dotnet-mcp-orchestrator: Agent for Claude Code

.github/agents/McpOrchestrator-Example.agent.md

Orchestrator-Agent is an agent for Claude Code from Byggarepop/dotnet-mcp-orchestrator. It costs 22 tokens per session (777 once invoked), scanned A, original, MIT.

An AI agent that reaches multiple MCP servers through one central orchestrator. MCP servers are services that provide tools to an AI agent, such as issue tracking or databases.

In plain words
What is it for?
Use it to work with several configured MCP services from one agent and to discover which capabilities are currently available.
Why use it?
It removes the need to switch between separate agents or connect to every tool directly. The orchestrator routes each request to the appropriate connected service.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

This is Byggarepop/dotnet-mcp-orchestrator's own configuration. It tells Claude Code how to work on dotnet-mcp-orchestrator itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything dotnet-mcp-orchestrator configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Byggarepop/dotnet-mcp-orchestrator. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Byggarepop/dotnet-mcp-orchestrator/main/.github/agents/McpOrchestrator-Example.agent.md
Clone the repo
git clone --depth 1 https://github.com/Byggarepop/dotnet-mcp-orchestrator

Made for: Claude Code.

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/byggarepop/dotnet-mcp-orchestrator/mcporchestrator-example/github.svg)](https://agentmods.dev/agents/byggarepop/dotnet-mcp-orchestrator/mcporchestrator-example)
Your own site
<a href="https://agentmods.dev/agents/byggarepop/dotnet-mcp-orchestrator/mcporchestrator-example"><img src="https://agentmods.dev/badge/agents/byggarepop/dotnet-mcp-orchestrator/mcporchestrator-example/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.

agentmods 80×15 button for Orchestrator-Agent

Your own site · 80×15
<a href="https://agentmods.dev/agents/byggarepop/dotnet-mcp-orchestrator/mcporchestrator-example"><img src="https://agentmods.dev/badge/agents/byggarepop/dotnet-mcp-orchestrator/mcporchestrator-example.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 777 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00022 $0.00777
Opus 5 $0.00011 $0.00388
Sonnet 5 $0.00004 $0.00155
Haiku 4.5 $0.00002 $0.00078

Measured 10d ago against content hash 23271ab35a9b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, 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 10d 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.

.github/agents/McpOrchestrator-Example.agent.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

This agent references the orchestrator MCP server as orchestrator/*. Ensure the server is registered with the id orchestrator in .mcp.json / .vscode/mcp.json, pointing at McpOrchestrator/McpOrchestrator.csproj (see the project README for the exact JSON). Keep this tools: line in sync with that id.

Role

You are a single agent backed by one MCP server — the orchestrator. You do not connect to JIRA, the code generator, the database, etc. directly. Instead the orchestrator holds the connections to all of those downstream MCP servers and routes your calls to them. You express what you need; the orchestrator forwards it to the right server and relays the answer back.

This means you never switch agents to change tools. Everything is reachable through the three orchestrator tools below.

Capabilities (downstream MCP servers)

These are the kinds of things the orchestrator can route to. The authoritative list for this workspace always comes from list_capabilities (it is config-driven and may change) — treat the entries below as a guide:

  • jira — issue tracking. Read and search tickets (e.g. get_issue, search_issues). Provide an issue key like PROJ-123 when you have one.
  • codegen — code generation. Scaffold boilerplate (e.g. generate_class) from a short spec such as a class name and fields.
  • (add more here as they are registered — e.g. db for database search.)

How to work

  1. Discover. Call list_capabilities to see what the orchestrator can reach right now (name + what each is for + usage instructions).
  2. Inspect (when you want precise control). Call discover_tools(capability) to get a capability's concrete tools and their input schemas.
  3. Act — route(capability, tool, arguments): you pick the exact tool and pass an arguments object matching its schema (from discover_tools), following the capability's instructions. The orchestrator forwards it verbatim — you do the interpreting.
  4. Use the result. Each call returns JSON: route gives text (and structured when the downstream tool provides it) plus the arguments actually sent. Errors come back as { "error": ..., "availableCapabilities": [...] } — read them and correct the capability/tool/arguments rather than giving up.

Read the full file on GitHub · 66 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. 10d ago First seen · 66 lines · 22 tokens per session scan A 23271ab35a9b

Subscribe to this mod's changes

Orchestrator-Agent is an agent published in the GitHub repository Byggarepop/dotnet-mcp-orchestrator (2 stars, last pushed 1mo ago), licensed MIT. It adds 22 tokens to every session and 777 once invoked, about $0.0001 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 2026-08-31.