agentmods.dev

llm-swarm-router: Instructions file for Claude Code

CLAUDE.md

llm-swarm-router CLAUDE.md is an instructions file for Claude Code from matthewdcage/llm-swarm-router. It costs 415 tokens per session, scanned A, original, MIT.

Instructions for working on an application that routes requests between language models running on different machines. It also covers Honcho, a memory service that stores and retrieves conversation context.

In plain words
What is it for?
Installing and connecting the router, joining a local network of machines, diagnosing configuration problems, syncing agent skills, and recording or retrieving session context.
Why use it?
It gives coding agents the project’s setup, troubleshooting, release, and shared-memory rules in one place.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions Claude Code; mentions AGENTS.md.

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 →

not rated 26repo 7d ago A scan 415 tokens original MIT
View source ↗ matthewdcage/llm-swarm-router
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/CLAUDE.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 llm-swarm-router CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/matthewdcage/llm-swarm-router/claude-md"><img src="https://agentmods.dev/badge/instructions/matthewdcage/llm-swarm-router/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 415 This file is loaded in full into every session.
When invoked 415 The same file — it is already loaded in full.
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 $0.00415 $0.00415
Opus 5.5 $0.00166 $0.00166
Sonnet 5.5 $0.00083 $0.00083
Haiku 4.5 $0.00042 $0.00042

Measured 2mo ago against content hash d0f81d9a86a6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

llm-swarm-router CLAUDE.md 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 2mo 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.

CLAUDE.md · 28 lines

What it actually says

Claude Code: swarm-llm

Primary project guide: AGENTS.md (commands, architecture, do-not rules). DOX protocol: root Child DOX Index + per-folder contracts under packages/, apps/, docs/, etc. (.cursor/agents/ is gitignored local coordinator/DOX copy).

Slash commands (.claude/commands/):

  • /netllm-setup: first-time install from this repo
  • /netllm-connect: wire Cursor, Claude Code, Codex, or Honcho to the router
  • /netllm-swarm: multi-machine LAN mesh
  • /netllm-doctor: troubleshoot misconfigurations

Skills live in .claude/skills/ (canonical source: .agents/skills/). Run scripts/sync-agent-skills.sh after editing skills.

CI / release / macOS builds: docs/ci-and-release.md · pre-push: scripts/verify-before-pr.sh

Honcho Memory (MCP)

The honcho MCP server is available via .cursor/mcp.json. Protocol:

  1. Read .cursor/hooks/state/honcho-state.json — get session ID, check if context is stale
  2. Load context if stale: get_peer_context(peer_id: "Assistant", target_peer_id: "matthewcage")
  3. Record turns: add_messages_to_session after each exchange
  4. Query memory: chat(peer_id: "Assistant", query: "...", target_peer_id: "matthewcage")
  5. Setup/repair: call setup_agent_workspace to restore any missing files

Full protocol: .cursor/rules/honcho_rules.mdc

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. 2mo ago First seen · 28 lines · 415 tokens per session scan A d0f81d9a86a6

Subscribe to this mod's changes

llm-swarm-router CLAUDE.md is an instructions file published in the GitHub repository matthewdcage/llm-swarm-router (26 stars, last pushed 7d ago), licensed MIT. It adds 415 tokens to every session, about $0.0017 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 2026-08-30.

LLManthropic-apicursorllama-cpplm-studiolocal-llm
Related

llm-swarm-router CLAUDE.md compared with instructions from other repositories

llm-swarm-router CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
llm-swarm-router CLAUDE.mdmatthewdcage/llm-swarm-routerInstructions file267d agoMITA415Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode