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.
npx agentmods add instructions/ergunsh/ask-user-mcp-app/agents-mdgit clone --depth 1 https://github.com/ergunsh/ask-user-mcp-appWrote 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/ergunsh/ask-user-mcp-app/agents-md)<a href="https://agentmods.dev/instructions/ergunsh/ask-user-mcp-app/agents-md"><img src="https://agentmods.dev/badge/instructions/ergunsh/ask-user-mcp-app/agents-md.svg" alt="Measured on agentmods" 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 | $0.04572 | $0.04572 |
| Opus 5 | $0.02286 | $0.02286 |
| Sonnet 5 | $0.00914 | $0.00914 |
| Haiku 4.5 | $0.00457 | $0.00457 |
Grade A, and why
ask-user-mcp-app 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 5d 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 — 462 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Guide: ask-user-mcp-app
This document helps AI agents understand and navigate the codebase efficiently.
Quick Overview
This is an MCP App that provides an ask_user tool for AI agents to ask users multiple questions with tab-based navigation and keyboard support. The UI renders inline in the host client (Claude, ChatGPT, etc.).
Key features:
- Multi-question tabs: Ask multiple questions displayed as navigable tabs
- Keyboard navigation: Tab/Shift+Tab for tabs, Arrow keys for options, Enter to select/submit
- "Other" input handling: When user clicks "Other", textbox auto-focuses; Arrow keys work for editing; Tab/Escape blur the input
- Auto-navigation: Single-select questions auto-advance to next tab
- Response format:
question -> answerformat for clear output
Documentation Requirements
IMPORTANT: You MUST update the documentation when making changes to the codebase.
Update README.md when:
- Adding or modifying tool parameters/schema
- Changing installation or usage instructions
- Adding new features users need to know about
- Modifying CLI commands or flags
- Changing default behavior
Update AGENTS.md when:
- Adding or modifying files in the project structure
- Changing implementation patterns or architecture
- Adding new common tasks or workflows
- Updating build output or dependencies
- Discovering new debugging tips
This ensures both users and future agents have accurate, up-to-date information.
Project Structure
ask-user-mcp-app/
├── server.ts # MCP server - tool + resource registration
├── main.ts # Entry point - HTTP and stdio transports
├── landing.ts # Self-contained HTML for GET / landing page
├── api/
│ └── index.ts # Vercel serverless entry (wires /, /mcp, /health)
├── mcp-app.html # UI entry point (Vite input)
├── src/
│ ├── mcp-app.tsx # Main React component - multi-question state management
│ ├── components/ # UI components (all use TailwindCSS)
│ │ ├── TabBar.tsx # Pill-style tab navigation with progress indicator
│ │ ├── QuestionPanel.tsx # Renders single question with refined card styling
│ │ ├── SubmitTab.tsx # Review page with staggered animations
│ │ ├── QuestionHeader.tsx # Question text with optional subtitle
│ │ ├── OptionButton.tsx # Elegant option cards with hover/selection states
│ │ ├── OptionList.tsx # List of OptionButtons with focusedIndex
│ │ ├── OtherInput.tsx # "Other" option with text input; imperatively focuses on toggle, blurs on Tab/Escape
│ │ ├── SubmitButton.tsx # Primary action button with accent color
│ │ └── index.ts # Barrel export
│ ├── hooks/ # Custom React hooks
│ │ ├── useTabNavigation.ts # Tab/Shift+Tab & arrow key tab navigation; Tab works even when focused on input
│ │ ├── useOptionNavigation.ts # Arrow key option navigation, Enter/Space select
│ │ └── useWindowFocus.ts # Tracks window focus state for conditional focus outlines
│ ├── types/index.ts # TypeScript interfaces (QuestionConfig, MultiQuestionState)
│ └── styles/app.css # Tailwind directives + CSS variables
├── tsconfig.json # Browser TypeScript (for Vite/React)
├── tsconfig.server.json # Server TypeScript (for Node.js)
├── vite.config.ts # Vite config with viteSingleFile plugin
├── tailwind.config.js # TailwindCSS config with theme colors
└── postcss.config.js # PostCSS config for Tailwind
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.
- 5d ago First seen · 462 lines · 4,572 tokens per session scan A 41b2c0f360c4
ask-user-mcp-app AGENTS.md is an instructions file published in the GitHub repository ergunsh/ask-user-mcp-app (1 stars, last pushed 4mo ago), licensed MIT. It adds 4,572 tokens to every session, about $0.0229 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.
Other instructions, from other repositories
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).
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.
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).
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.
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.
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.