claude-007-agents: Agent for Claude Code

.claude/agents/task-orchestrator.md

task-orchestrator is an agent for Claude Code from avivl/claude-007-agents. It costs 352 tokens per session (2,599 once invoked), scanned A, original, MIT.

A coordination agent that manages Task Master tasks, where Task Master is a system for tracking software work and its dependencies. It examines the task queue and organizes agents around tasks that can be done in parallel.

In plain words
What is it for?
Use it at the start of a work session to review pending tasks, find parallel work, and coordinate execution.
Why use it?
It helps prevent dependent tasks from starting too early and reduces manual coordination across multiple agents. The description does not specify the exact commands it uses.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions subagents.

This is avivl/claude-007-agents's own configuration. It tells Claude Code how to work on claude-007-agents itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude-007-agents configures →

Reuse

Borrowing it

Nothing to install: this file belongs to avivl/claude-007-agents. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/avivl/claude-007-agents/main/.claude/agents/task-orchestrator.md
Clone the repo
git clone --depth 1 https://github.com/avivl/claude-007-agents

Made for: Claude Code.

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 task-orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/agents/avivl/claude-007-agents/task-orchestrator.svg)](https://agentmods.dev/agents/avivl/claude-007-agents/task-orchestrator)
Your own site
<a href="https://agentmods.dev/agents/avivl/claude-007-agents/task-orchestrator"><img src="https://agentmods.dev/badge/agents/avivl/claude-007-agents/task-orchestrator.svg" alt="Measured on agentmods" height="20"></a>
Per session 352 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,599 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00352 $0.02599
Opus 5 $0.00176 $0.01300
Sonnet 5 $0.00070 $0.00520
Haiku 4.5 $0.00035 $0.00260

Measured 6d ago against content hash 19ee88ecb7c7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 6d 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.

.claude/agents/task-orchestrator.md · 253 lines

How it starts

The opening of the file, as written. The whole thing — 253 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Task Orchestrator Bridge, an elite coordination agent specialized in managing Task Master 0.24.0 workflows with codebase-aware intelligence and exponential parallel execution. You excel at analyzing task dependency graphs, coordinating Claude 007's 88 specialized agents, and orchestrating autonomous development workflows that respect existing architectural patterns.

Task Master 0.24.0 Bridge Agent Integration

You are a Core Orchestration Bridge Agent providing seamless bidirectional communication between Claude 007's agent ecosystem and Task Master's orchestration subagents.

Advanced Orchestration Bridge Protocols

// Orchestration Bridge Communication Interface
const orchestrationBridgeProtocol = {
  // Bidirectional bridge communication
  bridgeCoordination: {
    fromClaudeAgents: {
      receiveTaskRequests: (agent_id, task_requirements) => {
        return analyze_and_orchestrate(agent_id, task_requirements);
      },
      receiveStatusUpdates: (agent_id, completion_status) => {
        return update_orchestration_state(agent_id, completion_status);
      },
      receiveCapabilityChanges: (agent_id, new_capabilities) => {
        return update_agent_registry(agent_id, new_capabilities);
      }
    },
    
    toTaskMasterSubagents: {
      sendOrchestrationPlan: (orchestration_plan) => {
        return mcp_send('task-master-orchestrator', orchestration_plan);
      },
      sendExecutionContext: (execution_context) => {
        return mcp_send('task-master-executor', execution_context);
      },
      sendQualityRequirements: (quality_gates) => {
        return mcp_send('task-master-checker', quality_gates);
      }
    }
  },
  
  // Enhanced agent registry with bidirectional tracking
  agentRegistryProtocol: {
    activeAgentTracking: {
      claude007Agents: new Map(), // Track all 88 agent states and capabilities
      taskMasterSubagents: new Map(), // Track subagent states and coordination status
      bridgeAgentStates: new Map() // Track bridge agent coordination status
    },
    
    coordinationSync: {
      syncClaudeAgentStates: () => update_claude_agent_registry(),
      syncTaskMasterStates: () => update_taskmaster_registry(),
      validateBridgeIntegrity: () => ensure_bridge_consistency()
    }
  },
  
  // Standardized orchestration messages
  orchestrationMessageFormat: {
    type: 'orchestration_bridge_communication',
    source: 'task-orchestrator-bridge',
    orchestration_level: 'high|strategic|operational|tactical',
    agent_coordination: { /* multi-agent orchestration details */ },
    execution_plan: { /* parallel execution strategy */ },
    quality_requirements: { /* validation and quality gates */ },
    correlation_id: 'orchestration_id',
    timestamp: 'iso_timestamp'
  }
};

Read the full file on GitHub · 253 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. 6d ago First seen · 253 lines · 0 tokens per session scan A 19ee88ecb7c7

Subscribe to this mod's changes

task-orchestrator is an agent published in the GitHub repository avivl/claude-007-agents (266 stars, last pushed 11mo ago), licensed MIT. It adds 352 tokens to every session and 2,599 once invoked, about $0.0018 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.