manager

Route coding and toolchain tasks across multiple backends in an MCP client.

Updated Aug 27, 2026
One-click install
npx skills add https://github.com/josephwander-arch/manager --skill manager-josephwander-arch
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: manager
Source: https://github.com/josephwander-arch/manager/tree/main/skills/manager
Command: npx skills add https://github.com/josephwander-arch/manager --skill manager-josephwander-arch

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Orchestrates routing and coordination of coding, reasoning, and toolchain tasks across multiple backends inside an MCP client, enabling durable, server-side orchestration without bespoke glue code.

Core Features & Use Cases

  • Auto-route based on task shape, historical success, and backend availability to select Codex, Claude Code, Gemini, or GPT.
  • Server-side blocking and task_watch for synchronous waits while keeping other work non-blocking.
  • Durable coordination with Project Loafs that survive restarts and handoffs, plus analytics-driven routing insights.
  • Centralized security and containment by archiving prior states and enabling safe task reruns and rollbacks.
  • Broad applicability to software development, data processing, and multi-toolchain workflows within MCP clients.

Quick Start

Delegate a small coding task to the best backend and let the system route it automatically.

Frequently Asked Questions about manager

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I orchestrate coding tasks across multiple AI backends inside an MCP client?

You can orchestrate multi-backend tasks inside an MCP client by automatically routing coding, reasoning, and toolchain requests to backends like Codex, Claude Code, Gemini, or GPT based on task shape and historical success without bespoke glue code.

What is server-side blocking for task delegation in MCP?

Server-side blocking enables synchronous task_watch waits for delegated tasks while keeping other work non-blocking, ensuring durable coordination without freezing the entire MCP client environment during toolchain execution.

How do Project Loafs handle durable coordination for AI workflows?

Project Loafs provide durable coordination by surviving restarts and handoffs, ensuring your routed AI tasks maintain state and continuity even if the MCP client or backend connection drops unexpectedly.

Can I route tasks to different AI backends based on their strengths automatically?

Auto-routing evaluates task shape, historical success, and backend availability to select the most suitable backend like Codex, Claude Code, Gemini, or GPT, enabling strength-based task delegation across your software development workflows.

Does multi-backend task orchestration support rollback and safe reruns?

Centralized security and containment archive prior states to enable safe task reruns and rollbacks, protecting your software development workflows when a routed task fails or requires reverting to a previous configuration.

When should I use automated routing instead of direct backend calls in software development?

Use automated routing when managing complex delegation scenarios where backends differ in strengths, requiring analytics-backed routing decisions and durable coordination that direct calls cannot handle without custom orchestration glue code.