llm-swarm-router: Skill for Claude Code

.agents/skills/netllm-setup/SKILL.md

netllm-setup is a skill for Claude Code from matthewdcage/llm-swarm-router. It costs 118 tokens per session (1,666 once invoked), scanned A, original, MIT.

An installation and first-run guide for netllm, a tool that connects language-model servers and can route requests between them. It sets up the program from a downloaded code repository and checks that its router is working.

In plain words
What is it for?
Use it to install netllm on macOS, Linux, or Windows, initialize a single or shared setup, discover supported model servers, and verify the router before connecting an editor.
Why use it?
It removes the guesswork from installing dependencies, creating initial settings, finding local model servers, and confirming the service is reachable.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions Claude Code; installed under .agents/ (shared by several agents); mentions Codex.

This is matthewdcage/llm-swarm-router's own configuration. It tells Claude Code how to work on llm-swarm-router 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 llm-swarm-router configures →

Reuse

Borrowing it

Nothing to install: this file belongs to matthewdcage/llm-swarm-router. 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/matthewdcage/llm-swarm-router/main/.agents/skills/netllm-setup/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/matthewdcage/llm-swarm-router

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 netllm-setup

README.md
[![agentmods](https://agentmods.dev/badge/skills/matthewdcage/llm-swarm-router/netllm-setup/github.svg)](https://agentmods.dev/skills/matthewdcage/llm-swarm-router/netllm-setup)
Your own site
<a href="https://agentmods.dev/skills/matthewdcage/llm-swarm-router/netllm-setup"><img src="https://agentmods.dev/badge/skills/matthewdcage/llm-swarm-router/netllm-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.

agentmods 80×15 button for netllm-setup

Your own site · 80×15
<a href="https://agentmods.dev/skills/matthewdcage/llm-swarm-router/netllm-setup"><img src="https://agentmods.dev/badge/skills/matthewdcage/llm-swarm-router/netllm-setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 118 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,666 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Rogue Agent · line 46
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
How audits are shown
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 $0.00118 $0.01666
Opus 5 $0.00059 $0.00833
Sonnet 5 $0.00024 $0.00333
Haiku 4.5 $0.00012 $0.00167

Measured 10d ago against content hash 96d6a5dc5de3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

netllm-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 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.

.agents/skills/netllm-setup/SKILL.md · 137 lines

How it starts

The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.

netllm setup

When to use this skill

  • First-time install from a git clone
  • User says "set up netllm", "install swarm-llm", or /netllm-setup
  • Agent needs to verify the router is healthy before editor integration

Prerequisites

  • macOS, Linux, or Windows
  • git on PATH
  • uv on PATH: if missing, tell user to install from https://docs.astral.sh/uv/
  • Repo root contains pyproject.toml with name = "netllm" and [tool.uv.workspace]
  • At least one inference server is optional but warn if none are online after discover: Ollama :11434, LM Studio :1234, vLLM :8000; oMLX :8080 on macOS only

Install paths

User preference Steps
macOS menubar (macOS 26+) Clone latest release taguv syncuv pip install venvstacksapps/netllm-mac/Scripts/build.sh releasepackaging/scripts/macos-app-install.sh --source apps/netllm-mac/build/Stage/llm-swarm-router.app. GitHub DMG is ad-hoc until notarized — see docs/macos-install.md.
macOS DMG (when notarized) Download llm-swarm-router.dmg from Releases → bundled macos-app-install.sh --dmg — not Gatekeeper-safe on macOS 26 until Developer ID notarization ships
Homebrew brew tap matthewdcage/netllm <repo>brew install netllmbrew services start netllm
Linux deb/rpm Install netllm_*_amd64.deb or netllm-*.rpm from Releases → netllm initsystemctl --user enable --now netllm. See docs/linux-install.md.
Windows zip Extract netllm-*-windows-x64.zip → run install-service.ps1 as Admin → netllm initnetllm start. See docs/windows-install.md.
Source / dev Workflow below (uv sync, ./netllm init, ./netllm serve)

DMG, Homebrew, systemd, and Windows service installs use netllm start / netllm stop. Source installs keep ./netllm serve (foreground).

Read the full file on GitHub · 137 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 · 137 lines · 118 tokens per session scan A 96d6a5dc5de3

Subscribe to this mod's changes

netllm-setup is a skill published in the GitHub repository matthewdcage/llm-swarm-router (25 stars, last pushed 8d ago), licensed MIT. It adds 118 tokens to every session and 1,666 once invoked, about $0.0006 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.

Related

Other skills, from other repositories

tiktok-video

A workflow for making vertical short videos for TikTok or Douyin from a written request. It creates a storyboard, voiceover, word-timed karaoke captions, background music, and a 1080×1920 MP4 video.

Fangyuan025/Chaty · 59 tokens

firebase-messaging

Use when setting up Firebase Cloud Messaging, managing permissions and tokens, handling background/foreground notification taps, or dispatching messages server-side (HTTP v1).

evanca/flutter-ai-rules · 35 tokens

karpathy-llm-wiki

Use when building or maintaining a personal LLM-powered knowledge base. Triggers: ingesting sources into a wiki, querying wiki knowledge, linting wiki quality, 'add to wiki', 'what do I know about', or any mention of 'LLM wiki' or 'Karpathy wiki'.

Astro-Han/karpathy-llm-wiki · 67 tokens

firebase-cloud-functions

Use when calling callable functions (httpsCallable), passing data to server-side logic, handling function errors/timeouts, configuring regions, or testing with the Emulator Suite.

evanca/flutter-ai-rules · 36 tokens

excalidraw-architect

Choose and compose the right Excalidraw diagram - architecture, flowchart, sequence, state, ER, swimlane, process, timeline, quadrant, pyramid, venn, loop, gantt, bar, line, scatter, and more - using the excalidraw-architect-mcp server. Use whenever a reader would learn more from a picture than from prose, or when…

BV-Venky/excalidraw-architect-mcp · 101 tokens

lilbee-mcp

Search and manage the user's local lilbee knowledge base over MCP. Use whenever the user has indexed code, docs, PDFs, or web pages into lilbee and you need cited answers, or whenever they ask you to ingest content, swap models, or tune retrieval against their library. Every fact returned cites file and line.…

tobocop2/lilbee · 95 tokens