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 instructions/permashipai/nexus/claude-mdgit clone --depth 1 https://github.com/PermaShipAI/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/permashipai/nexus/claude-md)<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>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 | $0.01089 | $0.01089 |
| Opus 5 | $0.00544 | $0.00544 |
| Sonnet 5 | $0.00218 | $0.00218 |
| Haiku 4.5 | $0.00109 | $0.00109 |
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.
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:
- Prompts in the terminal for your LLM provider + API key (first run only)
- Saves the key to
.envautomatically - Uses an embedded database (PGlite) — no Postgres needed
- 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 |
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 · 100 lines · 1,089 tokens per session scan A ca71f948db64
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.
Other instructions, from other repositories
Browser4 CLAUDE.md
Claude Code instructions for platonai/Browser4, covering browser4 — project context for claude, architecture, key dispatch chain (cli → browser), batch commands and e2e test structure.
cc-websearch CLAUDE.md
Claude Code instructions for Djarvur/cc-websearch, covering project, constraints, technology stack, what not to add and conventions.
fix-quera AGENTS.md
Instructions for AlirezaKeshavarz83/fix-quera, covering agent guidance, project shape, visual style, quera page data findings and compatibility findings.
sniff AGENTS.md
AGENTS.md instructions for Aboudjem/sniff, covering agents.md: sniff, what this repo is, how an agent should use sniff, handling the playwright setup gate and finding output schema.
fast-browser CLAUDE.md
Claude Code instructions for m4ttstack/fast-browser, covering fast browser plugin, where a change belongs, fork branch: use fast-browser-runtime, releasing a new runtime and re-pinning this repo: use the script.
sendblue-browser-use AGENTS.md
Instructions for sendblue-api/sendblue-browser-use, covering agents.md — sendblue-browser-use, what this repo is, setup, common commands and health (no auth).