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 instructions/billallison/brsearch-mcp-server/copilot-instructionsgit clone --depth 1 https://github.com/billallison/brsearch-mcp-serverWrote 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/billallison/brsearch-mcp-server/copilot-instructions)<a href="https://agentmods.dev/instructions/billallison/brsearch-mcp-server/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/billallison/brsearch-mcp-server/copilot-instructions.svg" alt="Measured on agentmods" 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 | $0.00385 | $0.00385 |
| Opus 5 | $0.00192 | $0.00192 |
| Sonnet 5 | $0.00077 | $0.00077 |
| Haiku 4.5 | $0.00038 | $0.00038 |
Grade C, and why
brsearch-mcp-server copilot-instructions.md scanned grade C with 1 finding 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 5d 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- Use this file to provide workspace-specific custom instructions to Copilot. For more details, visit https://code.visualstudio.com/docs/copilot/copilot-customization#_use-a-githubcopilotinstructionsmd-file --> What it actually says
Copilot Instructions
MCP Server for URL Text Fetching and Web Search
This is a Model Context Protocol (MCP) server project that provides URL text fetching, web scraping, and web search capabilities.
Project Overview
- Purpose: Fetch text content and links from web pages, plus search the web with Brave Search
- Framework: MCP (Model Context Protocol) using the official Python SDK
- Dependencies: requests, beautifulsoup4, mcp
- Deployment: Can be used with LM Studio and other MCP-compatible clients
Key Features
fetch_url_text: Downloads all visible text from a URLfetch_page_links: Extracts all links from a web pagebrave_search_and_fetch: Searches the web using Brave Search API and automatically fetches content from top results- Error handling for network requests and parsing failures
- Configurable timeout for web requests
- Content length limiting to avoid excessive responses
API Requirements
- Brave Search API Key: Required for search functionality
- Get free API key at https://api.search.brave.com/
- 2,000 queries/month free tier, max 1 per second
- Set as environment variable:
BRAVE_API_KEY
Development Guidelines
- Follow MCP server conventions for tool definitions
- Use proper error handling for web requests
- Keep tool responses in the expected MCP format
- Test with various URL types and edge cases
References
- MCP Documentation: https://modelcontextprotocol.io/llms-full.txt
- Python SDK: https://github.com/modelcontextprotocol/create-python-server
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.
- 5d ago First seen · 38 lines · 385 tokens per session scan C a481d499d151
brsearch-mcp-server copilot-instructions.md is an instructions file published in the GitHub repository billallison/brsearch-mcp-server (1 stars, last pushed 2mo ago), licensed MIT. It adds 385 tokens to every session, about $0.0019 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
Browser4 CLAUDE.md
Claude Code instructions for platonai/Browser4, covering browser4 — project context for claude, architecture, key dispatch chain (cli → browser), batch commands and e2e test structure.
cc-websearch CLAUDE.md
Claude Code instructions for Djarvur/cc-websearch, covering project, constraints, technology stack, what not to add and conventions.
fix-quera AGENTS.md
Instructions for AlirezaKeshavarz83/fix-quera, covering agent guidance, project shape, visual style, quera page data findings and compatibility findings.
sniff AGENTS.md
AGENTS.md instructions for Aboudjem/sniff, covering agents.md: sniff, what this repo is, how an agent should use sniff, handling the playwright setup gate and finding output schema.
fast-browser CLAUDE.md
Claude Code instructions for m4ttstack/fast-browser, covering fast browser plugin, where a change belongs, fork branch: use fast-browser-runtime, releasing a new runtime and re-pinning this repo: use the script.
sendblue-browser-use AGENTS.md
Instructions for sendblue-api/sendblue-browser-use, covering agents.md — sendblue-browser-use, what this repo is, setup, common commands and health (no auth).