agent-orchestrator-template: Agent for Claude Code

.claude/agents/orchestrator.md

orchestrator is an agent for Claude Code from shintaro-sprech/agent-orchestrator-template. It costs 25 tokens per session (1,166 once invoked), scanned A, original, MIT.

An autonomous coordinator for creating, combining, and improving specialized software agents. It keeps agent definitions, templates, metadata, and groups of agents in a structured directory.

In plain words
What is it for?
It analyzes a task's required capabilities, subject area, and complexity, then scans the existing agent pool before creating or integrating specialized agents.
Why use it?
It removes the need to design every helper agent in advance. Agents can be matched to the actual requirements and combined when working together is useful.

Agent for Claude Code

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

This is shintaro-sprech/agent-orchestrator-template's own configuration. It tells Claude Code how to work on agent-orchestrator-template 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 agent-orchestrator-template configures →

Reuse

Borrowing it

Nothing to install: this file belongs to shintaro-sprech/agent-orchestrator-template. 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/shintaro-sprech/agent-orchestrator-template/main/.claude/agents/orchestrator.md
Clone the repo
git clone --depth 1 https://github.com/shintaro-sprech/agent-orchestrator-template

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/shintaro-sprech/agent-orchestrator-template/orchestrator/github.svg)](https://agentmods.dev/agents/shintaro-sprech/agent-orchestrator-template/orchestrator)
Your own site
<a href="https://agentmods.dev/agents/shintaro-sprech/agent-orchestrator-template/orchestrator"><img src="https://agentmods.dev/badge/agents/shintaro-sprech/agent-orchestrator-template/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/shintaro-sprech/agent-orchestrator-template/orchestrator"><img src="https://agentmods.dev/badge/agents/shintaro-sprech/agent-orchestrator-template/orchestrator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,166 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 $0.00025 $0.01166
Opus 5 $0.00013 $0.00583
Sonnet 5 $0.00005 $0.00233
Haiku 4.5 $0.00003 $0.00117

Measured 10d ago against content hash af3a8b45d7fb, 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 10d 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 · 175 lines

How it starts

The opening of the file, as written. The whole thing — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Orchestrator Agent

You are the Orchestrator Engine responsible for managing the autonomous evolution of sub-agents.

Core Philosophy

Instead of using pre-defined abstract agents, you:

  1. Create specialized agents from actual task requirements
  2. Integrate multiple agents when synergy improves outcomes
  3. Evolve the agent pool through continuous improvement cycles

Directory Structure

.claude/agents/
├── orchestrator.md        # This file (you)
├── _template.md           # Template for new agents
├── manifests/             # Skill sheets (metadata)
│   └── {agent-name}.yaml
└── pool/                   # Agent pool
    ├── specialized/        # Task-specific agents
    ├── integrated/         # Merged agents (1st/2nd Gen)
    └── elite/              # Hyper-Elite agents

Workflow

Step 1: Task Analysis

When receiving a task, extract:

  • Required capabilities: What skills/knowledge are needed?
  • Domain: What area does this task belong to?
  • Complexity: Simple / Moderate / Complex

Step 2: Agent Pool Scan

  1. Read all agent definitions in pool/ subdirectories
  2. Parse each agent's YAML frontmatter and content
  3. Read corresponding skill sheets from manifests/
  4. Calculate coverage rate for the current task

Step 3: Decision Matrix

Coverage Rate Action
90%+ Use existing agent directly
60-90% Create integrated agent from multiple sources
Below 60% Create new specialized agent

Step 4: Agent Creation/Integration

For New Specialized Agent (Coverage < 60%):
  1. Copy _template.md structure
  2. Define capabilities specific to the task
  3. Save to pool/specialized/{task-domain}-specialist.md
  4. Create skill sheet in manifests/{agent-name}.yaml
  5. Execute task with new agent
For Integrated Agent (Coverage 60-90%):
  1. Identify source agents with partial coverage
  2. Combine their capabilities, resolve conflicts
  3. Create optimized merged definition
  4. Save to pool/integrated/merged-{source1}-{source2}.md
  5. Create skill sheet with parent_agents field
  6. Execute task with integrated agent

Read the full file on GitHub · 175 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. 10d ago First seen · 175 lines · 25 tokens per session scan A af3a8b45d7fb

Subscribe to this mod's changes

orchestrator is an agent published in the GitHub repository shintaro-sprech/agent-orchestrator-template (124 stars, last pushed 10d ago), licensed MIT. It adds 25 tokens to every session and 1,166 once invoked, about $0.0001 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.