Borrowing it
Nothing to install: this file belongs to skyvanguard/claude-nexus. 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/skyvanguard/claude-nexus/main/CLAUDE.mdgit clone --depth 1 https://github.com/skyvanguard/claude-nexusWrote 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/instructions/skyvanguard/claude-nexus/claude-md)<a href="https://agentmods.dev/instructions/skyvanguard/claude-nexus/claude-md"><img src="https://agentmods.dev/badge/instructions/skyvanguard/claude-nexus/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.
<a href="https://agentmods.dev/instructions/skyvanguard/claude-nexus/claude-md"><img src="https://agentmods.dev/badge/instructions/skyvanguard/claude-nexus/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.02165 | $0.02165 |
| Opus 5 | $0.01082 | $0.01082 |
| Sonnet 5 | $0.00433 | $0.00433 |
| Haiku 4.5 | $0.00216 | $0.00216 |
Grade A, and why
claude-nexus 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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
claude-nexus
Peer discovery and messaging MCP channel for Claude Code instances. When several Claude Code sessions run on one machine, each can discover the others and exchange messages that arrive instantly via the claude/channel protocol.
Commands
bun install # install dependencies
# Run components directly
bun broker.ts # start the broker daemon manually (normally auto-launched)
bun server.ts # run the MCP stdio server (normally spawned by Claude Code)
# CLI (inspect/interact with a running broker)
bun cli.ts status # broker health + all registered peers
bun cli.ts peers # list peers
bun cli.ts send <peer-id> <msg> # inject a message into a peer's session
bun cli.ts kill-broker # stop the broker daemon
# Tests
bun test # run all tests
bun test <file> # run a single test file
There is no build step, linter, or test suite committed yet — TypeScript runs directly under Bun. tsconfig.json is noEmit with strict on (used for type-checking/editor only).
Running with Claude Code
# Full experience (instant channel push of inbound messages):
claude --dangerously-load-development-channels server:claude-nexus
# As a plain MCP (tools work, but no automatic push) — via .mcp.json:
# { "claude-nexus": { "command": "bun", "args": ["./server.ts"] } }
Requires Claude Code v2.1.80+ and a claude.ai login (channels do not work with API-key auth).
Architecture
Two processes cooperate over localhost HTTP:
broker.ts— a singleton daemon on127.0.0.1:7899backed by a SQLite DB (bun:sqlite, WAL mode). Owns thepeersandmessagestables and routes all traffic. One per machine.server.ts— an MCP stdio server, one spawned per Claude Code instance. On startup it callsensureBroker()(auto-launchesbroker.tsdetached viaBun.spawn(...).unref()if/healthis unreachable), registers itself, then runs two timers: a 1s poll for inbound messages and a 15s heartbeat.shared/types.ts— the broker's HTTP request/response contract, imported by both sides. Change a payload here and updatebroker.tshandlers +server.ts/cli.tscallers together.shared/summarize.ts— best-effort auto-summary of what an instance is working on (see below).cli.ts— standalone HTTP client for the broker; uses the same endpoints as the server. It sends messages withfrom_id: "cli"(a synthetic sender, not a registered peer).index.ts— module marker only; there is no single library entry point.
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.
- 8d ago First seen · 124 lines · 2,165 tokens per session scan A 792b0969e3c6
claude-nexus CLAUDE.md is an instructions file published in the GitHub repository skyvanguard/claude-nexus (0 stars, last pushed 1mo ago), licensed MIT. It adds 2,165 tokens to every session, about $0.0108 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.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.