What is laskobot CLAUDE.md?

Project instructions for Laskobot's browser MCP, a tool that lets coding agents automate browsers. They define deployment commands and two ways to run browser connections: unified and legacy multi-instance modes.

Use them when deploying, configuring, rolling back, or working on Laskobot's browser automation server.

They keep deployments consistent and document the connection limits, ports, backups, and rollback procedure.

How david-strejc/laskobot configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to david-strejc/laskobot. 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/david-strejc/laskobot/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/david-strejc/laskobot

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/david-strejc/laskobot/claude-md/github.svg)](https://agentmods.dev/instructions/david-strejc/laskobot/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/david-strejc/laskobot/claude-md"><img src="https://agentmods.dev/badge/instructions/david-strejc/laskobot/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/david-strejc/laskobot/claude-md"><img src="https://agentmods.dev/badge/instructions/david-strejc/laskobot/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,080 This file is loaded in full into every session.

When invoked 1,080 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.

Model	Per session	Once invoked
Fable 5.1	$0.01080	$0.01080
Opus 5.5	$0.00432	$0.00432
Sonnet 5.5	$0.00216	$0.00216
Haiku 4.5	$0.00108	$0.00108

Measured 2mo ago against content hash 6ea29d4cc024, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

laskobot 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 · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Browser MCP - Enhanced Browser Automation

🚀 Quick Deploy

ALWAYS USE THIS FOR DEPLOYMENT: ./scripts/deploy

IMPORTANT: Always use ./scripts/deploy for ANY browser MCP deployment
Smart version checking (compares source vs deployed)
Automatic version bumping with validation (patch/minor/major)
Creates timestamped backups (keeps last 5)
Rollback capability: ./scripts/deploy --rollback
Configuration management: ./scripts/deploy --config
Robust error handling and status checks
DO NOT MANUALLY COPY FILES - Let the script handle everything

Architecture Modes

🎯 UNIFIED MODE (Recommended - NEW!)

Industry-standard single-listener architecture

Entry: dist/index-unified.js
Port: Single port 8765 for ALL instances
Benefits:
- ✅ No port scanning needed
- ✅ Scales to unlimited Claude instances
- ✅ Simpler firewall rules (1 port)
- ✅ Follows Selenium/Playwright/Chrome DevTools pattern
- ✅ Lower memory footprint
Connection: ws://localhost:8765/session/<instanceId>

Multi-Instance Mode (Legacy)

Entry: dist/index-multi.js
Ports: 8765-8775 (11 pre-created servers)
Limit: Max 11 concurrent instances
Note: Will be deprecated in future release

HTTP Mode

Entry: dist/index-http.js
Port: HTTP 3000 + dynamic WebSocket allocation
Use Case: Alternative transport for specific setups

Components

1. MCP Server

📦 Location: /home/david/.local/lib/browsermcp-enhanced/

Running: Via Claude's MCP integration (configured in ~/.claude/mcp_servers.json)
Recommended Entry: /home/david/.local/lib/browsermcp-enhanced/dist/index-unified.js
Manual Update:
1. Bump version in package.json
2. Build: npm run build
3. Copy: cp -r dist/* /home/david/.local/lib/browsermcp-enhanced/dist/
4. RESTART CLAUDE - Required for new MCP code to load!

2. Chrome Extension

🔧 Location: /home/david/.local/lib/browsermcp-enhanced/chrome-extension/

Install: Load unpacked in chrome://extensions/
Purpose: Enables browser automation from MCP server
Features:
- Smart click detection (automatically uses trusted clicks for OAuth/popups)
- Enhanced element detection with component-based capture
- Accessibility-aware element selection
Manual Update:
1. Copy: cp -r chrome-extension/* /home/david/.local/lib/browsermcp-enhanced/chrome-extension/
2. Run: ./scripts/chrome-canary-restart.sh to restart browser
3. Reload extension in chrome://extensions/

Read the full file on GitHub · 102 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.

2mo ago First seen · 102 lines · 1,080 tokens per session scan A 6ea29d4cc024

Subscribe to this mod's changes

laskobot CLAUDE.md is an instructions file published in the GitHub repository david-strejc/laskobot (39 stars, last pushed 1y ago), licensed Apache-2.0. It adds 1,080 tokens to every session, about $0.0043 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 2026-08-30.

Browser automation

laskobot CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
laskobot CLAUDE.mddavid-strejc/laskobot	Instructions file	39	1y ago	Apache-2.0	A	1,080	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,649	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode ai-customization.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	1,907	GitHub Copilot

laskobot: Instructions file for Claude Code