Borrowing it
Nothing to install: this file belongs to laurentvv/crawl4ai-mcp-llm. 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/laurentvv/crawl4ai-mcp-llm/main/.github/copilot-instructions.mdgit clone --depth 1 https://github.com/laurentvv/crawl4ai-mcp-llmWrote 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/laurentvv/crawl4ai-mcp-llm/copilot-instructions)<a href="https://agentmods.dev/instructions/laurentvv/crawl4ai-mcp-llm/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/laurentvv/crawl4ai-mcp-llm/copilot-instructions/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/laurentvv/crawl4ai-mcp-llm/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/laurentvv/crawl4ai-mcp-llm/copilot-instructions.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 | $0.00395 | $0.00395 |
| Opus 5.5 | $0.00158 | $0.00158 |
| Sonnet 5.5 | $0.00079 | $0.00079 |
| Haiku 4.5 | $0.00040 | $0.00040 |
Grade A, and why
crawl4ai-mcp-llm copilot-instructions.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.
What it actually says
Contributing guidelines for AI assistants
This repository is an MCP (Model Context Protocol) server that exposes Crawl4AI web crawling over stdio. Keep changes small and idiomatic.
Layout
src/crawl4ai_mcp_llm/server.py— MCP tools (crawl,crawl_page,close_session),crawl://resultsresources, response formatting, shared-browser lifespan.src/crawl4ai_mcp_llm/crawler.py— crawl orchestration (crawl4ai config, streaming, timeouts, stats).src/crawl4ai_mcp_llm/security.py— URL / output path / wait condition validation.src/crawl4ai_mcp_llm/markdown.py— Markdown cleaning and page formatting.src/crawl4ai_mcp_llm/results.py— listing and reading saved results (resource backend).src/crawl4ai_mcp_llm/config.py— settings read fromCRAWL4AI_*environment variables.
Rules
- Never write to stdout: it carries the MCP protocol. Use
logging(configured on stderr). - Every new crawl option exposed to the LLM goes through validation in
security.pyand keeps JavaScript execution behindCRAWL4AI_MCP_ALLOW_JS. - The tool docstring is sent to the LLM as the tool description: keep it a plain string literal (not an f-string) and up to date.
- Tests must not hit the network: use the
fake_crawlerfixture fromtests/conftest.py.
Commands
uv sync— installuv run pytest— unit tests (uv run pytest -m integrationfor real crawls)uv run ruff check . && uv run ruff format --check . && uv run mypy— lint and types
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 Changed · +7 lines · +249 tokens per session 0f2a68047c16
- 2mo ago First seen · 19 lines · 146 tokens per session scan A f233f785fdca
crawl4ai-mcp-llm copilot-instructions.md is an instructions file published in the GitHub repository laurentvv/crawl4ai-mcp-llm (45 stars, last pushed 5d ago), licensed MIT. It adds 395 tokens to every session, about $0.0016 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.
crawl4ai-mcp-llm copilot-instructions.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| crawl4ai-mcp-llm copilot-instructions.mdlaurentvv/crawl4ai-mcp-llm | Instructions file | 45 | 5d ago | MIT | A | 395 | GitHub Copilot |
| vibetags com-example-config-AsyncTestConfig.instructions.mdPIsberg/vibetags | Instructions file | 25 | today | MIT | A | 82 | GitHub Copilot |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |