vector-os-nano CLAUDE.md

vector-os-nano CLAUDE.md is an instructions file for coding agents from VectorRobotics/vector-os-nano. It costs 2,086 tokens per session, scanned A, original, Apache-2.0.

A project constitution for Vector OS Nano, a system that coordinates AI models, specialised tools, and actions for physical AI such as robots. It defines the project’s goals, required documentation, and rules for making changes.

In plain words
What is it for?
Use it when working on Vector OS Nano’s orchestration runtime, simulator, models, skills, robot integrations, or documentation and commit process.
Why use it?
It gives coding agents the project’s fixed priorities and constraints before they modify code. This helps preserve the intended model routing, verification, recovery, and simulator-focused design.

Instructions file

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/vectorrobotics/vector-os-nano/claude-md
Clone the repo
git clone --depth 1 https://github.com/VectorRobotics/vector-os-nano

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 vector-os-nano CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/vectorrobotics/vector-os-nano/claude-md.svg)](https://agentmods.dev/instructions/vectorrobotics/vector-os-nano/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/vectorrobotics/vector-os-nano/claude-md"><img src="https://agentmods.dev/badge/instructions/vectorrobotics/vector-os-nano/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,086 This file is loaded in full into every session.
When invoked 2,086 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 $0.02086 $0.02086
Opus 5 $0.01043 $0.01043
Sonnet 5 $0.00417 $0.00417
Haiku 4.5 $0.00209 $0.00209

Measured 4d ago against content hash 41ee902cc7a3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

vector-os-nano 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 4d 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 · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Vector OS Nano — Project Constitution

North Star — read this first (the goal every session serves)

Vector OS is an agent-orchestration runtime built around models, for physical AI. The four things models do unreliably on their own are exactly the OS's job: (1) plan the task, (2) route each instruction to the right model AND skill, (3) verify every step of execution, (4) recover automatically on failure. It orchestrates general large models, specialized small models, classical skills, and atomic actions into one deployable whole that is cross-hardware, cross-model, cross-system — always the best tool for each job. The agent's value is in choosing right, sequencing right, verifying right, and recovering when wrong — NOT in re-implementing navigation or manipulation itself.

Further, Vector OS is a programmable platform: developers build physical AI the way they write code (code physical AI) — any model, any skill, any robot, plug and play.

Current focus — sim. In a high-quality simulator, an agent is commanded in natural language to:

  • switch embodimentgo2, go2 + arm, g1, … on demand;
  • route each task to the right specialized model / skill pack, then close the loop (execute → verify → recover):
    • explore → nav stack TARE
    • navigate to a point → planner (FAR, …)
    • VLN (semantic navigation) → SysNav
    • manipulation → VLA, or the classical route VLM + point-cloud localization + IK

Robots are the end; sim is the current means of building and proving it. Verification only ever gets stricter, never looser — every step must prove it happened, never merely claim it.

Acceptance interface (NON-NEGOTIABLE). The owner tests EVERYTHING by typing bare vector-cli + natural language — no pytest/python/flags/scripts. Every capability must be reachable + demonstrable through the bare REPL by NL (launch/switch sim+embodiment by NL, command the task, the honest verdict surfaces in that conversation). pytest/PTY harnesses are INTERNAL only. A capability that only works behind a flag or -p and is unreachable from bare vector-cli + NL is NOT done.

Read the full file on GitHub · 93 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. 4d ago First seen · 93 lines · 2,086 tokens per session scan A 41ee902cc7a3

Subscribe to this mod's changes

vector-os-nano CLAUDE.md is an instructions file published in the GitHub repository VectorRobotics/vector-os-nano (166 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 2,086 tokens to every session, about $0.0104 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.

Related

Other instructions, from other repositories

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).

microsoft/vscode · 6,785 tokens

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.

github/spec-kit · 7,104 tokens

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.

openai/codex · 5,182 tokens

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.

langchain-ai/langchain · 4,345 tokens

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).

microsoft/vscode · 5,001 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens