Borrowing it
Nothing to install: this file belongs to omgwtfwow/mcp-crawl4ai-ts. 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/omgwtfwow/mcp-crawl4ai-ts/main/.github/copilot-instructions.mdgit clone --depth 1 https://github.com/omgwtfwow/mcp-crawl4ai-tsWrote 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/omgwtfwow/mcp-crawl4ai-ts/copilot-instructions)<a href="https://agentmods.dev/instructions/omgwtfwow/mcp-crawl4ai-ts/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/omgwtfwow/mcp-crawl4ai-ts/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/omgwtfwow/mcp-crawl4ai-ts/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/omgwtfwow/mcp-crawl4ai-ts/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 | $0.01163 | $0.01163 |
| Opus 5 | $0.00581 | $0.00581 |
| Sonnet 5 | $0.00233 | $0.00233 |
| Haiku 4.5 | $0.00116 | $0.00116 |
Grade A, and why
mcp-crawl4ai-ts 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 10d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copilot Instructions: mcp-crawl4ai-ts
Concise, project-specific guidance for AI coding agents. Optimize for correctness, safety, and existing test expectations.
Architecture & Flow
- Entrypoint
src/index.ts: loads dotenv only ifCRAWL4AI_BASE_URLunset; fails fast if missing. Passes env + version intoCrawl4AIServer. src/server.ts: registers MCP tools, keeps aMap<string, SessionInfo>for persistent browser sessions, and usesvalidateAndExecute(Zod parse + invariant error message format). Do NOT alter error text pattern:Invalid parameters for <tool>: ...(tests & LLM reliability depend on it).- Service layer
src/crawl4ai-service.ts: pure HTTP wrapper around Crawl4AI endpoints; centralizes axios timeout & error translation (preserve wording likeRequest timed out,Request failed with status <code>:— tests rely on these substrings). - Handlers (
src/handlers/*.ts): orchestration & response shaping (text content arrays). No direct business logic inside server class beyond wiring. - Validation schemas (
src/schemas/validation-schemas.ts+ helpers): all tool inputs defined here. UsecreateStatelessSchemafor stateless tools; session/persistent tools have discriminated unions.
Tool Model
- Stateless tools (e.g.
get_markdown,capture_screenshot,execute_js) spin up a fresh browser each call. - Session-based operations use
manage_session(create/list/clear) +crawlfor persistent state, allowing chained JS + screenshot/pdf in ONE call. Never try to chain separate stateless calls to reflect JS mutations. - Output always returned as base64/text blocks; do not add file system side-effects unless explicitly using a save path param already supported (screenshots: optional local save dir).
JS & Input Validation Nuances
- JS code schema rejects: HTML entities ("), literal
\ntokens outside strings, embedded HTML tags. ReuseJsCodeSchema—do not duplicate logic. - For
get_markdown: if filter isbm25orllm,querybecomes required (enforced via.refine). Keep this logic centralized.
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.
- 10d ago First seen · 61 lines · 1,163 tokens per session scan A 788967f5b1ac
mcp-crawl4ai-ts copilot-instructions.md is an instructions file published in the GitHub repository omgwtfwow/mcp-crawl4ai-ts (11 stars, last pushed 1y ago), licensed MIT. It adds 1,163 tokens to every session, about $0.0058 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 instructions, from other repositories
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.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
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.