Architectural Layers
Five orthogonal concerns that compose into a complete agent
L1 Tools & Execution
What the agent CAN do. The foundation: tools give the model capabilities to interact with the world.
L2 Planning & Coordination
How work is organized. From simple todo lists to dependency-aware task boards shared across agents.
TodoWrite
先规划再执行
An agent without a plan drifts; list the steps first, then execute
![s04planningSubagents每个子任务干净上下文188 LOC5 toolsSubagents use independent messages[], keeping the main conversation clean](/dev/agentharness/auto-6.png/s04/){kind=link}
Subagents
每个子任务干净上下文
Subagents use independent messages[], keeping the main conversation clean
Skills
按需加载
Inject knowledge via tool_result when needed, not upfront in the system prompt
Tasks
任务图 + 依赖
A file-based task graph with ordering, parallelism, and dependencies -- the coordination backbone for multi-agent work
L3 Memory Management
Keeping context within limits. Compression strategies that let agents work infinitely without losing coherence.
L4 Concurrency
Non-blocking execution. Background threads and notification buses for parallel work.
L5 Collaboration
Multi-agent coordination. Teams, messaging, and autonomous teammates that think for themselves.
Agent Teams
队友 + 邮箱
When one agent can't finish, delegate to persistent teammates via async mailboxes
Team Protocols
共享通信规则
One request-response pattern drives all team negotiation
Autonomous Agents
扫描任务板，认领任务
Teammates scan the board and claim tasks themselves; no need for the lead to assign each one
Worktree + Task Isolation
按目录隔离
Each works in its own directory; tasks manage goals, worktrees manage directories, bound by ID