nexus CLAUDE.md

nexus CLAUDE.md is an instructions file for Claude Code from PermaShipAI/nexus. It costs 1,089 tokens per session, scanned A, original, MIT.

Setup and working instructions for Nexus Command, a locally running browser application in which multiple specialist AI agents collaborate on software development.

In plain words
What is it for?
Installing dependencies, starting the local web interface, configuring an AI provider, understanding available environment variables, and finding the project's main scripts.
Why use it?
They explain how to start the project without Docker or a separate PostgreSQL server, how the local database works, and when an API key is needed.

Instructions file for Claude Code

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

Install

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.

agentmods
npx agentmods add instructions/permashipai/nexus/claude-md
Clone the repo
git clone --depth 1 https://github.com/PermaShipAI/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 nexus CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/permashipai/nexus/claude-md.svg)](https://agentmods.dev/instructions/permashipai/nexus/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/permashipai/nexus/claude-md"><img src="https://agentmods.dev/badge/instructions/permashipai/nexus/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,089 This file is loaded in full into every session.
When invoked 1,089 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.01089 $0.01089
Opus 5 $0.00544 $0.00544
Sonnet 5 $0.00218 $0.00218
Haiku 4.5 $0.00109 $0.00109

Measured 6d ago against content hash ca71f948db64, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

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 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.

CLAUDE.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — AI-Assisted Setup Guide

This file helps AI coding assistants (Claude Code, Cursor, Copilot, etc.) understand how to set up and work with this project.

IMPORTANT: How to Start This Project

npm install
npm run dev

That's it. Do NOT start Docker or PostgreSQL. Do NOT set DISCORD_BOT_TOKEN. Do NOT manually create a .env file.

The npm run dev command:

  1. Prompts in the terminal for your LLM provider + API key (first run only)
  2. Saves the key to .env automatically
  3. Uses an embedded database (PGlite) — no Postgres needed
  4. Starts a web UI at http://localhost:3000

If the user already has a .env with LLM_API_KEY or GEMINI_API_KEY, the prompt is skipped.

What This Is

Nexus Command is a multi-agent AI system with 10 specialist agents (CISO, SRE, QA Manager, etc.) that collaborate on software development. It runs locally in a browser at http://localhost:3000.

Environment Variables

Only needed if you want to override defaults. The system works with zero env vars (it will prompt for the API key).

Variable Required Default Description
LLM_API_KEY Yes (prompted) - API key for your LLM provider
LLM_PROVIDER No gemini gemini, anthropic, openai, ollama, openrouter
DATABASE_URL No embedded PGlite PostgreSQL connection string (overrides embedded DB)
EXECUTION_BACKEND No noop claude-code, gemini-cli, codex-cli, openclaw, permaship
LOCAL_UI_PORT No 3000 Port for the web UI
LOG_LEVEL No info debug for verbose output

Do NOT set or require: DISCORD_BOT_TOKEN, DISCORD_CLIENT_ID, COMMS_SIGNING_SECRET, PERMASHIP_API_KEY, or any PermaShip-specific variables. These are only for the PermaShip deployment profile, not for local development.

Scripts

Script Purpose
npm run dev Start the local UI (this is the main command)
npm start Same as npm run dev
npm run dev:server Start the webhook server (Discord/Slack mode — requires additional config)
npm run build Compile TypeScript
npm run typecheck Type checking
npm run test:run Run tests

Read the full file on GitHub · 100 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. 6d ago First seen · 100 lines · 1,089 tokens per session scan A ca71f948db64

Subscribe to this mod's changes

nexus CLAUDE.md is an instructions file published in the GitHub repository PermaShipAI/nexus (57 stars, last pushed 1mo ago), licensed MIT. It adds 1,089 tokens to every session, about $0.0054 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.