eyebrowse: Instructions file for Claude Code

CLAUDE.md

eyebrowse CLAUDE.md is an instructions file for Claude Code from Evil-Bane/eyebrowse. It costs 4,175 tokens per session, scanned A, original, MIT.

Repository instructions for building EyeBrowse, a browser-control engine available as a Python library and as an MCP service. It explains the project's browser engine, supported controls, pinned versions, and important constraints.

In plain words
What is it for?
Use it when developing EyeBrowse, including its Playwright-based browser control, stealth Chromium setup, network inspection, PDFs, videos, and MCP interface.
Why use it?
It gives a coding agent the project-specific rules needed to change the code without breaking its two ways of being used or its browser behaviour.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is Evil-Bane/eyebrowse's own configuration. It tells Claude Code how to work on eyebrowse itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything eyebrowse configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Evil-Bane/eyebrowse. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Evil-Bane/eyebrowse/master/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Evil-Bane/eyebrowse

Made for: Claude Code.

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 eyebrowse CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/evil-bane/eyebrowse/claude-md/github.svg)](https://agentmods.dev/instructions/evil-bane/eyebrowse/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/evil-bane/eyebrowse/claude-md"><img src="https://agentmods.dev/badge/instructions/evil-bane/eyebrowse/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for eyebrowse CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/evil-bane/eyebrowse/claude-md"><img src="https://agentmods.dev/badge/instructions/evil-bane/eyebrowse/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 4,175 This file is loaded in full into every session.
When invoked 4,175 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.04175 $0.04175
Opus 5.5 $0.01670 $0.01670
Sonnet 5.5 $0.00835 $0.00835
Haiku 4.5 $0.00417 $0.00417

Measured 2mo ago against content hash ef45fac0bb8e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

eyebrowse 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 2mo 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 · 212 lines

How it starts

The opening of the file, as written. The whole thing — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — EyeBrowse build notes

Guidance for working in this repo. EyeBrowse is a stealthy, LLM-drivable browser-control engine consumed two ways from one codebase: as a Python library (from eyebrowse import EyeBrowse) and over MCP (FastMCP, stdio). The engine holds no workflow logic — consumers decide what to do; it provides what's possible.

Engine: CloakBrowser (stealth Chromium, Chrome/146). A Playwright drop-in — launch_async() / launch_persistent_context_async() return a standard Playwright Browser / BrowserContext. Everything above the launch primitive runs on the plain Playwright page, so engine/engine.py is the ONLY engine-specific layer. Chromium gives us the full CDP surface (trusted cursorless clicks, Network/initiator inspection, MHTML, PDF, native video), exposed as thin tools. CloakBrowser's stealth is its patched binary + an auto --fingerprint={seed} / --fingerprint-platform (nothing for us to spoof); we map only its native knobs — humanize, geoip, locale, timezone, proxy. HAR is Playwright-native (record_har_path), video is Playwright-native (record_video_dir) — no custom recorders. (EyeBrowse was originally built on Camoufox/Firefox; that engine has been removed — see git history if you need the old launch path.)

Layout

eyebrowse/
  api.py            EyeBrowse façade — the single public entry point
  config.py         pydantic-settings (proxy, captcha keys, stealth defaults)
  snapshot.py       aria_snapshot(mode="ai") + aria-ref= locator resolution
  proxy.py          ProxyConfig + ProxyProvider (pluggable rotation)
  identity.py       Identity + random_identity() (isolated profile dir for rotation)
  extract.py        Crawl4AI raw: feed → markdown (no LLM; lazy, optional `extract` extra)
  engine/
    engine.py       BrowserEngine — CloakBrowser launch primitive (launch_async /
                    launch_persistent_context_async, proxy/options mapping, HAR rule, _Cleanup)
    session.py      Session (verbs incl. CDP: cdp_click/cdp_send/capture_mhtml/save_pdf/
                    video_path) + SessionRegistry (current-session)
  captcha/          base (Anti-Captcha-style polling) + 4 providers + inject.py
  mcp/
    server.py       FastMCP entrypoint (lifespan holds one EyeBrowse), main()
    state.py        process-wide engine handle
    tools/          17 tool-group modules (1:1 over the façade) = 85 tools
examples/direct_usage.py   library usage proof (no MCP)
docs/TOOLS.md              full per-tool reference

Read the full file on GitHub · 212 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. 2mo ago First seen · 212 lines · 4,175 tokens per session scan A ef45fac0bb8e

Subscribe to this mod's changes

eyebrowse CLAUDE.md is an instructions file published in the GitHub repository Evil-Bane/eyebrowse (1 stars, last pushed 5mo ago), licensed MIT. It adds 4,175 tokens to every session, about $0.0167 per session on Opus 5.5. 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

eyebrowse CLAUDE.md compared with instructions from other repositories

eyebrowse CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
eyebrowse CLAUDE.mdEvil-Bane/eyebrowseInstructions file15mo agoMITA4,175Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file144ktodayMITA8,130Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA5,685GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file150ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA3,153GitHub Copilot
generative-ai-for-beginners AGENTS.mdmicrosoft/generative-ai-for-beginnersInstructions file124ktodayMITA2,981Codex, OpenCode