversation usable when the context window gets crowded.”

Learn More
09
s09Durable memory layer

MemoryKeep a Layer That Doesn't Lose Details

692 lines of code5 tools

“Some facts should survive summarization and future sessions.”

Learn More
10
s10Task board

Task SystemBreak Big Goals into Small Tasks

479 lines of code11 tools

“A task graph turns vague goals into ordered, observable work.”

Learn More
11
s11Background execution

Background TasksSlow Operations Go to the Background

437 lines of code5 tools

“The agent can keep reasoning while slow work completes elsewhere.”

Learn More
12
s12Scheduled task creation

Cron SchedulerProducing Work on a Schedule

657 lines of code5 tools

“Recurring work should be created by the harness, not remembered by the model.”

Learn More
13
s13Team runtime with task-bound worktrees

Agent Team RuntimePersistent Teammates, Atomic Claims, Task-Bound Worktrees

1605 lines of code5 tools

“Persistent teammates can reliably discover and execute parallel work when the runtime owns messaging, atomic claims, and task-bound working directories.”

Learn More
14
s14MCP tool bridge

MCP ToolsExternal Tools, Standard Protocol

458 lines of code5 tools

“External services can become agent tools through a standard discovery and call protocol.”

Learn More
15
s15Integrated harness

Integrated HarnessMany Mechanisms, One Loop

2800 lines of code26 tools

“The integrated harness is still one loop, surrounded by the systems introduced across the course.”

Learn More
16
s16Resumable workflow runtime

Workflow RuntimeScripts Own Fixed Orchestration

732 lines of code27 tools

“When orchestration has a fixed shape, code can make it parallel, deterministic, and resumable.”

Learn More
17
s17Goal completion gate

Goal LoopIndependent Evaluation Decides When to Stop

809 lines of code5 tools

“A durable goal keeps the loop working until an independent evaluator finds the completion condition satisfied in the conversation.”

Learn More

LOC Growth

s01
115
s02
158
s03
201
s04
224
s05
297
s06
304
s07
320
s08
517
s09
692
s10
479
s11
437
s12
657
s13
1605
s14
458
s15
2800
s16
732
s17
809