agent-task-coordinator

agent-task-coordinator is a skill for Claude Code, Codex from Omar-Obando/qwen-orchestrator. It costs 57 tokens per session (2,182 once invoked), scanned A, original, MIT.

A guide for coordinating several AI agents working on one complex task. It covers delegation, communication, task states, team monitoring, retries, and handoffs.

In plain words
What is it for?
Use it to split projects into smaller tasks, assign specialist agents, track their progress, exchange findings, and shut down agent teams cleanly.
Why use it?
Dividing work among agents can create duplicated effort, unclear ownership, or incomplete results without a shared process.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to split projects into smaller tasks, assign specialist agents, track their progress, exchange findings, and shut down agent teams cleanly.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/omar-obando/qwen-orchestrator/agent-task-coordinator
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add Omar-Obando/qwen-orchestrator --skill agent-task-coordinator
Clone the repo
git clone --depth 1 https://github.com/Omar-Obando/qwen-orchestrator

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for agent-task-coordinator

README.md
[![agentmods](https://agentmods.dev/badge/skills/omar-obando/qwen-orchestrator/agent-task-coordinator/github.svg)](https://agentmods.dev/skills/omar-obando/qwen-orchestrator/agent-task-coordinator)
Your own site
<a href="https://agentmods.dev/skills/omar-obando/qwen-orchestrator/agent-task-coordinator"><img src="https://agentmods.dev/badge/skills/omar-obando/qwen-orchestrator/agent-task-coordinator/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for agent-task-coordinator

Your own site · 80×15
<a href="https://agentmods.dev/skills/omar-obando/qwen-orchestrator/agent-task-coordinator"><img src="https://agentmods.dev/badge/skills/omar-obando/qwen-orchestrator/agent-task-coordinator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,182 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00057 $0.02182
Opus 5 $0.00028 $0.01091
Sonnet 5 $0.00011 $0.00436
Haiku 4.5 $0.00006 $0.00218

Measured 9d ago against content hash be2b221630c4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

agent-task-coordinator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/agent-task-coordinator/SKILL.md · 329 lines

How it starts

The opening of the file, as written. The whole thing — 329 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Task Coordinator

Overview

This skill provides guidance for coordinating multiple AI agents, managing agent teams, and delegating work across specialized agents. It covers communication patterns, task decomposition, and team coordination strategies. Based on agent collaboration patterns and distributed systems best practices.

When to Use

Use this skill when:

  • Coordinating multiple agents for complex tasks
  • Managing agent teams with different specializations
  • Delegating work across specialized agents
  • Designing agent communication patterns
  • Breaking down complex tasks for parallel execution
  • Managing agent team lifecycle
  • Implementing agent team composition strategies
  • Setting up task decomposition workflows
  • Creating agent communication protocols
  • Building agent swarm patterns
  • Implementing agent handoff mechanisms
  • Setting up MCP reporting for agent teams
  • Managing agent task state machines
  • Implementing agent team health monitoring
  • Creating agent team shutdown procedures
  • Building agent team documentation
  • Setting up agent team metrics and KPIs
  • Implementing agent team error handling
  • Creating agent team retry strategies
  • Building agent team monitoring dashboards
  • Setting up agent team alerting
  • Implementing agent team resource management
  • Creating agent team scaling strategies

Do NOT use this skill when:

  • Single-agent tasks (use specific skill for the task)
  • Simple, linear workflows (use standard workflow patterns)
  • Non-agentic workflows (use standard application development)
  • Basic task automation without agent coordination

Core Patterns

Agent Team Composition

┌─────────────────────────────────────────────────────────────┐
│              Team Lead (Orchestrator)                       │
│  └── Task decomposition, coordination, synthesis            │
├─────────────────────────────────────────────────────────────┤
│  ┌─────────────┐  ┌─────────────┐  ┌─────────────┐         │
│  │  Implementer│  │   Reviewer  │  │   Debugger  │         │
│  │   (Parallel)│  │   (Parallel)│  │   (Parallel)│         │
│  └─────────────┘  └─────────────┘  └─────────────┘         │
│         │              │              │                      │
│         └──────────────┴──────────────┘                      │
│                    │                                         │
│         ┌──────────▼──────────┐                              │
│         │   Integration Point │                              │
│         └─────────────────────┘                              │
└─────────────────────────────────────────────────────────────┘

Read the full file on GitHub · 329 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 329 lines · 57 tokens per session scan A be2b221630c4

Subscribe to this mod's changes

agent-task-coordinator is a skill published in the GitHub repository Omar-Obando/qwen-orchestrator (49 stars, last pushed 2mo ago), licensed MIT. It adds 57 tokens to every session and 2,182 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.