Borrowing it
Nothing to install: this file belongs to edk4971/Ratatoskr-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/edk4971/Ratatoskr-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/edk4971/Ratatoskr-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/edk4971/ratatoskr-mcp/agents-md)<a href="https://agentmods.dev/instructions/edk4971/ratatoskr-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/edk4971/ratatoskr-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/edk4971/ratatoskr-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/edk4971/ratatoskr-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 | $0.01134 | $0.01134 |
| Opus 5.5 | $0.00454 | $0.00454 |
| Sonnet 5.5 | $0.00227 | $0.00227 |
| Haiku 4.5 | $0.00113 | $0.00113 |
Grade A, and why
Ratatoskr-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 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.
How it starts
The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project: Ratatoskr-mcp
What this is
An MCP (Model Context Protocol) server that retrieves Wikipedia articles from local multistream dump files. No database, no ingest step, no internet required at query time. Named after Ratatoskr, the squirrel of Norse mythology who runs up and down Yggdrasil carrying messages.
Objective
Sub-3-second response time for article retrieval. Currently hitting 0.3–0.6s.
Architecture (4 files, flat — no subpackages)
server.py— MCP server entry point usingmcp.server.mcpserver.MCPServerwith configurable transport. Exposes one tool:get_wikipedia_article(topic).index.py— Flat-file index lookup.find_page(title) -> (byte_offset, stream_id, title). Uses ripgrepy for 0.2s case-insensitive search of the 1.2GB multistream index, rapidfuzz for fuzzy fallback.retrieval.py— Orchestrates: find_page → seek bz2 block → decompress → parse → follow redirects → assemble Markdown output.parser.py— XML parsing (lxml) + wikitext parsing (mwparserfromhell). Extracts title, lead section, infobox. Detects<redirect>elements.
Data flow
- Index lookup (
index.py): ripgrepy searches the plaintext index file (byte_offset:stream_id:titleformat) for the query. Exact case-sensitive match → exact case-insensitive match → fuzzy match (cluster hits by byte_offset, score each cluster with rapidfuzz word-boundary scoring). - Block fetch (
retrieval.py): seek to byte_offset in the bz2 dump, read 32MB chunk, decompress single bz2 block. - XML parse (
parser.py): find the matching<page>element (two-pass: case-sensitive then case-insensitive, to avoid grabbing redirect pages with different casing). - Redirect (
parser.py/retrieval.py): if<redirect title="X" />present, recurse withX(max depth 5, loop detection via visited-title set). - Extract (
parser.py): parse wikitext with mwparserfromhell. Extract infobox template, then lead section viaget_sections(include_lead=True, flat=True). - Output:
# Title\n\n{body}\n\n---\n\n{infobox}— body first (lead section only), infobox after as reference.
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 · +21 tokens per session 042236727f38
- 2mo ago First seen · 53 lines · 1,113 tokens per session scan A 0a3d63bac5d0
Ratatoskr-mcp AGENTS.md is an instructions file published in the GitHub repository edk4971/Ratatoskr-mcp (0 stars, last pushed 1mo ago), licensed Unlicense. It adds 1,134 tokens to every session, about $0.0045 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.
Ratatoskr-mcp AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| Ratatoskr-mcp AGENTS.mdedk4971/Ratatoskr-mcp | Instructions file | 0 | 1mo ago | Unlicense | A | 1,134 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,685 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode model-prompts.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 2,022 | GitHub Copilot |