Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/markusl/alko-mcp/claude-mdgit clone --depth 1 https://github.com/markusl/alko-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/markusl/alko-mcp/claude-md)<a href="https://agentmods.dev/instructions/markusl/alko-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/markusl/alko-mcp/claude-md.svg" alt="Measured on agentmods" 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 | $0.04176 | $0.04176 |
| Opus 5 | $0.02088 | $0.02088 |
| Sonnet 5 | $0.00835 | $0.00835 |
| Haiku 4.5 | $0.00418 | $0.00418 |
Grade A, and why
alko-mcp 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 6d 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 — 357 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Alko MCP Server
MCP (Model Context Protocol) server for querying the Alko.fi alcohol product catalog. Provides Claude Desktop with tools to search products, check store availability, and get recommendations.
Note: All tools return compact JSON (null values stripped) for efficient LLM processing. The LLM formats the response for human display.
Requirements
- Node.js 24+
- Google Cloud Firestore (or emulator for local dev)
- Playwright (for web scraping)
Project Structure
alko-mcp/
├── src/
│ ├── server.ts # MCP server entry point (stdio transport)
│ ├── config.ts # Configuration and environment variables
│ ├── tools/ # MCP tool implementations
│ │ ├── search-products.ts
│ │ ├── get-product.ts
│ │ ├── get-recommendations.ts
│ │ ├── list-stores.ts
│ │ ├── get-store-hours.ts
│ │ ├── get-availability.ts
│ │ └── get-sync-status.ts
│ ├── services/
│ │ ├── firestore.ts # Firestore database operations
│ │ ├── scraper.ts # Playwright-based web scraper
│ │ ├── cache.ts # LRU cache for search results
│ │ └── data-sync.ts # Product and store sync orchestration
│ ├── types/
│ │ └── index.ts # TypeScript type definitions
│ └── utils/
│ ├── logger.ts # Pino logger (writes to stderr + /tmp/alko-mcp.log)
│ ├── rate-limiter.ts # Rate limiting for scraping
│ └── excel-parser.ts # Alko price list Excel parser
├── scripts/
│ ├── sync-data.ts # Sync products from Excel price list
│ ├── sync-stores.ts # Scrape stores from Alko.fi
│ └── export-seed-data.ts # Export to seed file with diff
├── data/
│ └── seed-data.json # Bundled seed data (auto-loaded if Firestore empty)
├── tests/
│ ├── unit/ # Unit tests (excel-parser, rate-limiter, search-products)
│ ├── integration/ # Integration tests (tools, store-hours)
│ └── fixtures/ # Test data (6000+ products)
└── dist/ # Compiled JavaScript output
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.
- 6d ago First seen · 357 lines · 4,176 tokens per session scan A 8c4ebcee8ad2
alko-mcp CLAUDE.md is an instructions file published in the GitHub repository markusl/alko-mcp (14 stars, last pushed 6mo ago), licensed MIT. It adds 4,176 tokens to every session, about $0.0209 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
vibetags com-example-service-OrderService.instructions.md
Instructions for PIsberg/vibetags, covering copilot instructions for orderservice, rules for method calculatetax, rules for method processpayment, rules for method validateorder and context & focus.
rubydex AGENTS.md
AGENTS.md instructions for Shopify/rubydex, covering instructions, project overview, documentation, ruby gem and structure.
hw-mcp CLAUDE.md
Instructions for Hertwill/hw-mcp, covering project, constraints, technology stack, executive recommendation and recommended stack.
VectorCart copilot-instructions.md
Copilot instructions for Rounit-1st/VectorCart, covering vectorcart shopping assistant — llm instructions, role, 1. understand the customer, 2. convert the request into search inputs and visual search query.
gengeo-agent-registry AGENTS.md
Instructions for warwickwood-cell/gengeo-agent-registry: GenGEO provides machine-readable merchant verification infrastructure for AI agents.
kronan-mcp CLAUDE.md
Instructions for sandsower/kronan-mcp, covering kronan-mcp, build, configure, usage in claude code and api reference.