ovo AGENTS.md

ovo AGENTS.md is an instructions file for Codex, OpenCode from dushaobindoudou/ovo. It costs 781 tokens per session, scanned A, original, MIT.

Project instructions for Ovo, an Electron desktop assistant with several windows and features such as reading text from images, spoken output, a knowledge graph, and Codex API integration. Electron is a framework for building desktop apps with web technologies.

In plain words
What is it for?
Use them when developing Ovo, starting its development environment, checking TypeScript and code style, running agent tests, verifying scenarios, or creating a packaged build.
Why use it?
They give developers the project’s layout and the commands needed to run, check, test, build, and package the application.

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/dushaobindoudou/ovo/agents-md
Clone the repo
git clone --depth 1 https://github.com/dushaobindoudou/ovo

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 ovo AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/dushaobindoudou/ovo/agents-md.svg)](https://agentmods.dev/instructions/dushaobindoudou/ovo/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/dushaobindoudou/ovo/agents-md"><img src="https://agentmods.dev/badge/instructions/dushaobindoudou/ovo/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 781 This file is loaded in full into every session.
When invoked 781 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 $0.00781 $0.00781
Opus 5 $0.00391 $0.00391
Sonnet 5 $0.00156 $0.00156
Haiku 4.5 $0.00078 $0.00078

Measured 5d ago against content hash c9d07945d8c9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ovo 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 5d 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 · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

This file provides guidance to Codex (Codex.ai/code) when working with code in this repository.

Project Overview

Ovo is an Electron-based proactive AI desktop assistant. The app runs multiple windows: a main console window, a floating icon, and a suggestion panel. It integrates OCR, TTS, knowledge graph, and Codex API for AI capabilities.

Common Commands

# Development
pnpm dev                    # Start both renderer and electron in dev mode
pnpm dev:renderer           # Start Vite dev server only (port 5173)
pnpm dev:electron           # Start Electron with live reload

# Build
pnpm build                  # Build both renderer and electron
pnpm build:renderer         # Build React/Vite frontend
pnpm build:electron         # Compile TypeScript to electron/

# Type checking and linting
pnpm typecheck              # Run TypeScript on both renderer and electron
pnpm lint                   # Run ESLint

# Testing
pnpm test:agents            # Run agent smoke tests (scripts/smoke-agents.ts)
pnpm verify:p0             # Run P0 verification script
pnpm verify:real30         # Run 30-scenario real log verification

# Packaging
pnpm pack:dir               # Package as unpacked directory
pnpm pack:mac               # Package as macOS DMG
pnpm pack:all               # Package for all platforms

# CI
pnpm test:ci                # typecheck && lint && build && test:agents

Architecture

Electron Process (electron/)

  • main.ts: Entry point, creates BrowserWindows for console (#console), floating (#float), and suggestion (#panel) windows
  • preload.cjs: Context bridge exposing IPC APIs to renderer
  • ipc-handlers.ts: Central IPC handler registration
  • window-manager.ts: Window lifecycle management
  • agent-bridge.ts: Codex API communication
  • pipeline-logger.ts: Logging pipeline stages
  • knowledge-graph.ts: SQLite-based entity relationship storage (better-sqlite3)
  • ocr-engine.ts: Tesseract.js OCR integration
  • tts-engine.ts: Text-to-speech functionality
  • action-executor.ts: Executes AI-suggested actions
  • screenshot.ts: Screen capture functionality

Read the full file on GitHub · 83 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. 5d ago First seen · 83 lines · 781 tokens per session scan A c9d07945d8c9

Subscribe to this mod's changes

ovo AGENTS.md is an instructions file published in the GitHub repository dushaobindoudou/ovo (10 stars, last pushed 19d ago), licensed MIT. It adds 781 tokens to every session, about $0.0039 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

opencove AGENTS.md

AGENTS.md instructions for DeadWaveWave/opencove, covering system prompt: opencove project ai developer agent, 1. core directives & golden rules, 2. decision framework (small vs large), a. small change (fast feedback / 小步快反馈) and b. large change (deep thinking / 慎重对齐).

DeadWaveWave/opencove · 1,183 tokens

wesight AGENTS.md

Instructions for freestylefly/wesight, covering claude.md, build and development commands, build production bundle (typescript + vite), lint with eslint and run memory extractor tests (node.js built-in test runner).

freestylefly/wesight · 6,627 tokens

limboo CLAUDE.md

Claude Code instructions for limboo-ai/limboo, covering claude.md, 1. what is limboo?, 2. tech stack (current), 3. project structure and the three electron contexts (critical mental model).

limboo-ai/limboo · 25,202 tokens

nextclaw AGENTS.md

AGENTS.md instructions for Peiiii/nextclaw, covering nextclaw ai 常驻内核, 产品愿景, 沟通与推进, 深思与目标模式 and 协作与 git 安全.

Peiiii/nextclaw · 3,095 tokens

ChatCrystal AGENTS.md

AGENTS.md instructions for ZengLiangYi/ChatCrystal, covering agents.md, project overview, commands, development (server port 3721 + client port 13721) and build for production.

ZengLiangYi/ChatCrystal · 2,922 tokens

getvect AGENTS.md

Instructions for craigjmidwinter/getvect, covering agents.md, commands (green on a clean checkout), invariants a pr must not break and process.

craigjmidwinter/getvect · 961 tokens