booth-mcp AGENTS.md

booth-mcp AGENTS.md is an instructions file for Codex, OpenCode from cstria0106/booth-mcp. It costs 310 tokens per session, scanned A, original, MIT.

Development instructions for a read-only BOOTH seller-data MCP server. BOOTH is a marketplace for creator products, and MCP is a standard way for an assistant to access another program's tools.

In plain words
What is it for?
Use them when developing, testing, or releasing the booth-mcp project.
Why use it?
They define safe handling for account data, masking of personal information, testing, and release checks.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/cstria0106/booth-mcp/agents-md
Clone the repo
git clone --depth 1 https://github.com/cstria0106/booth-mcp

Made for: Codex, OpenCode.

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 booth-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/cstria0106/booth-mcp/agents-md.svg)](https://agentmods.dev/instructions/cstria0106/booth-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/cstria0106/booth-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/cstria0106/booth-mcp/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 310 This file is loaded in full into every session.
When invoked 310 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00310 $0.00310
Opus 5 $0.00155 $0.00155
Sonnet 5 $0.00062 $0.00062
Haiku 4.5 $0.00031 $0.00031

Measured 4d ago against content hash 0e785fe42ff6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

booth-mcp AGENTS.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 4d 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.

AGENTS.md · 25 lines

What it actually says

Repository Guidelines

Development

  • Use Bun for dependency management and project commands.
  • Run bun install to install dependencies.
  • After meaningful changes, run bun run lint, bun run typecheck, bun run test, and bun run build as applicable.
  • Run bun run test:live only when explicitly requested because it uses a real BOOTH account.

Design Constraints

  • Keep the MCP runtime read-only. BOOTH data requests must use HTTP GET only.
  • Use Chrome or Edge only for interactive login; normal MCP queries must not launch a browser.
  • Keep playwright-core external to the bundled dist/cli.js output.
  • Never commit real sessions, orders, conversations, or other account data. Test fixtures must contain fictional data only.
  • Preserve masking of personal contact, address, and message data.

Release

  • package.json is the only version source. Do not edit .codex-plugin/plugin.json or the pinned version in .mcp.json directly.
  • The npm version lifecycle synchronizes generated version metadata. Run bun run check:distribution before release work and do not bypass a drift failure.
  • For a patch release, run npm version patch, then git push origin main --follow-tags.
  • Use npm version minor for backward-compatible features and npm version major for breaking changes.
  • Pushing the version tag triggers the npm release workflow. Do not run npm publish manually.
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. 4d ago First seen · 25 lines · 310 tokens per session scan A 0e785fe42ff6

Subscribe to this mod's changes

booth-mcp AGENTS.md is an instructions file published in the GitHub repository cstria0106/booth-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 310 tokens to every session, about $0.0015 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.