nekoro-browser AGENTS.md

nekoro-browser AGENTS.md is an instructions file for Codex, OpenCode from zeshuochen/nekoro-browser. It costs 650 tokens per session, scanned A, original, MIT.

Project instructions for nekoro-browser, a tool that lets an AI agent control a user's everyday Chrome through a browser extension and a local helper program. It preserves the browser's existing login state instead of requiring a separate remote-debugging setup.

In plain words
What is it for?
Use them when modifying nekoro-browser, especially its Chrome extension, local daemon, browser-tab lifecycle, WebSocket connection, or command-line helpers.
Why use it?
They give contributors clear priorities and describe how the extension, local program, and browser-control connection fit together. They also require failures to be reported honestly rather than pretending an action succeeded.

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/zeshuochen/nekoro-browser/agents-md
Clone the repo
git clone --depth 1 https://github.com/zeshuochen/nekoro-browser

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 nekoro-browser AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/zeshuochen/nekoro-browser/agents-md.svg)](https://agentmods.dev/instructions/zeshuochen/nekoro-browser/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/zeshuochen/nekoro-browser/agents-md"><img src="https://agentmods.dev/badge/instructions/zeshuochen/nekoro-browser/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 650 This file is loaded in full into every session.
When invoked 650 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 $0.00650 $0.00650
Opus 5 $0.00325 $0.00325
Sonnet 5 $0.00130 $0.00130
Haiku 4.5 $0.00065 $0.00065

Measured 4d ago against content hash ecd52513ee2c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

nekoro-browser 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 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.

AGENTS.md · 48 lines

How it starts

The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.

nekoro-browser is a CLI that lets an agent drive the user's daily Chrome via a MV3 extension (chrome.debugger API) + a local daemon, keeping the real login state — no --remote-debugging-port (Chrome 136+ blocks that on the default profile anyway).

Code priorities

  • Clarity
  • Precision
  • Low verbosity
  • Never fabricate success — helpers return {"ok": false, "error": ...} on failure, not a silently-wrong {"ok": true}

Overview

Two halves, one wire (HTTP + WebSocket, same port):

  • extension/ — MV3 extension. background.js is the service worker: WS transport to the daemon, chrome.debugger attach/CDP dispatch, dialog auto-handling, tab lifecycle. keepalive.js is a content script that gives the service worker an independent wake vector (MV3 workers get evicted; a plain WS/alarm keep-alive alone isn't reliable).
  • src/nekoro_browser/ — the daemon + CLI.
    • daemon.py — long-lived middleman process between the extension and the agent's -c code
    • bridge.py — the WS/HTTP transport
    • lifecycle.py — pid file, process fingerprint, stale-daemon self-heal
    • helpers.py — CDP wrapper functions auto-imported into -c scripts, each a thin (≤10 line) wrapper over one CDP capability
    • cli.py — the nekoro-browser command
    • mcp_server.py — the nekoro-browser-mcp command: stdio JSON-RPC MCP server for clients that don't read skill files (Claude Desktop, Cursor, opencode, Codex, VS Code/Copilot, …). Tools are reflected off helpers.py via inspect.signature, then forwarded to the same daemon /exec endpoint the CLI uses — no second execution path to keep in sync.

SKILL.md tells agents how to use the CLI and lists every helper. README.md covers install + quick start for humans.

An agent operating nekoro-browser edits two places:

  • src/nekoro_browser/agent_helpers.py — task-specific browser helpers the agent adds at runtime; hot-reloaded via reload_agent_helpers(), no daemon restart needed
  • domain-skills/ — Markdown notes on specific sites, written and read by the agent. Empty by default and never imported; workflows go in agent_helpers.py.

Read the full file on GitHub · 48 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 · 48 lines · 650 tokens per session scan A ecd52513ee2c

Subscribe to this mod's changes

nekoro-browser AGENTS.md is an instructions file published in the GitHub repository zeshuochen/nekoro-browser (5 stars, last pushed 13d ago), licensed MIT. It adds 650 tokens to every session, about $0.0032 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

rustwright AGENTS.md

AGENTS.md instructions for Skyvern-AI/rustwright, covering repository instructions, public boundary, pull-request review, local verification and browser launches.

Skyvern-AI/rustwright · 996 tokens

chrome-agent CLAUDE.md

Claude Code instructions for sderosiaux/chrome-agent, covering chrome-agent v0.16.0, architecture, build & test, release and → requires npmtoken in github secrets.

sderosiaux/chrome-agent · 6,345 tokens

codex-browser-bridge AGENTS.md

AGENTS.md instructions for DeliciousBuding/codex-browser-bridge, covering agents.md, 仓库级 skill, mcp 工具设计规范, 1. browser 层(src/browser.rs) and 2. mcp 层(src/mcp/ 目录).

DeliciousBuding/codex-browser-bridge · 1,730 tokens

cdpilot CLAUDE.md

Instructions for mehmetnadir/cdpilot, covering cdpilot, kimlik, hızlı başlangıç, dosya haritası and dikkat edilecekler.

mehmetnadir/cdpilot · 1,172 tokens

cdpilot GEMINI.md

Instructions for mehmetnadir/cdpilot, covering context-mode — mandatory routing rules, blocked commands — do not attempt these, curl / wget — blocked, inline http — blocked and webfetch / web browsing — blocked.

mehmetnadir/cdpilot · 892 tokens

native-devtools-mcp AGENTS.md

AGENTS.md instructions for vectora-foundry/native-devtools-mcp, covering agent context: native-devtools-mcp, 🧠 core reasoning loop, 🗺️ capabilities matrix (strategy guide), 🛠️ tool definitions & schemas and 1. vision & perception (the "eyes").

vectora-foundry/native-devtools-mcp · 8,302 tokens