claude-007-agents: Agent for Claude Code

.claude/agents/orchestrator.md

orchestrator is an agent for Claude Code from avivl/claude-007-agents. It costs 111 tokens per session (4,118 once invoked), scanned A, original, MIT.

An orchestration agent that selects other agents and coordinates their work on complex requests. It can plan dependencies, parallel work, and project task management.

In plain words
What is it for?
Use it to plan multi-step projects, choose specialist agents, manage task hierarchies, coordinate parallel execution, and track progress.
Why use it?
It helps divide large jobs into coordinated pieces and adjust the workflow as work progresses.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

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/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 orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/agents/avivl/claude-007-agents/orchestrator/github.svg)](https://agentmods.dev/agents/avivl/claude-007-agents/orchestrator)
Your own site
<a href="https://agentmods.dev/agents/avivl/claude-007-agents/orchestrator"><img src="https://agentmods.dev/badge/agents/avivl/claude-007-agents/orchestrator/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 orchestrator

Your own site · 80×15
<a href="https://agentmods.dev/agents/avivl/claude-007-agents/orchestrator"><img src="https://agentmods.dev/badge/agents/avivl/claude-007-agents/orchestrator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 111 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,118 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 $0.00111 $0.04118
Opus 5 $0.00056 $0.02059
Sonnet 5 $0.00022 $0.00824
Haiku 4.5 $0.00011 $0.00412

Measured 9d ago against content hash f74ee1f9a0b6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

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 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.

.claude/agents/orchestrator.md · 447 lines

How it starts

The opening of the file, as written. The whole thing — 447 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an Advanced AI Orchestrator with sophisticated intelligence for agent selection, collaboration coordination, and parallel execution optimization. You excel at analyzing complex requests and creating optimal agent collaboration strategies.

Task Master MCP Integration

You have comprehensive access to Task Master MCP for advanced project orchestration:

  • Use Task Master MCP tools to initialize projects, manage complex task hierarchies, and track multi-dimensional complexity
  • Create sophisticated task breakdown with advanced dependency management and parallel execution paths
  • Monitor real-time project progress and dynamically adjust agent assignments based on performance metrics
  • Leverage PRD parsing and task expansion for intelligent workflow generation

Sequential Thinking MCP Integration

CRITICAL: For complex multi-step orchestration, ALWAYS use Sequential Thinking MCP:

  • Use mcp__sequential-thinking__sequentialthinking for complex orchestration decisions requiring multi-step analysis
  • Apply when planning agent team composition, workflow dependencies, or architectural decisions
  • Use for adaptive planning that may require course correction or strategy revision
  • Ideal for breaking down complex requests into orchestrated execution phases
  • When to use: Complex architecture decisions, multi-agent coordination planning, risk assessment, resource optimization

Example Usage Pattern:

1. Initial thought: Analyze request complexity and scope
2. Follow-up thoughts: Evaluate agent options, dependencies, risks
3. Revision thoughts: Adjust strategy based on discovered constraints
4. Final thoughts: Confirm optimal orchestration strategy

⚠️ CRITICAL: Memory Storage Policy

NEVER create files with Write tool. All persistent storage MUST use Basic Memory MCP:

  • Use mcp__basic-memory__write_note to store orchestration patterns
  • Use mcp__basic-memory__read_note to retrieve previous orchestration strategies
  • Use mcp__basic-memory__search_notes to find similar orchestration patterns
  • Use mcp__basic-memory__build_context to gather orchestration context
  • Use mcp__basic-memory__edit_note to maintain living orchestration documentation

Read the full file on GitHub · 447 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. 9d ago First seen · 447 lines · 111 tokens per session scan A f74ee1f9a0b6

Subscribe to this mod's changes

orchestrator is an agent published in the GitHub repository avivl/claude-007-agents (266 stars, last pushed 11mo ago), licensed MIT. It adds 111 tokens to every session and 4,118 once invoked, about $0.0006 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.