Borrowing it
Nothing to install: this file belongs to vintik100/bunbrowser. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/vintik100/bunbrowser/main/AGENTS.mdgit clone --depth 1 https://github.com/vintik100/bunbrowserWrote 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/vintik100/bunbrowser/agents-md)<a href="https://agentmods.dev/instructions/vintik100/bunbrowser/agents-md"><img src="https://agentmods.dev/badge/instructions/vintik100/bunbrowser/agents-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.
<a href="https://agentmods.dev/instructions/vintik100/bunbrowser/agents-md"><img src="https://agentmods.dev/badge/instructions/vintik100/bunbrowser/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.01008 | $0.01008 |
| Opus 5.5 | $0.00403 | $0.00403 |
| Sonnet 5.5 | $0.00202 | $0.00202 |
| Haiku 4.5 | $0.00101 | $0.00101 |
Grade A, and why
bunbrowser 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 1mo 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Context & Guidelines
1. Project Overview
@bunbrowser/mcp (bunbrowser, GitHub: github.com/vintik100/bunbrowser) is an ultra-fast, zero-download Model Context Protocol (MCP) server for browser automation powered natively by Bun.WebView. It serves as a drop-in replacement for @playwright/mcp with identical AI tool semantics, native OS-level user events (isTrusted: true), raw CDP execution, and sub-50ms startup times.
2. Technology Stack
- Language & Runtime: TypeScript (Strict mode), Bun (>= 1.3.12 / 1.4.0+)
- Protocol & Frameworks: Model Context Protocol (
@modelcontextprotocol/sdk),Bun.WebViewnative bindings - Schema & Validation: Zod (
zod) - Package Manager:
bun - Documentation Standard: Diátaxis Framework (
docs/)
3. Essential Commands
- Install dependencies:
bun install - Run server (stdio):
bun startorbun run src/index.ts - Run tests:
bun test - Lint & Typecheck:
bun run check(executesbun tsc --noEmit && biome check .) - Auto-format:
bun run format(executesbiome format --write .)
4. Architecture & Directory Structure
bunbrowser/
├── bin/
│ ├── bunbrowser.ts # CLI binary entry point
│ └── bunpw-mcp.ts # Legacy alias binary entry point
├── src/
│ ├── index.ts # Main entry point, CLI flag parsing & stdio transport
│ ├── server.ts # MCP server initialization & tool registration
│ ├── browser/ # Core browser management
│ │ ├── manager.ts # Multi-tab lifecycle & active tab tracking
│ │ ├── tab.ts # Bun.WebView wrapper, actions & CDP bridges
│ │ ├── recorder.ts # Video recording manager (TabRecorder)
│ │ ├── gif_encoder.ts # Pure TS GIF89a encoder
│ │ ├── snapshot.ts # Accessibility tree parsing & [ref=eN] ref resolver
│ │ └── types.ts # Internal types & configuration options
│ └── tools/ # MCP Tool implementations
│ ├── navigation.ts # browser_navigate, back, forward, reload
│ ├── interaction.ts # click, type, fill_form, press_key, hover, scroll, drag, etc.
│ ├── inspection.ts # snapshot, screenshot, evaluate, content, logs
│ ├── tabs.ts # tabs, tab_new, tab_switch, tab_close, resize
│ ├── storage_cdp.ts # cookies, localstorage, cdp
│ ├── metrics.ts # get_metrics, lighthouse_audit
│ └── video.ts # start_recording, stop_recording, record_animation
├── test/ # Bun test suites (*.test.ts)
└── docs/ # Diátaxis documentation structure
├── 1-tutorials/ # Step-by-step onboarding
├── 2-how-to/ # Practical task-based guides
├── 3-reference/ # Tool catalogs & CLI reference
└── 4-explanation/ # Architecture & Playwright comparisons
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.
- 1mo ago First seen · 62 lines · 1,008 tokens per session scan A 7c9b12904097
bunbrowser AGENTS.md is an instructions file published in the GitHub repository vintik100/bunbrowser (3 stars, last pushed 1mo ago), licensed MIT. It adds 1,008 tokens to every session, about $0.0040 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.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.