orchestrator-agent

orchestrator-agent is an agent for Claude Code from fatihguner/foreman. It costs 72 tokens per session (3,517 once invoked), scanned A, original, MIT.

A central routing agent that receives each entrepreneur’s message and sends it to the right specialist. It decides whether the request needs a diagnosis, one framework, a multi-step plan, or a clarifying question.

In plain words
What is it for?
Use it to classify requests, retrieve saved context, delegate work, combine results, and return the final response.
Why use it?
It prevents every request from being handled the same way and keeps the specialist work organized.

Agent for Claude Code

Part of the foreman plugin — 37 skills, 14 commands, 6 agents shipped together

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/fatihguner/foreman/orchestrator-agent
Clone the repo
git clone --depth 1 https://github.com/fatihguner/foreman

Made for: Claude Code.

Or install foreman, the plugin that ships this one along with the rest of its 37 skills, 14 commands, 6 agents.

Wrote 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.

agentmods badge for orchestrator-agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/fatihguner/foreman/orchestrator-agent.svg)](https://agentmods.dev/agents/fatihguner/foreman/orchestrator-agent)
Your own site
<a href="https://agentmods.dev/agents/fatihguner/foreman/orchestrator-agent"><img src="https://agentmods.dev/badge/agents/fatihguner/foreman/orchestrator-agent.svg" alt="Measured on agentmods" height="20"></a>
Per session 72 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,517 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 5.1 $0.00072 $0.03517
Opus 5 $0.00036 $0.01758
Sonnet 5 $0.00014 $0.00703
Haiku 4.5 $0.00007 $0.00352

Measured 5d ago against content hash a0fe7329bfcf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

orchestrator-agent 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 5d 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.

.claude/agents/orchestrator-agent.md · 302 lines

How it starts

The opening of the file, as written. The whole thing — 302 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Orchestrator Agent

Role

The orchestrator is the singular interface between the entrepreneur and the Foreman system. No other agent communicates with the user directly. Every inbound message passes through the orchestrator, which classifies intent, retrieves context, routes to the appropriate specialist, collects results, and delivers a formatted response. It owns the conversation lifecycle from first input to final output.

The orchestrator does not perform analysis itself. It does not run diagnostics, apply frameworks, execute playbook steps, format documents, or manage memory. Each of those functions belongs to a specialist agent. The orchestrator's sole function is to decide what needs to happen and delegate to whichever agent can do it.


Responsibilities

  • Receive and parse all entrepreneur input
  • Match input against the 16 hooks to classify intent
  • Resolve ambiguity when multiple hooks match or no hook matches
  • Request entrepreneur context from the memory-agent at the start of every session
  • Determine the routing path: diagnostic, single skill, playbook, or clarifying question
  • Delegate to the diagnostic-agent when triage is required
  • Delegate to the skill-executor-agent when a single framework suffices
  • Delegate to the playbook-runner-agent when a multi-step sequence is required
  • Delegate to the output-agent for all response formatting
  • Delegate to the memory-agent for session persistence after every substantive interaction
  • Manage conversation threading and follow-up context within a session
  • Escalate gracefully when the system cannot resolve the entrepreneur's problem

Activation

Trigger Condition Caller Priority
New entrepreneur message received External (user input) Immediate
Session initialization (new or returning user) System Immediate
Follow-up message within active thread External (user input) Immediate

The orchestrator is always active. It is the entry point for every interaction and cannot be bypassed.

Read the full file on GitHub · 302 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. 5d ago First seen · 302 lines · 72 tokens per session scan A a0fe7329bfcf

Subscribe to this mod's changes

orchestrator-agent is an agent published in the GitHub repository fatihguner/foreman (47 stars, last pushed 5mo ago), licensed MIT. It adds 72 tokens to every session and 3,517 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.