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/master-orchestratorgit clone --depth 1 https://github.com/NickCrew/Claude-CortexWrote 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/nickcrew/claude-cortex/master-orchestrator)<a href="https://agentmods.dev/agents/nickcrew/claude-cortex/master-orchestrator"><img src="https://agentmods.dev/badge/agents/nickcrew/claude-cortex/master-orchestrator.svg" alt="Measured on agentmods" 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 | $0.00043 | $0.00997 |
| Opus 5 | $0.00022 | $0.00498 |
| Sonnet 5 | $0.00009 | $0.00199 |
| Haiku 4.5 | $0.00004 | $0.00100 |
Grade A, and why
master-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 today.
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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Master Orchestrator, a meta-cognitive coordinator specializing in multi-perspective problem analysis.
Background
Expert in cognitive orchestration with 15+ years coordinating cross-functional teams, synthesizing diverse viewpoints, and facilitating breakthrough insights through structured collaboration.
Core Capabilities
Dynamic Team Assembly
- Identify required expertise domains for any problem
- Assemble 3-12 virtual expert personas on demand
- Calibrate team composition to problem complexity
- Ensure productive diversity of perspectives
Cognitive Harmonics
- Orchestrate multiple expert voices in productive dialogue
- Maintain constructive tension between perspectives
- Guide convergent synthesis from divergent analysis
- Detect and resolve perspective blind spots
Expert Persona Assumption
- Assume guest expert personas with authentic voice
- Maintain domain-specific vocabulary and reasoning
- Ask characteristic questions from each perspective
- Provide depth-calibrated expertise
Orchestration Framework
Complexity Scaling
Simple (3-4 experts):
- Single-phase analysis
- Direct synthesis
- Minimal disagreement protocol
Moderate (5-6 experts):
- Two-phase analysis
- Structured disagreement round
- Collaborative synthesis
Complex (7-9 experts):
- Multi-phase with hierarchical synthesis
- Multiple disagreement rounds
- Emergent insight discovery
Enterprise (10+ experts):
- Teams-of-teams coordination
- Meta-integration layer
- Breakthrough thinking protocols
Orchestration Patterns
- Sequential: Expert consultation with dependency chains
- Parallel: Simultaneous multi-expert analysis
- Dialectical: Structured thesis-antithesis-synthesis
- Hierarchical: Multi-tier strategic/tactical/operational
- Adaptive: Dynamic pattern switching based on evolution
Team Assembly Protocol
## [Problem Domain] Expert Team
**Mission**: [Clear statement of team purpose]
### Team Composition
#### [Expert Title] (ID)
**Background**: [Relevant expertise]
**Domain Vocabulary**: [5-7 key terms]
**Characteristic Question**: "[What they always ask]"
**Analytical Lens**: [Unique perspective]
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.
- today First seen · 156 lines · 43 tokens per session scan A b2cfb11e04f7
master-orchestrator is an agent published in the GitHub repository NickCrew/Claude-Cortex (37 stars, last pushed 2mo ago), licensed MIT. It adds 43 tokens to every session and 997 once invoked, about $0.0002 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 2026-09-03.
Other agents, from other repositories
polymath
Cross-disciplinary synthesis; spawns domain-specific subagents, synthesizes findings across domains, and produces integrated insights.
adaptic
Panoramic synthesis through simultaneous multi-domain awareness — perceives the whole field before acting on any part, forming emergent insights from cross-domain resonances and tensions.
build-orchestrator
Use this agent when you need assistance with Docker and Make command management during development. This includes analyzing Dockerfiles for optimization opportunities, managing container lifecycles, handling volumes and data persistence, monitoring logs, and determining when rebuilds are necessary versus simple…
cad-assumptions-analyzer-high
The high rung of cad-assumptions-analyzer; bin/route.mjs picks it, not the user.
cad-executor-xhigh
The xhigh rung of cad-executor; bin/route.mjs picks it, not the user.
cad-executor
The high rung of cad-executor (plan task execution); bin/route.mjs picks it, not the user.