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/cherchyk/mcpbrowser/copilot-instructionsgit clone --depth 1 https://github.com/cherchyk/MCPBrowserWhat 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 | $0.00000 | $0.00680 |
| Opus 5 | $0.00000 | $0.00340 |
| Sonnet 5 | $0.00000 | $0.00136 |
| Haiku 4.5 | $0.00000 | $0.00068 |
Grade A, and why
copilot-instructions scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCPBrowser Development Guidelines
Auto-generated from all feature plans. Last updated: 2026-03-03
Active Technologies
-
JavaScript (ES Modules), Node.js 18+ +
@modelcontextprotocol/sdk^1.25.1,puppeteer-core^23.4.1 (002-site-plugins) -
File-based plugin registry (
plugins.json), plugin folders on disk (002-site-plugins) -
JavaScript (ES Modules), Node.js 18+ +
@modelcontextprotocol/sdk^1.25.1,puppeteer-core^23.4.1, MCPBrowser plugin system (002-site-plugins) (003-gmail-plugin) -
N/A (plugin registry is file-based
plugins.json, already implemented) (003-gmail-plugin) -
JavaScript (ES modules), Node.js 18+ + Puppeteer-core (for
page.keyboard,page.$(),page.evaluate()), MCPBrowser core (responses.js, plugin-loader.js, browser.js, logger.js) (003-gmail-plugin) -
N/A (stateless plugin, no persistence) (003-gmail-plugin)
-
JavaScript (ES Modules), Node.js 18+ + MCPBrowser plugin system (002-site-plugins), Puppeteer (page object provided by plugin-action dispatcher), MCPBrowser core responses (
MCPResponse,ErrorResponse) (004-google-calendar-plugin) -
N/A — stateless plugin, no persistence (004-google-calendar-plugin)
-
Node.js 18+ (ESM) + puppeteer-core, @modelcontextprotocol/sdk (001-js-action-fallback)
Project Structure
MCPBrowser/
├── src/
│ ├── actions/
│ ├── browsers/
│ ├── core/
│ └── mcp-browser.js
└── tests/
├── actions/
├── browsers/
├── core/
├── tool-selection/
└── run-*.js
Commands
cd MCPBrowser && npm install && npm testcd MCPBrowser && node tests/run-unit.jscd MCPBrowser && node tests/tool-selection/run-tool-selection-tests.js
Code Style
- Node.js ESM modules; structured responses for MCP tools; prefer explicit async/await and try/catch with structured errors.
Recent Changes
- 004-google-calendar-plugin: Added JavaScript (ES Modules), Node.js 18+ + MCPBrowser plugin system (002-site-plugins), Puppeteer (page object provided by plugin-action dispatcher), MCPBrowser core responses (
MCPResponse,ErrorResponse) - 003-gmail-plugin: Added JavaScript (ES modules), Node.js 18+ + Puppeteer-core (for
page.keyboard,page.$(),page.evaluate()), MCPBrowser core (responses.js, plugin-loader.js, browser.js, logger.js) - 003-gmail-plugin: Added JavaScript (ES Modules), Node.js 18+ +
@modelcontextprotocol/sdk^1.25.1,puppeteer-core^23.4.1, MCPBrowser plugin system (002-site-plugins)
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 · 52 lines · 0 tokens per session scan A b8fdc93685e4
copilot-instructions is an agent published in the GitHub repository cherchyk/MCPBrowser (8 stars, last pushed 21d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 680 tokens. 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.