random-design-mcp: Instructions file for Codex

AGENTS.md

random-design-mcp AGENTS.md is an instructions file for Codex, OpenCode from yanislav-igonin/random-design-mcp. It costs 682 tokens per session, scanned A, original, MIT.

A set of project instructions for random-design-mcp, a TypeScript server that generates randomized frontend design directions as English Markdown. It documents the project map, architecture, constraints, and tests.

In plain words
What is it for?
Use it when working on random-design-mcp, especially its MCP tool, design generator, catalogs, configuration, Markdown output, or tests.
Why use it?
It helps coding agents understand the repository before changing code, reducing the risk of editing generated files or breaking project rules.

Instructions file for CodexOpenCode

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

This is yanislav-igonin/random-design-mcp's own configuration. It tells Codex and OpenCode how to work on random-design-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 random-design-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to yanislav-igonin/random-design-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/yanislav-igonin/random-design-mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/yanislav-igonin/random-design-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 random-design-mcp AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/yanislav-igonin/random-design-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/yanislav-igonin/random-design-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 682 This file is loaded in full into every session.
When invoked 682 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 $0.00682 $0.00682
Opus 5.5 $0.00273 $0.00273
Sonnet 5.5 $0.00136 $0.00136
Haiku 4.5 $0.00068 $0.00068

Measured 2mo ago against content hash 169da294dd43, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

random-design-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 2mo 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 · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Project Purpose

random-design-mcp is a TypeScript MCP server that generates randomized frontend design directions as English Markdown.

The server does not call an LLM. It exposes one stdio MCP tool: generate_design_description.

Repository Map

  • src/index.ts: executable stdio MCP entrypoint.
  • src/tool.ts: MCP server creation, tool registration, input schema, and MCP boundary error handling.
  • src/generator.ts: design profile generation core.
  • src/random.ts: random selection helpers and injectable random source.
  • src/render-markdown.ts: Markdown output renderer.
  • src/config.ts: generator probabilities and config validation.
  • src/types.ts: shared catalog, generation, and profile types.
  • src/catalog/*.ts: editable design catalogs with compatibility tags.
  • tests/*.test.ts: Vitest coverage for generator behavior, catalog integrity, Markdown rendering, publishing metadata, dev preview, and MCP tool behavior.
  • docs/superpowers/specs/: design specs.
  • docs/superpowers/plans/: implementation plans.
  • dist/: generated build output. Do not edit by hand.

Architecture

Flow:

MCP stdio entrypoint
  -> generate_design_description tool
    -> generator core
      -> catalog/*.ts
      -> config.ts
      -> random.ts
      -> render-markdown.ts

Keep the generator core independent from MCP so it can be tested directly.

Product Constraints

  • Keep exactly one MCP tool unless user explicitly requests a product change.
  • Tool name: generate_design_description.
  • Output language: English Markdown.
  • Optional input fields: productType, audience, priority, compatibility.
  • compatibility defaults to true.
  • Do not add LLM calls, HTTP transport, auth, persistent state, deterministic replay, or UI unless the user explicitly asks.
  • Do not add undocumented input fields casually. The schema is strict and tests verify unknown arguments fail.

Development Commands

npm install
npm run build
npm test
npm run check
npm run dev

Read the full file on GitHub · 94 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. 2mo ago First seen · 94 lines · 682 tokens per session scan A 169da294dd43

Subscribe to this mod's changes

random-design-mcp AGENTS.md is an instructions file published in the GitHub repository yanislav-igonin/random-design-mcp (0 stars, last pushed 5mo ago), licensed MIT. It adds 682 tokens to every session, about $0.0027 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 2026-08-31.

Related

random-design-mcp AGENTS.md compared with instructions from other repositories

random-design-mcp AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
random-design-mcp AGENTS.mdyanislav-igonin/random-design-mcpInstructions file05mo agoMITA682Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode