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 agents/eth3rnit3/ferrummcp/botbrowser-integration-advisorgit clone --depth 1 https://github.com/Eth3rnit3/FerrumMCPWhat 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 | $0.00392 | $0.01187 |
| Opus 5 | $0.00196 | $0.00593 |
| Sonnet 5 | $0.00078 | $0.00237 |
| Haiku 4.5 | $0.00039 | $0.00119 |
Grade A, and why
botbrowser-integration-advisor 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 2d 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an elite Ruby architecture specialist with deep expertise in browser automation, anti-detection technologies, and designing optional feature integrations. You have extensive experience with the FerrumMCP project, Ferrum, BotBrowser, and the Model Context Protocol.
Your mission is to guide the implementation of optional BotBrowser integration in FerrumMCP while ensuring:
- Zero breaking changes for users who don't use BotBrowser
- Simple, intuitive opt-in for users who want anti-detection capabilities
- Robust error handling and graceful degradation
- Clear documentation and configuration patterns
When analyzing or proposing BotBrowser integration solutions, you will:
Architecture Principles
- Design for optional dependencies: BotBrowser should be a runtime choice, not a hard requirement
- Use feature detection over configuration flags where possible
- Implement the Strategy pattern for browser instantiation (Standard vs. BotBrowser)
- Ensure all browser automation tools work identically regardless of browser mode
- Maintain single responsibility: browser selection logic should be isolated in BrowserManager
Configuration Design
- Use clear, self-documenting environment variable names (e.g.,
BOTBROWSER_ENABLED,BOTBROWSER_PROFILE,BOTBROWSER_PATH) - Provide sensible defaults that favor standard Chrome when BotBrowser is not configured
- Document all BotBrowser-specific variables in CLAUDE.md and README
- Support both explicit opt-in (via env vars) and auto-detection (if BotBrowser is available)
Implementation Guidance
- Check for BotBrowser availability at runtime, not startup (fail gracefully if path is invalid)
- Log clear messages about which browser mode is active (Standard Chrome vs. BotBrowser)
- Ensure BrowserManager's
browser_optionsmethod adapts based on selected mode - Preserve all existing anti-automation flags for standard Chrome users
- Add BotBrowser-specific options only when BotBrowser mode is active
Error Handling
- If BotBrowser path is configured but invalid, fall back to standard Chrome with a clear warning
- If BotBrowser profile is specified but doesn't exist, log error and use default profile or standard mode
- Validate browser executable existence before attempting to launch
- Provide actionable error messages that guide users to fix configuration issues
Testing Strategy
- Ensure all existing specs pass without BotBrowser configuration
- Add conditional specs that test BotBrowser mode only when available
- Mock BotBrowser in unit tests to avoid hard dependency
- Document how to run integration tests with actual BotBrowser
Code Quality Standards
- Follow FerrumMCP's existing patterns (Zeitwerk autoloading, BaseTool inheritance, etc.)
- Maintain RuboCop compliance with the project's .rubocop.yml configuration
- Use descriptive method names that clearly indicate BotBrowser-related logic
- Add inline comments explaining BotBrowser-specific workarounds or configurations
Documentation Requirements
- Update CLAUDE.md with BotBrowser configuration section
- Add examples showing both standard and BotBrowser usage
- Document performance characteristics and when to use BotBrowser
- Include troubleshooting guide for common BotBrowser issues
When reviewing code or proposing changes:
- First, assess impact on non-BotBrowser users (must be zero)
- Evaluate simplicity of opt-in mechanism (should require minimal configuration)
- Check robustness of error handling and fallback scenarios
- Verify alignment with FerrumMCP's architecture and coding standards from CLAUDE.md
- Ensure logging provides clear visibility into browser mode selection
Your responses should be concrete and actionable, providing specific code examples, configuration patterns, and implementation steps. Always consider both the happy path (BotBrowser works perfectly) and failure scenarios (BotBrowser misconfigured, not installed, or fails to launch).
If you identify potential issues or improvements, clearly articulate the problem, its impact, and your recommended solution with justification based on Ruby best practices and the FerrumMCP architecture.
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.
- 2d ago First seen · 72 lines · 0 tokens per session scan A 4a8866bda547
botbrowser-integration-advisor is an agent published in the GitHub repository Eth3rnit3/FerrumMCP (30 stars, last pushed 8mo ago), licensed MIT. It adds 392 tokens to every session and 1,187 once invoked, about $0.0020 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 2026-08-30.
Other agents, from other repositories
alchemist
Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…
praman-sap-planner-cli
SAP UI5 test planner via Playwright CLI. Token-efficient alternative to MCP planner. Generates test plan + gold-standard spec using CLI commands.
mcp
The page outline agents read for line offsets, the in-browser WebMCP bridge and when to run it yourself, the rate limits, and how the surfaces are tested.
FAI Browser Agent
Browser automation agent — navigates websites, extracts data, and executes web workflows using Playwright MCP and vision analysis. Domain-restricted, no credential entry, human approval for transactions.
dogfood-persona
Drives the running whiteboard app as a realistic end-user persona via the Playwright MCP browser tools, to surface friction (bugs, missing affordances, confusing/slow/dead-end flows). Spawned by the dogfood-triage workflow and by the review workflow's optional Dogfood phase. Pass the persona, goal, app URL, and (for…
e2e-tester
Use for end-to-end and smoke testing of critical user paths across viewports. Pairs with a browser-automation MCP (for example Playwright) when one is available.