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.
curl -O https://raw.githubusercontent.com/matthewdcage/llm-swarm-router/main/.agents/skills/netllm-doctor/SKILL.mdgit clone --depth 1 https://github.com/matthewdcage/llm-swarm-routerWrote 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.
[](https://agentmods.dev/skills/matthewdcage/llm-swarm-router/netllm-doctor)<a href="https://agentmods.dev/skills/matthewdcage/llm-swarm-router/netllm-doctor"><img src="https://agentmods.dev/badge/skills/matthewdcage/llm-swarm-router/netllm-doctor/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.
<a href="https://agentmods.dev/skills/matthewdcage/llm-swarm-router/netllm-doctor"><img src="https://agentmods.dev/badge/skills/matthewdcage/llm-swarm-router/netllm-doctor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
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 53 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.
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 | $0.00081 | $0.01441 |
| Opus 5 | $0.00041 | $0.00720 |
| Sonnet 5 | $0.00016 | $0.00288 |
| Haiku 4.5 | $0.00008 | $0.00144 |
Grade A, and why
netllm-doctor scanned grade A with 1 finding 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 12d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sf http://127.0.0.1:11400/health || echo "agent down" 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 doctor
When to use this skill
- Setup failed or agent unreachable
- No models in
./netllm models - Swarm peers not discovered
- User says "netllm broken", "fix netllm", or
/netllm-doctor
Workflow
-
Run built-in doctor
./netllm doctorCapture each issue title and suggested fix from output.
-
PATH check
which netllm || true ./netllm --version- Repo checkout: prefer
./netllmfrom root - Global install:
~/.local/bin/netllm: run./netllm envfor PATH export if needed
- Repo checkout: prefer
-
Agent reachability
curl -sf http://127.0.0.1:11400/health || echo "agent down"If down, start by install channel:
- Source / dev:
./netllm serve(foreground) - macOS app / Homebrew:
./netllm startor menubar → Restart Agent - Linux deb/rpm:
systemctl --user enable --now netllm: see docs/linux-install.md - Windows zip/winget:
netllm startafterinstall-service.ps1: see docs/windows-install.md
- Source / dev:
-
Local providers
./netllm discoverExpected ports: Ollama
11434, LM Studio1234, vLLM8000; oMLX8080on macOS only -
Config review, read
~/.config/netllm/config.toml(or path from user):agent.listen: loopback vs0.0.0.0agent.advertise: required for gateway roleswarm.mdns: needs zeroconf fromuv syncswarm.cluster_token: empty is fine on trusted home LAN (open swarm); set only for untrusted networks
-
Platform-specific swarm checks (when
./netllm peersis empty but LAN routing is expected):- All platforms:
./netllm doctornow prints per-platform firewall commands (UDP 5353 mDNS in/out + TCP 11400 in) when mDNS looks blocked. LAN-bound agents auto-run a one-shot subnet scan 10s after start when mDNS finds nothing. - Loopback peers:
./netllm peerslists loopback-bound agents as found but unreachable — fix is menubar LAN mode,netllm init --swarm, orserve --host 0.0.0.0on that machine - Token mismatches: heartbeats return 401; align tokens with
netllm swarm-token+netllm join URL --token T - Linux: mDNS uses Avahi via
python-zeroconf; install Avahi if browse fails. Fallback:swarm.peersor./netllm peers --subnet-scan --save - Windows: mDNS is often blocked by firewall or missing Bonjour: prefer static
swarm.peersor--subnet-scan. Allow inbound TCP on agent port (default11400) whenserve --host 0.0.0.0 - All platforms: Guest Wi‑Fi often blocks mDNS; loopback bind (
127.0.0.1) hides the agent from LAN peers
- All platforms:
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.
- 12d ago First seen · 137 lines · 81 tokens per session scan A 10ba25774efe
netllm-doctor is a skill published in the GitHub repository matthewdcage/llm-swarm-router (25 stars, last pushed 10d ago), licensed MIT. It adds 81 tokens to every session and 1,441 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
firebase-crashlytics
Use when implementing crash reporting, capturing fatal/non-fatal errors, recording isolate/async exceptions, customizing reports, or uploading obfuscated symbols.
flutter-errors
Use when hitting layout errors (RenderFlex overflow, unbounded constraints, RenderBox not laid out), scroll errors, or setState-during-build errors.
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.
security-review
Review flows, code paths, and configuration with a bias toward real exploit paths and practical mitigations.
bug-reproducer
Turn vague bug reports into minimal, deterministic reproduction steps.
session-logs
Use activity, logs, and execution traces to reconstruct what actually happened in the app.