agentmods.dev

satorntcg-mcpserver: Instructions file for Claude Code

CLAUDE.md

satorntcg-mcpserver CLAUDE.md is an instructions file for Claude Code from satorntcg/satorntcg-mcpserver. It costs 2,820 tokens per session, scanned A, original, MIT.

A repository instruction file describing how to run and maintain an MCP server, including its tests, evaluation script, environment variables, and code structure. MCP is a way for an AI assistant to call tools provided by another program.

In plain words
What is it for?
Use it when editing the server, running its test suite or offline tool-selection evaluation, and handling its Supabase and tracing settings.
Why use it?
It gives a coding agent the project's local rules and prevents it from guessing commands, architecture, or required configuration.

Instructions file for Claude Code

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

This is satorntcg/satorntcg-mcpserver's own configuration. It tells Claude Code how to work on satorntcg-mcpserver 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 satorntcg-mcpserver configures →

not rated 0repo changed 8d ago A scan 2,820 tokens original MIT
View source ↗ satorntcg/satorntcg-mcpserver
Reuse

Borrowing it

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

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 satorntcg-mcpserver CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/satorntcg/satorntcg-mcpserver/claude-md"><img src="https://agentmods.dev/badge/instructions/satorntcg/satorntcg-mcpserver/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,820 This file is loaded in full into every session.
When invoked 2,820 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 $0.02820 $0.02820
Opus 5.5 $0.01128 $0.01128
Sonnet 5.5 $0.00564 $0.00564
Haiku 4.5 $0.00282 $0.00282

Measured 8d ago against content hash cd3218cf641d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

satorntcg-mcpserver 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 8d 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 · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 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.

Commands

  • npm start — run the MCP server over stdio (meant to be launched by an MCP client, not used interactively)
  • npm run dev — same, with node --watch
  • npm test — run every test/**/*.test.js with Node's built-in test runner (node --test)
  • node --test test/<file>.test.js — run one test file
  • node evals/run-offline.js — run the offline tool-selection eval (run from the repo root: it reads evals/tool-selection.json relative to the cwd)
  • ANTHROPIC_MODEL=<id> node agent/run-agent.js "<question>" — one-shot CLI agent over the read-only tools (calls the real DB and Anthropic API). Loop logic lives in agent/agentCore.js (no SDK/Supabase/tracing imports) so test/agent.test.js can drive it with fake clients. Tracing is added from outside by agent/agentTracing.js, which wraps the Anthropic and MCP clients passed to runAgent() (tested in test/agentTracing.test.js with an in-memory exporter). Keep tracing out of agentCore.js. Metrics (agent/agentMetrics.js, tested in test/agentMetrics.test.js) are off unless OTEL_METRICS_EXPORTER=console. Instruments must be created after initTracing(), because the metrics API has no proxy meter.
  • No lint, typecheck, or build step.

Env vars (from .env, loaded by src/env.js via an absolute path — see .env.example):

  • SUPABASE_URL, SUPABASE_SERVICE_KEY — required; src/supabaseClient.js throws at import time without them
  • OTEL_EXPORTER_OTLP_ENDPOINT — optional, defaults to http://localhost:4318/v1/traces (Jaeger)
  • OTEL_METRICS_EXPORTER — agent CLI only: otlp sends delta metrics to the Collector in observability/ (OTEL_EXPORTER_OTLP_METRICS_ENDPOINT, default http://localhost:4319/v1/metrics; port 4318 is Jaeger's); console prints them to stderr at exit; unset/none disables them. Metrics use their own MeterProvider with a service.name-only resource, so per-process attributes never become labels.
  • TCGPLAYER_COOKIE — only read when print_packing_slip runs
  • EBAY_CLIENT_ID, EBAY_CLIENT_SECRET — only read when find_ebay_deals runs (production eBay keyset; EBAY_APP_ID/EBAY_CERT_ID are accepted as fallbacks, matching the Supabase Edge Function's names)
  • npm run test:deals (scripts/test-deals.js) — live smoke test of find_ebay_deals against real eBay + Supabase; prints totals, top deals, lots and sample ambiguous/unmatched titles. Doesn't record seen deals unless --record is passed. Not part of npm test.

Read the full file on GitHub · 89 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. 8d ago Changed · +10 lines · +520 tokens per session cd3218cf641d
  2. 9d ago Changed · +11 lines · +530 tokens per session 011410b1e593
  3. 23d ago Changed · +2 lines · +288 tokens per session 28f84eb5e129
  4. 28d ago First seen · 66 lines · 1,482 tokens per session scan A 17aa441b4dd9

Subscribe to this mod's changes

satorntcg-mcpserver CLAUDE.md is an instructions file published in the GitHub repository satorntcg/satorntcg-mcpserver (0 stars, last pushed 5d ago), licensed MIT. It adds 2,820 tokens to every session, about $0.0113 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 2026-10-10.

Writing and docs
Related

satorntcg-mcpserver CLAUDE.md compared with instructions from other repositories

satorntcg-mcpserver CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
satorntcg-mcpserver CLAUDE.mdsatorntcg/satorntcg-mcpserverInstructions file05d agoMITA2,820Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file275k3d agoMITA4,313Codex, OpenCode