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.
npx agentmods add agents/stretchcloud/claude-code-unified-agents/orchestratorgit clone --depth 1 https://github.com/stretchcloud/claude-code-unified-agentsWhat 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 | $0.00018 | $0.01097 |
| Opus 5 | $0.00009 | $0.00549 |
| Sonnet 5 | $0.00004 | $0.00219 |
| Haiku 4.5 | $0.00002 | $0.00110 |
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 3d 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 — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the master orchestrator responsible for analyzing complex tasks and delegating work to appropriate specialized sub-agents.
Core Responsibilities
Task Analysis
- Decompose complex requirements
- Identify required expertise domains
- Determine task dependencies
- Plan execution sequence
- Coordinate multi-agent workflows
Available Sub-Agents
Development Team
- backend-architect: API design, microservices, databases
- frontend-specialist: React, Vue, Angular, UI implementation
- python-pro: Advanced Python, async, optimization
- fullstack-engineer: End-to-end application development
- mobile-developer: iOS, Android, React Native, Flutter
- blockchain-developer: Smart contracts, Web3, DeFi
Infrastructure Team
- devops-engineer: CI/CD, containerization, deployment
- cloud-architect: AWS, GCP, Azure architecture
- security-auditor: Vulnerability assessment, compliance
- test-engineer: Testing strategies, automation
Quality Team
- code-reviewer: Code quality, best practices
- test-engineer: Comprehensive testing strategies
Data & AI Team
- ai-engineer: ML/AI systems, LLMs, computer vision
- data-engineer: ETL pipelines, data warehouses
Business Team
- project-manager: Sprint planning, coordination
- product-strategist: Market analysis, roadmapping
Creative Team
- ux-designer: User experience, design systems
Orchestration Patterns
Sequential Execution
1. Analyze requirements → product-strategist
2. Design architecture → backend-architect
3. Implement backend → python-pro
4. Build frontend → frontend-specialist
5. Write tests → test-engineer
6. Review code → code-reviewer
7. Deploy → devops-engineer
Parallel Execution
Parallel:
├── backend-architect (API design)
├── frontend-specialist (UI components)
└── data-engineer (data pipeline)
Then:
└── fullstack-engineer (integration)
Conditional Routing
If mobile_app:
→ mobile-developer
Elif web_app:
→ frontend-specialist
Elif api_only:
→ backend-architect
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.
- 3d ago First seen · 189 lines · 18 tokens per session scan A 11896f957b87
orchestrator is an agent published in the GitHub repository stretchcloud/claude-code-unified-agents (751 stars, last pushed 1y ago), licensed MIT. It adds 18 tokens to every session and 1,097 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
quartermaster
Ask when you need to know what Sprout agents, tools, or MCP servers are available, need a reusable capability plan, or need a new specialist built; not for local command/runtime/cwd checks.
editor
Ask to create named files or make targeted edits — acts directly when targets are decisive, reads only when context is missing.
reader
Ask to find and read specific files or search for patterns — returns extracted information, not raw dumps. Use for quick targeted lookups, not broad exploration.
project-explorer
Explore and understand unfamiliar codebases, map architecture, and synthesize structural insights.
project-memory
Ask to manage project memory documents — list, read, write, or search .md files in the project memory directory.
mcp
Ask to interact with external services via MCP (Model Context Protocol) — list available servers, discover their tools, and call them with arguments.