What is ratatoskr CLAUDE.md?

Repository-specific instructions for working on Ratatoskr, a project that lets language models interact with APIs through an MCP server. They describe setup, server commands, architecture, tests, code checks, and Docker usage.

Use them when starting the Ratatoskr server, running its Python tests, checking code quality and types, or building and running it with Docker.

They give a coding agent the project context and the commands needed to work on the repository consistently.

How innago-property-management/ratatoskr configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to innago-property-management/ratatoskr. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/innago-property-management/ratatoskr/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/innago-property-management/ratatoskr

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/innago-property-management/ratatoskr/claude-md/github.svg)](https://agentmods.dev/instructions/innago-property-management/ratatoskr/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/innago-property-management/ratatoskr/claude-md"><img src="https://agentmods.dev/badge/instructions/innago-property-management/ratatoskr/claude-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/innago-property-management/ratatoskr/claude-md"><img src="https://agentmods.dev/badge/instructions/innago-property-management/ratatoskr/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,728 This file is loaded in full into every session.

When invoked 2,728 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.02728	$0.02728
Opus 5	$0.01364	$0.01364
Sonnet 5	$0.00546	$0.00546
Haiku 4.5	$0.00273	$0.00273

Measured 9d ago against content hash c5ba2b2e42a1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

ratatoskr CLAUDE.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 9d 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.

CLAUDE.md · 206 lines

How it starts

The opening of the file, as written. The whole thing — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Ratatoskr is a polyglot-LLM fork of agoda-com/api-agent. Upstream changes may need periodic cherry-picking.

Commands

Setup:

uv sync --group dev

Run server:

uv run api-agent                    # Local dev (OpenAI default)
uv run api-agent --provider anthropic --api-key sk-ant-...  # Anthropic
uv run api-agent --provider openai-compat --base-url http://localhost:11434/v1 --model llama3  # Local
# Server starts on http://localhost:3000/mcp

Tests:

uv run pytest tests/ -v              # All tests (1412 passing)
uv run pytest tests/test_foo.py -v   # Single test file
uv run pytest tests/test_foo.py::test_bar -v  # Single test

Linting & Formatting:

uv run ruff check api_agent/
uv run ruff check --fix api_agent/   # Auto-fix
uv run ruff format api_agent/        # Format
uv run ty check                      # Type check

Docker:

docker build -t ratatoskr .
docker run -p 3000:3000 -e OPENAI_API_KEY="..." ratatoskr

Architecture

MCP Server (FastMCP) receives NL queries + headers → routes to Agents (pluggable LLM providers) → agents call target APIs + DuckDB for SQL processing.

Request Flow

Client sends MCP request w/ headers (X-Target-URL, X-API-Type, X-Target-Headers)
middleware.py: DynamicToolNamingMiddleware transforms tool names per session (e.g., _query → flights_api_query based on URL)
context.py: Extracts RequestContext from headers
tools/query.py: Routes to GraphQL or REST agent
agent/graphql_agent.py or agent/rest_agent.py:
- Fetches schema (introspection or OpenAPI)
- Creates agent w/ dynamic tools (graphql_query/rest_call, sql_query, search_schema)
- Runs agent loop (max 30 turns) via LLMProvider.run_tool_loop()
- Returns results
executor.py: DuckDB integration for SQL post-processing

Read the full file on GitHub · 206 lines

Changes

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.

9d ago First seen · 206 lines · 2,728 tokens per session scan A c5ba2b2e42a1

Subscribe to this mod's changes

ratatoskr CLAUDE.md is an instructions file published in the GitHub repository innago-property-management/ratatoskr (0 stars, last pushed 4mo ago), licensed MIT. It adds 2,728 tokens to every session, about $0.0136 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 2026-09-01.

ai-agents developer-tools graphql kaizen-enabled mcp mcp-server

repobrain copilot-instructions.md

Copilot instructions for study8677/repobrain, covering github copilot bootstrap instructions and hard rule — query the repobrain hub first.

study8677/repobrain · 229 tokens

plugin-files-mode

Rosetta Plugin Mode Bootstrap.

griddynamics/rosetta · 236 tokens

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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.

github/spec-kit · 7,104 tokens

ratatoskr: Instructions file for Claude Code