agentmods.dev

stays: Instructions file for Claude Code

CLAUDE.md

stays CLAUDE.md is an instructions file for Claude Code from him229/stays. It costs 4,053 tokens per session, scanned A, original, MIT.

Development instructions for Stays, a Python library and MCP server that retrieves Google Hotels data through direct requests. They describe the project structure, commands, search system, and data models.

In plain words
What is it for?
Use them when developing, testing, or maintaining the Stays hotel-search library and its MCP server.
Why use it?
They give coding agents the project context and the correct places to make changes or run checks.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code; mentions Codex.

This is him229/stays's own configuration. It tells Claude Code how to work on stays itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything stays configures →

not rated 14repo 2mo ago A scan 4,053 tokens original MIT
View source ↗ him229/stays pypi.org
Reuse

Borrowing it

Nothing to install: this file belongs to him229/stays. 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/him229/stays/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/him229/stays

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.

agentmods badge for stays CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/him229/stays/claude-md/github.svg)](https://agentmods.dev/instructions/him229/stays/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/him229/stays/claude-md"><img src="https://agentmods.dev/badge/instructions/him229/stays/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.

agentmods 80×15 button for stays CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/him229/stays/claude-md"><img src="https://agentmods.dev/badge/instructions/him229/stays/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 4,053 This file is loaded in full into every session.
When invoked 4,053 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.04053 $0.04053
Opus 5.5 $0.01621 $0.01621
Sonnet 5.5 $0.00811 $0.00811
Haiku 4.5 $0.00405 $0.00405

Measured 2mo ago against content hash cec69602ea2f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

stays 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 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.

CLAUDE.md · 205 lines

How it starts

The opening of the file, as written. The whole thing — 205 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.

Project Overview

stays is a Python library and MCP server that provides programmatic access to Google Hotels through direct API interaction (reverse engineering). The project consists of:

  • MCP server (stays/mcp/) — FastMCP-based stdio + streamable-HTTP server exposing three tools. Layered into server.py (registration only — @mcp.tool/@mcp.prompt/@mcp.resource + re-exports), _config.py (HotelSearchConfig, CONFIG, CONFIG_SCHEMA, HARD_MAX_HOTELS_WITH_DETAILS = 15), _params.py (pydantic *Params classes + shared _validate_child_ages), and _executors.py (_execute_*_from_params + MCP-subset _serialize_hotel_* wrappers).
  • Search engine (stays/search/) — hotel search, detail, and parallel enrichment
  • Core client (stays/search/client.py) — rate-limited curl_cffi session with Chrome TLS impersonation
  • Data models (stays/models/google_hotels/) — pydantic filter/result/detail models
  • Parse layer (stays/search/parse/) — response parsing split across search_parser/detail_parser/policy_parser/provider_parser/slots.py. slots.py owns named slot-index constants + safe_get(tree, *path, default).
  • Canonical serializers (stays/serialize.py) — single source of truth for hotel → dict serialization consumed by both the CLI and MCP (the CLI-local stays/cli/_serialize.py is a re-export shim).
  • CLI runtime helpers (stays/cli/_runtime.py) — shared emit_result / emit_error / build_filters_from_cli_args plumbing used by search / details / enrich subcommands.
  • MCP setup backends (stays/mcp/setup/_backend.py + _adapters.py) — SetupBackend Protocol + SetupReport dataclass + BACKENDS registry; the legacy stays.mcp.setup.{claude,codex,chatgpt}.register(...) / .build() entry points are preserved on top.

The implementation leans heavily on reverse-engineering captures under docs/reverse-engineering/ — slot maps and filter coverage notes are the authoritative reference for the wire format.

Read the full file on GitHub · 205 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.

  1. 2mo ago First seen · 205 lines · 4,053 tokens per session scan A cec69602ea2f

Subscribe to this mod's changes

stays CLAUDE.md is an instructions file published in the GitHub repository him229/stays (14 stars, last pushed 2mo ago), licensed MIT. It adds 4,053 tokens to every session, about $0.0162 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.

Backend and APIsResearch
Related

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).

microsoft/vscode · 9,715 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 · 7,461 tokens

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).

microsoft/vscode · 5,262 tokens

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.

langchain-ai/langchain · 4,680 tokens

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).

microsoft/vscode · 2,750 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 4,261 tokens