Agent Router — Development skill for Claude Code
本地多 Agent 协作调度器:主代理常驻主线程(Claude Code/ZCode/Devin/Codex/OpenCode/Antigravity 可指定),共享任务板 MCP、事件驱动非阻塞派发、自动收割合并.
How to install Agent Router
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open dazhi666666/agent-router and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Agent Router does
本地多 Agent 协作调度器:主代理常驻主线程(Claude Code/ZCode/Devin/Codex/OpenCode/Antigravity 可指定),共享任务板 MCP、事件驱动非阻塞派发、自动收割合并.
Alternatives in Development
- Zeron — A native control plane for Claude Code, Codex, Cursor, Devin and other coding agents 1.4k ★
- Oh My Agent — Portable multi-agent harness for .agents-based skills, workflows, and standards-aware agent teams across Antig 786 ★
- Tulpa — 基于Windows本地QQ+微信的Harness/MCP:用Agent进行实时检索、跟进、管理、记忆与工作区 179 ★
README
Agent Router
**A main agent runs the main thread (Claude Code by default; pick zcode / devin / codex / opencode / antigravity via `--main`)**: it holds a long-lived session, breaks the overall goal into tasks and dispatches them to local subagents (ZCode / Devin / Codex / OpenCode / Antigravity / other Claude Code instances). Dispatch is non-blocking — the manager creates tasks and immediately moves on; subagent progress (completion / failure / messages) is pushed back into the main session in real time. All agents collaborate through a **shared local task board** and exchange messages via the **board mailbox**; the Router handles automatic dispatch, harvest & merge, and the final summary.
Everything stays on your machine — agent runtimes, sessions, task data and communication. Model inference calls each vendor's API; that is the only boundary.
Communication: shared task board + event-driven
Agents never talk to each other directly — everything goes through one **local MCP server** (stdio + a JSON file); the Router is the main agent's "hands and feet" (scheduler + event layer):
you ──goal──▶ main agent session (main thread, persistent, bidirectional stream-json)
├─ create_task → returns instantly, keeps working on its own stuff
├─ followup_task → a subagent continues with the original task context
├─ receives [event]/[mailbox] pushes → replies / spawns follow-ups / codes itself
└─ goal achieved → calls finish_run to end the run
▲ events injected live │ dispatch / harvest (Node scheduler)
┌─────┴──────────────────────────────┴─────┐
│ board-server.mjs (MCP/stdio) │
│ tasks + mailbox → data//board.json│
└─────┬──────────┬───────────┬─────────────┘
claude -p agy(stream-json) zcode -p o
Related Skills
Artcraft Skills
Agent skills (SKILL.md) for the ArtCraft Rust creative suite — evidence-verified, MCP/CLI surfaces — for Claud
All Agent Shared Memory
Zero-dependency cross-agent memory + session bridge for Claude Code, Codex, opencode and ZCode: one auditable
Netvein
Local-first Chrome CDP reverse engineering & wire-level traffic MCP server, for Claude Code, Cursor, Codex, Op
Limisaw
LIMISAW (LIMIT SAW) - a one-file Windows tray monitor for how much quota is left across Codex, Claude Code, An
Openspec Agents
OpenSpec 的配套插件,兼容 Claude Code / Codex / ZCode / DeepSeek Harness / OpenCode:提案标准更严(澄清在前、改动范围与契约变更逐条确认),实施由多 Ag
Oc Run
让任意 Harness(ZCode/Claude Code/Codex…)把 OpenCode 当子 Agent 调度:并行派活(≤6)、结构化汇总、--session 续跑、跨项目 session 历史;模型自由不绑定
Related Agents
Paf Reviewer
Runs one phone-a-friend relay or review command in the background and reports back a receipt plus the findings
Transport Verifier
Runs live end-to-end checks of a delivery transport (Herdr socket, MCP server, Claude Code or Codex hook, Open
Protocol Researcher
Verifies facts about vendor agent CLIs, SDKs, protocols and terms (Claude Code, Codex, Gemini CLI, OpenCode, A