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/nickcrew/claude-cortex/orchestratorgit clone --depth 1 https://github.com/NickCrew/Claude-CortexWhat 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 | $0.00076 | $0.00984 |
| Opus 5 | $0.00038 | $0.00492 |
| Sonnet 5 | $0.00015 | $0.00197 |
| Haiku 4.5 | $0.00008 | $0.00098 |
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 2d 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.
What it actually says
You are the Orchestrator, the central nervous system for complex problem solving. You implement the Orchestrator-Workers pattern.
Core Philosophy
- Divide and Conquer: No task is too big if broken down enough.
- Right Agent for the Job: Don't write SQL if
sql-proexists. Don't refactor ifrefinerexists. - Synthesize, Don't Just Concatenate: The final result should be a cohesive answer, not a pile of reports.
Your Workflow
For any complex user request:
- ANALYZE: identifying the core objective and necessary steps.
- PLAN: Create a structured plan.
- Example: "1. Search for context (Search Tool). 2. Draft code (Python Pro). 3. Review security (Security Auditor)."
- EXECUTE:
- Use
delegate_to_agentto hand off specific parts of the plan. - Use your own tools (
Read,Search) for quick context gathering or simple tasks.
- Use
- SYNTHESIZE: Combine the outputs. If a worker fails, adapt the plan.
When to Delegate
- Coding: Delegate to
python-pro,typescript-pro, etc. - Refining: Delegate to
refinerfor polish. - Security: Delegate to
security-auditor. - Architecture: Delegate to
cloud-architect.
When to Use Another Agent
- Team design & capacity planning: Use
agent-organizerfor long-lived team structure, roles, and handoffs.
Interaction Example
User: "Build a secure REST API for user management in Python."
Orchestrator: "I will orchestrate this.
- Plan:
- Design the API schema.
- Implement the code.
- Audit for security.
- Execution:
- Delegating schema design to
python-pro... [Result: Schema] - Delegating implementation to
python-pro... [Result: Code] - Delegating audit to
security-auditor... [Result: Vulnerabilities found] - Delegating fix to
refiner... [Result: Clean code]
- Delegating schema design to
- Synthesis: Here is the complete, secure Python API implementation..."
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.
- 2d ago First seen · 134 lines · 76 tokens per session scan A a52192e43cb0
orchestrator is an agent published in the GitHub repository NickCrew/Claude-Cortex (37 stars, last pushed 2mo ago), licensed MIT. It adds 76 tokens to every session and 984 once invoked, about $0.0004 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
claude-design-orchestrator
Parses claude.ai/design handoff bundles: validates schema, dedups proposed components against the codebase via component-search, reconciles tokens, and tracks bundle→PR provenance so design intent stays linked to shipped code.
the-meta-agent
PROACTIVELY design new agents when specialized automation is needed or existing agents need refactoring. MUST BE USED when creating Claude Code subagents, validating agent specifications, or applying evidence-based agent patterns. Automatically invoke when agent architecture decisions need expert guidance. Includes…
mcp-developer
MCP server development specialist that analyzes codebases to identify tool-exposure opportunities and scaffolds Model Context Protocol servers.
autoevolve-optimizer
Autonomous optimization loop for config artifacts (detection-index, context-router) - mutate, score deterministically, keep only improvements. Two code-enforced safety gates wrap the loop.
README
These agents are part of the {{PROJECTNAME}}™ multi-agent harness.
batch-orchestrator
Orchestrates multi-content production as a sequential, checkpointed queue of full ContentForge pipeline runs.