|
26 | 26 |
|
27 | 27 | > **s01** *"One loop & Bash is all you need"* — one tool + one loop = an agent |
28 | 28 | > |
29 | | -> **s02** *"The loop didn't change"* — adding tools means adding handlers, not rewriting the loop |
| 29 | +> **s02** *"Adding a tool means adding one handler"* — the loop stays the same; new tools register into the dispatch map |
30 | 30 | > |
31 | | -> **s03** *"Plan before you act"* — visible plans improve task completion |
| 31 | +> **s03** *"An agent without a plan drifts"* — list the steps first, then execute; completion doubles |
32 | 32 | > |
33 | | -> **s04** *"Process isolation = context isolation"* — fresh messages[] per subagent |
| 33 | +> **s04** *"Break big tasks down; each subtask gets a clean context"* — subagents use independent messages[], keeping the main conversation clean |
34 | 34 | > |
35 | | -> **s05** *"Load on demand, not upfront"* — inject knowledge via tool_result, not system prompt |
| 35 | +> **s05** *"Load knowledge when you need it, not upfront"* — inject via tool_result, not the system prompt |
36 | 36 | > |
37 | | -> **s06** *"Strategic forgetting"* — forget old context to enable infinite sessions |
| 37 | +> **s06** *"Context will fill up; you need a way to make room"* — three-layer compression strategy for infinite sessions |
38 | 38 | > |
39 | | -> **s07** *"State survives /compact"* — file-based state outlives context compression |
| 39 | +> **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 |
40 | 40 | > |
41 | | -> **s08** *"Fire and forget"* — non-blocking threads + notification queue |
| 41 | +> **s08** *"Run slow operations in the background; the agent keeps thinking"* — daemon threads run commands, inject notifications on completion |
42 | 42 | > |
43 | | -> **s09** *"Append to send, drain to read"* — async mailboxes for persistent teammates |
| 43 | +> **s09** *"When the task is too big for one, delegate to teammates"* — persistent teammates + async mailboxes |
44 | 44 | > |
45 | | -> **s10** *"Same request_id, two protocols"* — one FSM pattern powers shutdown + plan approval |
| 45 | +> **s10** *"Teammates need shared communication rules"* — one request-response pattern drives all negotiation |
46 | 46 | > |
47 | | -> **s11** *"Poll, claim, work, repeat"* — no coordinator needed, agents self-organize |
| 47 | +> **s11** *"Teammates scan the board and claim tasks themselves"* — no need for the lead to assign each one |
48 | 48 | > |
49 | | -> **s12** *"Isolate by directory, coordinate by task ID"* — task board + optional worktree lanes |
| 49 | +> **s12** *"Each works in its own directory, no interference"* — tasks manage goals, worktrees manage directories, bound by ID |
50 | 50 |
|
51 | 51 | --- |
52 | 52 |
|
@@ -167,17 +167,17 @@ Available in [English](./docs/en/) | [中文](./docs/zh/) | [日本語](./docs/j |
167 | 167 | | Session | Topic | Motto | |
168 | 168 | |---------|-------|-------| |
169 | 169 | | [s01](./docs/en/s01-the-agent-loop.md) | The Agent Loop | *One loop & Bash is all you need* | |
170 | | -| [s02](./docs/en/s02-tool-use.md) | Tool Use | *The loop didn't change* | |
171 | | -| [s03](./docs/en/s03-todo-write.md) | TodoWrite | *Plan before you act* | |
172 | | -| [s04](./docs/en/s04-subagent.md) | Subagents | *Process isolation = context isolation* | |
173 | | -| [s05](./docs/en/s05-skill-loading.md) | Skills | *Load on demand, not upfront* | |
174 | | -| [s06](./docs/en/s06-context-compact.md) | Context Compact | *Strategic forgetting* | |
175 | | -| [s07](./docs/en/s07-task-system.md) | Tasks | *State survives /compact* | |
176 | | -| [s08](./docs/en/s08-background-tasks.md) | Background Tasks | *Fire and forget* | |
177 | | -| [s09](./docs/en/s09-agent-teams.md) | Agent Teams | *Append to send, drain to read* | |
178 | | -| [s10](./docs/en/s10-team-protocols.md) | Team Protocols | *Same request_id, two protocols* | |
179 | | -| [s11](./docs/en/s11-autonomous-agents.md) | Autonomous Agents | *Poll, claim, work, repeat* | |
180 | | -| [s12](./docs/en/s12-worktree-task-isolation.md) | Worktree + Task Isolation | *Isolate by directory, coordinate by task ID* | |
| 170 | +| [s02](./docs/en/s02-tool-use.md) | Tool Use | *Adding a tool means adding one handler* | |
| 171 | +| [s03](./docs/en/s03-todo-write.md) | TodoWrite | *An agent without a plan drifts* | |
| 172 | +| [s04](./docs/en/s04-subagent.md) | Subagents | *Break big tasks down; each subtask gets a clean context* | |
| 173 | +| [s05](./docs/en/s05-skill-loading.md) | Skills | *Load knowledge when you need it, not upfront* | |
| 174 | +| [s06](./docs/en/s06-context-compact.md) | Context Compact | *Context will fill up; you need a way to make room* | |
| 175 | +| [s07](./docs/en/s07-task-system.md) | Tasks | *Break big goals into small tasks, order them, persist to disk* | |
| 176 | +| [s08](./docs/en/s08-background-tasks.md) | Background Tasks | *Run slow operations in the background; the agent keeps thinking* | |
| 177 | +| [s09](./docs/en/s09-agent-teams.md) | Agent Teams | *When the task is too big for one, delegate to teammates* | |
| 178 | +| [s10](./docs/en/s10-team-protocols.md) | Team Protocols | *Teammates need shared communication rules* | |
| 179 | +| [s11](./docs/en/s11-autonomous-agents.md) | Autonomous Agents | *Teammates scan the board and claim tasks themselves* | |
| 180 | +| [s12](./docs/en/s12-worktree-task-isolation.md) | Worktree + Task Isolation | *Each works in its own directory, no interference* | |
181 | 181 |
|
182 | 182 | ## What's Next -- from understanding to shipping |
183 | 183 |
|
|
0 commit comments