NeoMind: Instructions file for Claude Code

CLAUDE.md

NeoMind CLAUDE.md is an instructions file for Claude Code from camthink-ai/NeoMind. It costs 5,387 tokens per session, scanned A, original, Apache-2.0.

Project instructions for NeoMind, an edge AI platform that runs on local devices and connects to hardware such as sensors through several communication methods.

In plain words
What is it for?
Use them when developing NeoMind's Rust backend, React and Tauri applications, extensions, device templates, or related repositories.
Why use it?
They give developers the commands, repository structure, and file formats needed to build and extend the platform consistently.

Instructions file for Claude Code

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

This is camthink-ai/NeoMind's own configuration. It tells Claude Code how to work on NeoMind 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 NeoMind configures →

Reuse

Borrowing it

Nothing to install: this file belongs to camthink-ai/NeoMind. 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/camthink-ai/NeoMind/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/camthink-ai/NeoMind

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 NeoMind CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/camthink-ai/neomind/claude-md/github.svg)](https://agentmods.dev/instructions/camthink-ai/neomind/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/camthink-ai/neomind/claude-md"><img src="https://agentmods.dev/badge/instructions/camthink-ai/neomind/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 NeoMind CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/camthink-ai/neomind/claude-md"><img src="https://agentmods.dev/badge/instructions/camthink-ai/neomind/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 5,387 This file is loaded in full into every session.
When invoked 5,387 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 $0.05387 $0.05387
Opus 5.5 $0.02155 $0.02155
Sonnet 5.5 $0.01077 $0.01077
Haiku 4.5 $0.00539 $0.00539

Measured yesterday against content hash 0a97947817ab, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

NeoMind 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 yesterday.

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 · 209 lines

How it starts

The opening of the file, as written. The whole thing — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.

NeoMind — Edge AI Platform for IoT

Rust (Axum) backend + React 18 + Tauri 2.x desktop. Runs LLM agents on local hardware, connects devices via MQTT/BLE/Webhook, automates via a rule engine, visualizes on real-time dashboards.

The spine is an async EventBus (neomind_core::eventbus) — all subsystems (devices, agents, rules, dashboards, frontend WS/SSE) communicate via pub/sub events, not direct calls.

Development Commands

cargo build && cargo test && cargo run -p neomind-cli -- serve   # API on :9375, swagger at /api/docs
cd web && npm install && npm run dev                              # frontend :5173
cd web && npm run tauri:dev                                       # desktop app

The gate CI actually runs

cargo test --workspace is NOT it. behavior_tests.rs and the mock-LLM suites are gated behind neomind-agent/test-utils, so a plain workspace run skips them and reports green on a tree CI would fail. Use:

cargo test --workspace --locked --features neomind-agent/test-utils

scripts/verify-all.sh already uses this exact command — prefer it.

Ecosystem Repositories

NeoMind is the core platform; three companion repos hold community content. This repo defines the format contracts each must follow.

Repo Contains Loaded by this repo as
NeoMind (this) Backend + frontend + desktop app —
NeoMind-Extensions Official extension marketplace (weather, YOLO, OCR, face, HA/LoRaWAN/Modbus bridges, stream player…) .nep packages → data/extensions/<id>/
NeoMind-DeviceTypes Standardized device type JSON templates (e.g. NE301, NE101 cameras) JSON imported into the device registry
NeoMind-Dashboard-Components Community dashboard widget marketplace (charts, gauges, maps…) Bundles → data/frontend-components/<id>/

Read the full file on GitHub · 209 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. yesterday Changed · +27 tokens per session 0a97947817ab
  2. 8d ago Changed · +94 tokens per session 7b1511651789
  3. 26d ago Changed · -8 tokens per session df9607a98507
  4. 27d ago Changed · +1 lines · +111 tokens per session fee20368afa1
  5. 1mo ago Changed · +21 lines · +706 tokens per session 0c53de79cc9c
  6. 2mo ago Changed · +1 lines · +161 tokens per session eb29b5105ded
  7. 2mo ago First seen · 186 lines · 4,296 tokens per session scan A 5f80b5b92b4d

Subscribe to this mod's changes

NeoMind CLAUDE.md is an instructions file published in the GitHub repository camthink-ai/NeoMind (60 stars, last pushed yesterday), licensed Apache-2.0. It adds 5,387 tokens to every session, about $0.0215 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

NeoMind CLAUDE.md compared with instructions from other repositories

NeoMind CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
NeoMind CLAUDE.mdcamthink-ai/NeoMindInstructions file60yesterdayApache-2.0A5,387Claude 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