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.
curl -O https://raw.githubusercontent.com/yanislav-igonin/random-design-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/yanislav-igonin/random-design-mcpWrote 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.
[](https://agentmods.dev/instructions/yanislav-igonin/random-design-mcp/agents-md)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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. compatibilitydefaults totrue.- 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
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.
- 2mo ago First seen · 94 lines · 682 tokens per session scan A 169da294dd43
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.
random-design-mcp AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| random-design-mcp AGENTS.mdyanislav-igonin/random-design-mcp | Instructions file | 0 | 5mo ago | MIT | A | 682 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |