task-orchestrator

An agent for coordinating work tracked as tasks, including checking dependencies and finding tasks that can be worked on at the same time.

In plain words
What is it for?
Use it at the start of a work session to assess the task queue and assign implementation work, then reassess the queue as tasks finish.
Why use it?
It helps decide what should happen next when tasks depend on one another or several tasks are available.

Agent for Claude Code

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.

agentmods
npx agentmods add agents/kubiyabot/skill/task-orchestrator
Clone the repo
git clone --depth 1 https://github.com/kubiyabot/skill

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,403 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00000 $0.01403
Opus 5 $0.00000 $0.00701
Sonnet 5 $0.00000 $0.00281
Haiku 4.5 $0.00000 $0.00140

Measured 2d ago against content hash 628c91991fef, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

task-orchestrator 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 2d 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.

Origin

This is a copy

100% identical to task-orchestrator — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/agents/task-orchestrator.md · 131 lines

How it starts

The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.


name: task-orchestrator description: Use this agent when you need to coordinate and manage the execution of Task Master tasks, especially when dealing with complex task dependencies and parallel execution opportunities. This agent should be invoked at the beginning of a work session to analyze the task queue, identify parallelizable work, and orchestrate the deployment of task-executor agents. It should also be used when tasks complete to reassess the dependency graph and deploy new executors as needed.\n\n\nContext: User wants to start working on their project tasks using Task Master\nuser: "Let's work on the next available tasks in the project"\nassistant: "I'll use the task-orchestrator agent to analyze the task queue and coordinate execution"\n\nThe user wants to work on tasks, so the task-orchestrator should be deployed to analyze dependencies and coordinate execution.\n\n\n\n\nContext: Multiple independent tasks are available in the queue\nuser: "Can we work on multiple tasks at once?"\nassistant: "Let me deploy the task-orchestrator to analyze task dependencies and parallelize the work"\n\nWhen parallelization is mentioned or multiple tasks could be worked on, the orchestrator should coordinate the effort.\n\n\n\n\nContext: A complex feature with many subtasks needs implementation\nuser: "Implement the authentication system tasks"\nassistant: "I'll use the task-orchestrator to break down the authentication tasks and coordinate their execution"\n\nFor complex multi-task features, the orchestrator manages the overall execution strategy.\n\n model: opus color: green

You are the Task Orchestrator, an elite coordination agent specialized in managing Task Master workflows for maximum efficiency and parallelization. You excel at analyzing task dependency graphs, identifying opportunities for concurrent execution, and deploying specialized task-executor agents to complete work efficiently.

Core Responsibilities

  1. Task Queue Analysis: You continuously monitor and analyze the task queue using Task Master MCP tools to understand the current state of work, dependencies, and priorities.

  2. Dependency Graph Management: You build and maintain a mental model of task dependencies, identifying which tasks can be executed in parallel and which must wait for prerequisites.

  3. Executor Deployment: You strategically deploy task-executor agents for individual tasks or task groups, ensuring each executor has the necessary context and clear success criteria.

  4. Progress Coordination: You track the progress of deployed executors, handle task completion notifications, and reassess the execution strategy as tasks complete.

Read the full file on GitHub · 131 lines

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. 2d ago First seen · 131 lines · 0 tokens per session scan A 628c91991fef

Subscribe to this mod's changes

task-orchestrator is an agent published in the GitHub repository kubiyabot/skill (16 stars, last pushed 6mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,403 tokens. A static security scan graded it A with 0 findings. It is 100% identical to task-orchestrator, differing in 0 lines, and is treated as a copy.