A setup command that creates a starter configuration for the Orchestrator MCP server and checks whether the configured agent command-line logins work. It does not add a duplicate server registration.

Use it to initialize the local orchestrator configuration, verify reviewer access, and identify any agent configuration that needs manual repair.

It gives the server a configuration based on the agent tools already installed and exposes missing or invalid logins before use.

setup — Command for Claude Code by crAK1644/orchestrator-mcp

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.

Clone the repo

git clone --depth 1 https://github.com/crAK1644/orchestrator-mcp

Made for: Claude Code.

Or install orchestrator-mcp, the plugin that ships this one along with the rest of its 1 command.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/crak1644/orchestrator-mcp/setup/github.svg)](https://agentmods.dev/commands/crak1644/orchestrator-mcp/setup)

Your own site

<a href="https://agentmods.dev/commands/crak1644/orchestrator-mcp/setup"><img src="https://agentmods.dev/badge/commands/crak1644/orchestrator-mcp/setup/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/commands/crak1644/orchestrator-mcp/setup"><img src="https://agentmods.dev/badge/commands/crak1644/orchestrator-mcp/setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 520 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00011	$0.00520
Opus 5.5	$0.00004	$0.00208
Sonnet 5.5	$0.00002	$0.00104
Haiku 4.5	$0.00001	$0.00052

Measured yesterday against content hash fd0e0b625b39, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

setup 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 yesterday.

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.

plugin/commands/setup.md · 26 lines

What it actually says

Set up the MCP server this plugin registers. Run each command below with Bash and show the user its output.

Write a starter config at ~/.orchestrator-mcp/config.yaml from the agent CLIs installed here:
```
uvx [email protected] init --host claude
```
On success it ends by printing a claude mcp add orchestrator ... command. Do not run it: this plugin already registers the server, and adding it again would run two. A review: left out line needs no action: ~/.orchestrator-mcp/agents.yaml already names the reviewers.

If it says the file already exists, that is fine; go on to step 2. If it refuses for any other reason -- no reviewer CLI found, or a reviewer that ~/.orchestrator-mcp/agents.yaml names and the starter config does not define -- quote the refusal and say what fixes it, then go on to step 2 anyway. init has no OpenCode template: if that is the only other agent here, point the user at its agent, opencode, in https://github.com/crAK1644/orchestrator-mcp/blob/main/config.example.yaml to copy into the config by hand.

Check it with the same environment the plugin gives the server:

ORCHESTRATOR_CONFIG="$HOME/.orchestrator-mcp/config.yaml" ORCHESTRATOR_HOST_RUNTIME=claude uvx [email protected] doctor

Quote every FAIL line with what fixes it: install the CLI it names, log in to it, or edit the config key it names. A copilot agent that is not signed in needs COPILOT_HOME=$HOME/.orchestrator-mcp/copilot/home copilot login, not a plain copilot login: the server runs Copilot under a home of its own. init prints that line only when it writes the config, so give it to the user either way. Do not edit the config yourself unless the user asks.
Finish by telling the user to reconnect plugin:orchestrator-mcp:orchestrator in /mcp, or to restart Claude Code. /reload-plugins is not enough: it keeps the server that started before the config existed.

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.

yesterday Changed fd0e0b625b39
5d ago Changed 8f6862445cd4
8d ago Changed 2db0a25faf82
9d ago Changed e759c38a0b7d
10d ago Changed c9932e6d765f
11d ago Changed 8ce02b42b941
14d ago First seen · 26 lines · 11 tokens per session scan A 8c9faa8bb3bd

Subscribe to this mod's changes

setup is a command published in the GitHub repository crAK1644/orchestrator-mcp (10 stars, last pushed yesterday), licensed MIT. It adds 11 tokens to every session and 520 once invoked, about $0.0000 per session on Opus 5.5. 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 2026-09-26.

Building agents Claude Code LLM Productivity codex llm-routing mcp model-context-protocol

setup

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other commands, from other repositories

gsd:profile-user

gsd:resume-work

gsd-manage

check

fire-todos

help