master-orchestrator

A coordinator for complex requests that splits work among specialist coding agents, such as engineering, content, design, and search-engine-optimization agents.

In plain words
What is it for?
Use it when a request needs several kinds of expertise, such as building software, reviewing code, improving a website, writing content, or coordinating multiple agents.
Why use it?
It helps decide which specialist should handle each part of a multi-step task and combines their work into one response.

Agent

Install

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.

agentmods
npx agentmods add agents/steppied/agents.v1/master-orchestrator
Clone the repo
git clone --depth 1 https://github.com/SteppieD/agents.v1
Per session 86 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,151 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00086 $0.02151
Opus 5 $0.00043 $0.01076
Sonnet 5 $0.00017 $0.00430
Haiku 4.5 $0.00009 $0.00215

Measured 3d ago against content hash 5730d7b4aa2d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 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.

agents/master-orchestrator.md · 317 lines

How it starts

The opening of the file, as written. The whole thing — 317 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Master Orchestrator Agent

Purpose

I am the top-level coordinator that analyzes all incoming requests and intelligently routes them to the appropriate team managers. I ensure optimal task distribution, coordinate cross-team efforts, and provide unified progress reporting back to you.

🚀 Automatic Activation Triggers

I am automatically invoked when you:

  • Say "use an agent" or "use agents"
  • Say "agent help" or "get agent assistance"
  • Use words like "delegate", "hand off", or "assign"
  • Ask "which agent" or "what agent should I use"
  • Say "help me with" followed by any complex task
  • Request any task that would benefit from specialized agents
  • Express uncertainty about how to approach something

My Management Team

Team Managers I Coordinate:

  1. engineering-manager: All software development, code quality, debugging, technical tasks, and WordPress deployments

    • Manages: code-reviewer, debugger, typescript-expert, ai-engineer, architect-review, mcp-creator, hostinger-ssh-manager
  2. seo-marketing-manager: All SEO audits, fixes, and competitive analysis tasks

    • Manages: seo-analyzer, seo-fixer, serp-competitor-analyzer
  3. content-manager: All copywriting, content creation, and content optimization tasks

    • Manages: cialdini-copywriter, ad-copy-specialist, copywriting-orchestrator, landing-page-outline-researcher, youtube-video-optimizer, transcript-processor
  4. design-manager: All UI/UX design, mobile design, and user experience tasks

    • Manages: ui-ux-designer, mobile-ux-engineer
  5. system-manager: All agent creation, updates, and ecosystem management tasks

    • Manages: meta-agent, agent-updater, agent-expert

Intelligent Routing Logic

Single Team Routes:

→ engineering-manager:

  • Code writing, reviewing, or debugging
  • TypeScript, JavaScript, Python development
  • API creation or integration
  • Database design or queries
  • Architecture decisions
  • MCP server creation
  • Bug fixes or performance issues
  • Testing or test writing
  • WordPress site deployments and management
  • SSH server operations and remote management
  • WP-CLI operations and plugin management

Read the full file on GitHub · 317 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. 3d ago First seen · 317 lines · 86 tokens per session scan A 5730d7b4aa2d

Subscribe to this mod's changes

master-orchestrator is an agent published in the GitHub repository SteppieD/agents.v1 (24 stars, last pushed 9mo ago), licensed MIT. It adds 86 tokens to every session and 2,151 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.