n2n-nexus: Instructions file for Claude Code

CLAUDE.md

n2n-nexus CLAUDE.md is an instructions file for Claude Code from n2ns/n2n-nexus. It costs 1,976 tokens per session, scanned A, original, Apache-2.0.

A project instruction file for n2n-nexus, documenting its commands, tests, local servers, and code structure.

In plain words
What is it for?
Running all tests or one test file, starting the daemon or MCP server locally, and understanding the TypeScript entry points and architecture.
Why use it?
It gives the coding agent the repository-specific details needed to build, test, lint, and run the project correctly.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code; mentions Codex.

This is n2ns/n2n-nexus's own configuration. It tells Claude Code how to work on n2n-nexus 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 n2n-nexus configures →

Reuse

Borrowing it

Nothing to install: this file belongs to n2ns/n2n-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.

Copy the file
curl -O https://raw.githubusercontent.com/n2ns/n2n-nexus/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/n2ns/n2n-nexus

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 n2n-nexus CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/n2ns/n2n-nexus/claude-md/github.svg)](https://agentmods.dev/instructions/n2ns/n2n-nexus/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/n2ns/n2n-nexus/claude-md"><img src="https://agentmods.dev/badge/instructions/n2ns/n2n-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.

agentmods 80×15 button for n2n-nexus CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/n2ns/n2n-nexus/claude-md"><img src="https://agentmods.dev/badge/instructions/n2ns/n2n-nexus/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,976 This file is loaded in full into every session.
When invoked 1,976 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 $0.01976 $0.01976
Opus 5.5 $0.00790 $0.00790
Sonnet 5.5 $0.00395 $0.00395
Haiku 4.5 $0.00198 $0.00198

Measured 9d ago against content hash af1983761e5f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

n2n-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 9d 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 · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 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.

Commands

npm run build            # tsc → build/
npm run dev              # tsc -w (watch mode)
npm run lint             # eslint src tests
npm test                 # vitest run: client tests (globalSetup builds the client and the Go test host first)
npm run host:build-test  # go build -tags testclock → host/bin/test/n2n-nexus-host
npm run test:conformance # black-box tests in tests/conformance/ against NEXUS_HOST_BIN (default: the test build)
npm run check            # lint, test, build, audit, pack dry run (prepublishOnly)

go vet ./...
go test ./host/...

# Run a single client test file
npx vitest run tests/mcp_proxy.test.ts

# Run the host locally (foreground, no tray)
go run ./host/cmd/n2n-nexus-host serve --port 5799 --root /tmp/x

# Run the MCP adapter against it
NEXUS_ENDPOINT=http://127.0.0.1:5799 node build/index.js mcp

Hooks (lefthook): pre-commit runs npm run lint; pre-push runs go vet ./... && go test ./host/... && npm run build && npm test && npm run host:build-test && npm run test:conformance.

CI (.github/workflows/host.yml) runs go vet, go test ./host/..., lint, build, npm test, the test-host build and the conformance tests on ubuntu, windows and macos for every push to main and every pull request. Releases: v* tags publish the npm client (publish.yml); host-v* tags build and release the host (host-release.yml, see host/README.md).

Architecture

Two programs share one protocol. See docs/ARCHITECTURE.md for the full design.

Contract (contract/)

The single source of the protocol: tools.json (every tool's name, title, description, annotations, input and output JSON Schema), hook.json (hook clients, request fields, _meta keys, the LAN discovery query, timings, limits, notification texts), errors.json (endpoints, error body, status codes). The Go host embeds them (contract/contract.go), the TypeScript client reads hook.json at run time (src/contract.ts), and the conformance tests read all three. Bump contractVersion in all three files when a change breaks an older client or host. See contract/README.md.

Read the full file on GitHub · 85 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. 9d ago Changed · +1 lines · +67 tokens per session af1983761e5f
  2. 12d ago Changed · +26 tokens per session 2c95d6d9c24e
  3. 14d ago Changed · +14 lines · +506 tokens per session b0c6e1735171
  4. 16d ago Changed · +34 tokens per session 4af06855f6a8
  5. 17d ago Changed · +3 lines · +255 tokens per session 838d776d6111
  6. 18d ago Changed · +47 tokens per session 81385435199e
  7. 22d ago Changed · +6 lines · +336 tokens per session 85d56ae09943
  8. 2mo ago First seen · 61 lines · 705 tokens per session scan A 9962601d5ece

Subscribe to this mod's changes

n2n-nexus CLAUDE.md is an instructions file published in the GitHub repository n2ns/n2n-nexus (14 stars, last pushed 3d ago), licensed Apache-2.0. It adds 1,976 tokens to every session, about $0.0079 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.

Related

n2n-nexus CLAUDE.md compared with instructions from other repositories

n2n-nexus CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
n2n-nexus CLAUDE.mdn2ns/n2n-nexusInstructions file143d agoApache-2.0A1,976Claude 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