Borrowing it
Nothing to install: this file belongs to schlemperdev/shantycrawl-mcp. 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/schlemperdev/shantycrawl-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/schlemperdev/shantycrawl-mcpWrote 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/schlemperdev/shantycrawl-mcp/agents-md)<a href="https://agentmods.dev/instructions/schlemperdev/shantycrawl-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/schlemperdev/shantycrawl-mcp/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/schlemperdev/shantycrawl-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/schlemperdev/shantycrawl-mcp/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 | $0.01820 | $0.01820 |
| Opus 5.5 | $0.00728 | $0.00728 |
| Sonnet 5.5 | $0.00364 | $0.00364 |
| Haiku 4.5 | $0.00182 | $0.00182 |
Grade A, and why
shantycrawl-mcp 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 2mo 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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ShantyCrawl MCP -- Dynamic Firecrawl MCP Server
Purpose
Custom MCP server for Firecrawl with lazy-loading tool architecture. Replaces the official firecrawl-mcp (28 tools upfront) with 6 base tools (scrape, crawl, search, check_crawl_status, tool_enable, tool_disable) and dynamic activation of advanced tools via tool_enable/tool_disable. Drastically reduces context consumption.
Ownership
- Published as
shantycrawl-mcpon npm. - Source at
~/projects/shantycrawl-mcp/. - Stack: Node.js + TypeScript +
@modelcontextprotocol/sdk - Transport: stdio
- API target:
FIRECRAWL_API_URLenv var (defaulthttps://api.firecrawl.devifFIRECRAWL_API_KEYis set, elsehttp://localhost:3002).
Local Contracts
- Built with
@modelcontextprotocol/sdk. No FastMCP or other wrappers. - Communication exclusively via stdio.
- In-memory state tracks which advanced tools are active in the session.
tool_enableadds tool to state and emitsnotifications/tools/list_changed.tool_disableremoves tool from state and emitsnotifications/tools/list_changed.- Authentication:
FIRECRAWL_API_KEYenv var →Authorization: Bearerheader on all requests. Never exposed in tool schemas. - Extraction tools (scrape, crawl, etc.) call Firecrawl API at the configured
FIRECRAWL_API_URLvia HTTP fetch, return formatted Markdown. - POST/PATCH tools use optional
buildBodymapper for argument shaping before API call. No mapper = raw args sent unchanged (fallback-safe).
Work Guidance
- This server lazy-loads 22 advanced tools via
tool_enable. Only 6 base tools appear intools/listinitially. Calltool_enable("<name>")to activatemap,extract,parse,agent,interact,research_*, ormonitor_*tools. - The server also exposes a
shantycrawl-setupprompt with full usage instructions — fetch it viaGetPromptRequestSchemawhen connecting. - Build output goes to
dist/. Config reference lives in~/shantio/dotfiles/opencode/opencode.jsonc. - AGENTS.md is the single source of project contracts — update when purpose, scope, or workflow changes.
- To add a tool: register schema in
tools.ts, add route infirecrawl.ts. - Keep schemas minimal (≤4 word descriptions, only vital params).
- All routes target Firecrawl v2 API. Add
buildBodytoRoutewhen API body shape differs from user schema. - GET tools with query params use
URLSearchParamsinpathfunction. scripts/coderabbit-loop.tsautomates CodeRabbit fix loop: polls PR reviews, applies inline suggestions, commits/pushes until green light or MAX_LOOPS (5). Invoke viatsx scripts/coderabbit-loop.ts <PR_NUMBER> [BRANCH]aftergit-workflowopens PR. Exit 0 → safe to merge viagit-merge. Exit 1/2 → manual.
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.
- 2mo ago First seen · 145 lines · 1,820 tokens per session scan A 488fc67771e5
shantycrawl-mcp AGENTS.md is an instructions file published in the GitHub repository schlemperdev/shantycrawl-mcp (1 stars, last pushed 4mo ago), licensed MIT. It adds 1,820 tokens to every session, about $0.0073 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.