costco-mcp: Instructions file for Claude Code

CLAUDE.md

costco-mcp CLAUDE.md is an instructions file for Claude Code from thehesiod/costco-mcp. It costs 2,043 tokens per session, scanned A, original, MIT.

Instructions for a server that connects to Costco’s internal online services through their GraphQL interface. It uses browser-based sign-in and saved refresh tokens to access receipts, orders, and product information without scraping pages at runtime.

In plain words
What is it for?
Use it when changing the Costco server, its GraphQL client, browser login flow, account token storage, product cache, or MCP tools.
Why use it?
It documents the system’s architecture and authentication rules so agents can work on account handling and API access safely.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is thehesiod/costco-mcp's own configuration. It tells Claude Code how to work on costco-mcp 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 costco-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to thehesiod/costco-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.

Copy the file
curl -O https://raw.githubusercontent.com/thehesiod/costco-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/thehesiod/costco-mcp

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 costco-mcp CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/thehesiod/costco-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/thehesiod/costco-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,043 This file is loaded in full into every session.
When invoked 2,043 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 $0.02043 $0.02043
Opus 5 $0.01022 $0.01022
Sonnet 5 $0.00409 $0.00409
Haiku 4.5 $0.00204 $0.00204

Measured 9d ago against content hash e3c76402f76d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

costco-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 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 · 146 lines

How it starts

The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Costco MCP Server

Architecture

MCP server that talks directly to Costco's internal GraphQL API using OAuth2 refresh tokens extracted from a browser session. No scraping, no headless browser at runtime — all API calls are pure HTTP via httpx[http2]. Runs as stdio transport.

src/costco_mcp_server/
  server.py         — MCP tool definitions (FastMCP)
  api.py            — CostcoAPI: GraphQL client, receipt/order/product queries
  auth.py           — CostcoAuth: per-account refresh token persistence + bearer minting
  auth_browser.py   — costco-auth-browser console script (launches Chrome with remote debugging)
  product_cache.py  — SQLite cache for product names + department codes

Key Patterns

Authentication (Azure AD B2C)

  • Costco's SPA uses Azure AD B2C OAuth2. Tenant + policy + client IDs are public (ship in Costco's own browser JS) and hardcoded in auth.py.
  • Refresh tokens live in ~/.costco-mcp/accounts/<name>/auth.json. Valid ~90 days.
  • Bearer tokens (id_token) are minted on demand, cached in memory with a 120-second expiry buffer (_is_token_expired).
  • No ROPC (resource owner password credentials) — initial auth requires a browser login to Costco's MFA flow. After that, it's pure API via the refresh token.
  • client-identifier header (api.py:CLIENT_IDENTIFIER) must be the exact value 481b1aec-aa3b-454b-b81b-48187e28f205. Random UUIDs cause 401. This appears to be a static per-app identifier (not per-user), copied from Costco's browser bundle.

Multi-account

  • Accounts: ~/.costco-mcp/accounts/<name>/auth.json per account. Config (default account + account list) at ~/.costco-mcp/config.json.
  • Every MCP tool takes an optional account parameter. Omitting it uses the default.
  • Legacy single-account ~/.costco-mcp/auth.json is auto-migrated to default/ on first load (_migrate_legacy).
  • _apis dict in server.py caches CostcoAPI instances per account name. save_refresh_token evicts on token update.

Read the full file on GitHub · 146 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. 9d ago First seen · 146 lines · 2,043 tokens per session scan A e3c76402f76d

Subscribe to this mod's changes

costco-mcp CLAUDE.md is an instructions file published in the GitHub repository thehesiod/costco-mcp (2 stars, last pushed 4mo ago), licensed MIT. It adds 2,043 tokens to every session, about $0.0102 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 2026-08-31.

Related

Other instructions, from other repositories

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

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 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 · 4,469 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 · 3,735 tokens