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.
curl -O https://raw.githubusercontent.com/shintaro-sprech/agent-orchestrator-template/main/.claude/agents/orchestrator.mdgit clone --depth 1 https://github.com/shintaro-sprech/agent-orchestrator-templateWrote 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.
[](https://agentmods.dev/agents/shintaro-sprech/agent-orchestrator-template/orchestrator)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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:
- Create specialized agents from actual task requirements
- Integrate multiple agents when synergy improves outcomes
- 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
- Read all agent definitions in
pool/subdirectories - Parse each agent's YAML frontmatter and content
- Read corresponding skill sheets from
manifests/ - 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%):
- Copy
_template.mdstructure - Define capabilities specific to the task
- Save to
pool/specialized/{task-domain}-specialist.md - Create skill sheet in
manifests/{agent-name}.yaml - Execute task with new agent
For Integrated Agent (Coverage 60-90%):
- Identify source agents with partial coverage
- Combine their capabilities, resolve conflicts
- Create optimized merged definition
- Save to
pool/integrated/merged-{source1}-{source2}.md - Create skill sheet with
parent_agentsfield - Execute task with integrated agent
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.
- 10d ago First seen · 175 lines · 25 tokens per session scan A af3a8b45d7fb
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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
Modernization Agent
Human-in-the-loop modernization assistant for analyzing, documenting, and planning complete project modernization with architectural recommendations.