npu-vision-fallback AGENTS.md

npu-vision-fallback AGENTS.md is an instructions file for Codex, OpenCode from Byte-Naut/npu-vision-fallback. It costs 1,764 tokens per session, scanned A, original, MIT.

Project instructions for AI coding assistants working on an NPU vision fallback project. They define rules for local processing, hardware choices, optional software backends, privacy, and testing.

In plain words
What is it for?
Use them when modifying or testing the Byte-Naut/npu-vision-fallback project. They also document the commands, architecture guidance, and deviations that agents should follow.
Why use it?
They give coding agents the project's constraints before they change code. This helps prevent cloud calls, unwanted GPU use, heavy required dependencies, crashes when optional backends are missing, and saved screenshots or OCR text in logs.

Instructions file for CodexOpenCode

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/byte-naut/npu-vision-fallback/agents-md
Clone the repo
git clone --depth 1 https://github.com/Byte-Naut/npu-vision-fallback

Made for: Codex, OpenCode.

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 npu-vision-fallback AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/byte-naut/npu-vision-fallback/agents-md.svg)](https://agentmods.dev/instructions/byte-naut/npu-vision-fallback/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/byte-naut/npu-vision-fallback/agents-md"><img src="https://agentmods.dev/badge/instructions/byte-naut/npu-vision-fallback/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,764 This file is loaded in full into every session.
When invoked 1,764 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 $0.01764 $0.01764
Opus 5 $0.00882 $0.00882
Sonnet 5 $0.00353 $0.00353
Haiku 4.5 $0.00176 $0.00176

Measured 3d ago against content hash 29ad6a5da1db, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

npu-vision-fallback AGENTS.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 3d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

AGENTS.md · 159 lines

How it starts

The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — Project Constitution

This file is read by AI coding assistants (Claude Code, Codex, OpenCode) to understand the constraints of this project. Violating these principles requires updating this document and explicit maintainer approval.

It also serves as the day-to-day guide for build/test commands and the high-level architecture. Read it fully before making changes.


Core Principles

  1. Local-first. All inference must run locally. No cloud API calls except in explicit examples/remote_*.py demos.

  2. GPU-avoidant. By default, code paths must NOT wake up discrete GPUs. Prefer NPU > CPU > System OCR > dGPU.

  3. Lightweight core. Core dependencies must not include torch, torchvision, paddlepaddle, or tensorflow. These stay optional. (See Known Deviations for the current ultralytics exception.)

  4. Backend-optional. openvino, ultralytics, rapidocr_onnxruntime, and the Windows winrt-* packages must all be gracefully import-guarded. A missing backend means fallback, not crash.

  5. No screenshot persistence. Never write screenshots to disk by default. Logs must not include OCR text content (privacy).

  6. Coordinate integrity. OCR/detection backends return backend-local coordinates; the Orchestrator is solely responsible for remapping to absolute screen coordinates. Don't double-shift.

  7. Fail loudly, degrade gracefully. An unavailable backend should log a warning and fall through to the next. Never silently return an empty result with ok=True when the real backend is broken.

  8. Test invariants. All tests must pass on Linux CI (using dummy / rapid_ocr). Platform-specific tests are gated by pytest marks: windows_only, macos_only, npu_required.

  9. One tool = one responsibility. Adding a new MCP tool requires updating the README, tests/, and the tool's inputSchema in mcp_server.py.

  10. Privacy-by-default. Respect any blocked_window_titles config. Never log text that comes from OCR'd screenshots.

Read the full file on GitHub · 159 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. 3d ago First seen · 159 lines · 1,764 tokens per session scan A 29ad6a5da1db

Subscribe to this mod's changes

npu-vision-fallback AGENTS.md is an instructions file published in the GitHub repository Byte-Naut/npu-vision-fallback (1 stars, last pushed 1mo ago), licensed MIT. It adds 1,764 tokens to every session, about $0.0088 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 2026-08-31.

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