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.
npx agentmods add instructions/zeshuochen/nekoro-browser/agents-mdgit clone --depth 1 https://github.com/zeshuochen/nekoro-browserWrote 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.
[](https://agentmods.dev/instructions/zeshuochen/nekoro-browser/agents-md)<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>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.
| Model | Per session | Once 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 |
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.
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.jsis the service worker: WS transport to the daemon,chrome.debuggerattach/CDP dispatch, dialog auto-handling, tab lifecycle.keepalive.jsis 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-ccodebridge.py— the WS/HTTP transportlifecycle.py— pid file, process fingerprint, stale-daemon self-healhelpers.py— CDP wrapper functions auto-imported into-cscripts, each a thin (≤10 line) wrapper over one CDP capabilitycli.py— thenekoro-browsercommandmcp_server.py— thenekoro-browser-mcpcommand: stdio JSON-RPC MCP server for clients that don't read skill files (Claude Desktop, Cursor, opencode, Codex, VS Code/Copilot, …). Tools are reflected offhelpers.pyviainspect.signature, then forwarded to the same daemon/execendpoint 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 viareload_agent_helpers(), no daemon restart neededdomain-skills/— Markdown notes on specific sites, written and read by the agent. Empty by default and never imported; workflows go inagent_helpers.py.
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.
- 4d ago First seen · 48 lines · 650 tokens per session scan A ecd52513ee2c
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.
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.
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.
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).
cdpilot CLAUDE.md
Instructions for mehmetnadir/cdpilot, covering cdpilot, kimlik, hızlı başlangıç, dosya haritası and dikkat edilecekler.
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.
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").