japan-ux-mcp: Instructions file for Codex

AGENTS.md

japan-ux-mcp AGENTS.md is an instructions file for Codex, OpenCode from mrslbt/japan-ux-mcp. It costs 1,135 tokens per session, scanned A, original, MIT.

An AGENTS.md instruction file for a local server that checks whether web interfaces follow Japanese design and user-experience conventions. MCP is a way for an AI agent to call tools provided by a program.

In plain words
What is it for?
It helps developers build, test, run, and extend the Japanese-interface review server, including its main UI-review tool.
Why use it?
It gives coding agents the project's purpose, structure, commands, and required checks before changes are committed. It also explains that the server works offline with bundled data.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions Claude Code; mentions AGENTS.md; mentions Codex.

This is mrslbt/japan-ux-mcp's own configuration. It tells Codex and OpenCode how to work on japan-ux-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 japan-ux-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to mrslbt/japan-ux-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/mrslbt/japan-ux-mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/mrslbt/japan-ux-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 japan-ux-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/mrslbt/japan-ux-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/mrslbt/japan-ux-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/mrslbt/japan-ux-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/mrslbt/japan-ux-mcp/agents-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 japan-ux-mcp AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/mrslbt/japan-ux-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/mrslbt/japan-ux-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,135 This file is loaded in full into every session.
When invoked 1,135 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 $0.01135 $0.01135
Opus 5 $0.00567 $0.00567
Sonnet 5 $0.00227 $0.00227
Haiku 4.5 $0.00113 $0.00113

Measured 11d ago against content hash ecd0768a2ec3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

japan-ux-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 11d 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 · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — japan-ux-mcp

Guide for AI coding agents (Claude Code, Cursor, Codex, Copilot…) working in this repo.

What this project is

Japan Design — an MCP server that enforces Japanese UI (typography, colour, layout) and UX (forms, keigo, trust, seasonal) conventions on real CSS/markup, so AI generates culturally correct Japanese interfaces instead of Western defaults.

  • npm: japan-ux-mcp · registry name: io.github.mrslbt/japan-ux
  • Local stdio server, read-only, deterministic, bundled data only — no API keys, no network.
  • Flagship tool: review_jp_ui — the front-end correctness enforcer (scores any UI against the Japanese standard with JLReq/JIS citations + fixes).

Quick commands

npm install        # deps
npm run build      # tsc → dist/   (must pass before commit)
npm test           # build + node --test test/*.test.mjs   (must pass before commit)
npm run smoke      # build + a live MCP round-trip (lists tools, calls review_jp_ui)
npm run dev        # tsc --watch

Pre-commit: npm run build && npm test. Both must pass. 18 tests today.

Architecture (the whole mental model)

src/
├── index.ts            # McpServer — registers every tool/prompt/resource + server instructions
├── meta.ts             # READONLY annotation + withTitles() param-title helper
├── tools/
│   ├── review-jp-ui.ts # FLAGSHIP — composes typography + colour + font-payload checks
│   ├── check-jp-typography.ts, audit-japan-ux.ts, transform-for-japan.ts, … (one file per tool)
└── data/               # bundled, offline rule data (typography-rules, visual-rules, keigo, seasonal, …)
test/                   # integration + regression (.test.mjs) and smoke.mjs

11 tools · 10 prompts · 9 resources. The SDK is @modelcontextprotocol/sdk (1.29+), zod 4.

How to add or change a tool

Every tool is registered in index.ts with annotations + parameter titles. Use this exact shape — do not drop withTitles or READONLY:

import { READONLY, withTitles } from "./meta.js";

server.tool(
  "your_tool_name",                                   // snake_case, verb-first
  "Verb-first description, ≤2 sentences, names the next tool to call.",
  withTitles({
    some_field: z.string().describe("English description with a concrete example."),
  }),
  READONLY,                                           // every tool is read-only + deterministic
  async (params) => {
    const result = yourToolFn({ ...params });
    return { content: [{ type: "text", text: JSON.stringify(result, null, 2) }] };
  }
);

Read the full file on GitHub · 88 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. 11d ago First seen · 88 lines · 1,135 tokens per session scan A ecd0768a2ec3

Subscribe to this mod's changes

japan-ux-mcp AGENTS.md is an instructions file published in the GitHub repository mrslbt/japan-ux-mcp (0 stars, last pushed 26d ago), licensed MIT. It adds 1,135 tokens to every session, about $0.0057 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

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,126 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

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