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.
npx agentmods add rules/matthewdcage/llm-swarm-router/netllmgit 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/rules/matthewdcage/llm-swarm-router/netllm)<a href="https://agentmods.dev/rules/matthewdcage/llm-swarm-router/netllm"><img src="https://agentmods.dev/badge/rules/matthewdcage/llm-swarm-router/netllm.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00027 | $0.00307 |
| Opus 5 | $0.00014 | $0.00153 |
| Sonnet 5 | $0.00005 | $0.00061 |
| Haiku 4.5 | $0.00003 | $0.00031 |
Grade A, and why
netllm 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 6d 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.
What it actually says
When the user asks to install, set up, connect, swarm, or troubleshoot netllm or swarm-llm, load the matching skill from .cursor/skills/:
For PR checks, release, macOS menubar builds, or CI failures on menubar-lifecycle: read docs/ci-and-release.md and run scripts/verify-before-pr.sh before claiming green. Do not bump Package.swift to Swift 6 without updating runners.
| Intent | Skill path |
|---|---|
| First-time install, clone setup | .cursor/skills/netllm-setup/SKILL.md |
| Wire Cursor, Claude Code, Codex, Honcho | .cursor/skills/netllm-connect-editor/SKILL.md |
| LAN mesh, multi-machine, peers, gateway | .cursor/skills/netllm-swarm/SKILL.md |
| Broken agent, no models, doctor | .cursor/skills/netllm-doctor/SKILL.md |
Follow the skill workflow exactly. Prefer ./netllm from repo root. Project context: AGENTS.md.
Do not commit changes or edit user .env / editor settings without explicit permission.
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.
- 6d ago First seen · 20 lines · 27 tokens per session scan A 28ba8bdb2804
netllm is a cursor rule published in the GitHub repository matthewdcage/llm-swarm-router (25 stars, last pushed 4d ago), licensed MIT. It adds 27 tokens to every session and 307 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 2026-08-30.
Other cursor rules, from other repositories
python-app
Here's how the python application is organized.
pytest-integration-tests
Below is an example test. Notice the following.
alembic-migrations
To add a non-nullable column and set a specific value for all existing rows without a persistent server default.
nauro-ship-task
Run the full planner -> executor -> reviewer -> tech-lead -> direct-user-confirm -> push chain through Cursor's native project workflow agents. Requires the four bundled .cursor/agents/nauro-.md definitions and fails closed without native dispatch.
testing
Testing contract — how to build and run tests in this repo.
codesynapse-cli
Use this rule to answer codebase architecture questions, trace dependencies, find callers/callees, calculate blast radius, and explore the code graph. Triggers on: "how does X work", "what handles Y", "where is Z defined", "explain the mechanism", "who calls", "blast radius", "shortest path", "trace request flow"…