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/blizzy78/mcp-elicit/claude-mdgit clone --depth 1 https://github.com/blizzy78/mcp-elicitWrote 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/blizzy78/mcp-elicit/claude-md)<a href="https://agentmods.dev/instructions/blizzy78/mcp-elicit/claude-md"><img src="https://agentmods.dev/badge/instructions/blizzy78/mcp-elicit/claude-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 | $0.01367 | $0.01367 |
| Opus 5 | $0.00683 | $0.00683 |
| Sonnet 5 | $0.00273 | $0.00273 |
| Haiku 4.5 | $0.00137 | $0.00137 |
Grade A, and why
mcp-elicit CLAUDE.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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Elicitation MCP Server
Project Description
The Elicitation MCP Server is a Model Context Protocol (MCP) server that provides user elicitation capabilities for AI applications. The server enables AI assistants to prompt users for structured input through various elicitation tools, supporting different data types and validation patterns. It acts as a bridge between AI systems and human users, allowing for interactive data gathering in conversational AI workflows.
The project implements the MCP specification and provides a comprehensive set of tools for soliciting user input, including free-form text, multiple choice options, numbers, booleans, dates, email addresses, and URIs. Each interaction supports user actions to accept, decline, or cancel prompts, providing a robust user experience.
High-Level Architecture
Transport Layer Architecture
The project follows a modular transport pattern with three distinct communication protocols:
┌─────────────┐ ┌──────────────────┐ ┌─────────────────┐
│ Client │ │ MCP Transport │ │ Elicit Server │
│ │◄──►│ │◄──►│ │
│ (AI/Bot) │ │ • STDIO │ │ • Tool Registry │
│ │ │ • SSE │ │ • Elicitation │
└─────────────┘ │ • HTTP │ │ • Validation │
└──────────────────┘ └─────────────────┘
Transport Implementations:
- STDIO (
stdio.ts): Command-line interface using standard input/output for direct integration with CLI applications - SSE (
sse.ts): Server-Sent Events over HTTP for web-based real-time communication with session management - HTTP (
streamableHttp.ts): Full HTTP server with session management, resumability, and connection lifecycle handling
Core Components:
- Entry Point (
index.ts): Dynamic transport dispatcher that loads the appropriate communication module based on command-line arguments - Server Factory (
elicit.ts): Creates configured MCP server instances with tool capabilities and elicitation features - Tool Registry (
tools/index.ts): Centralized registry of all available elicitation tools with handlers and schemas
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 · 137 lines · 1,367 tokens per session scan A bf381d034bf2
mcp-elicit CLAUDE.md is an instructions file published in the GitHub repository blizzy78/mcp-elicit (2 stars, last pushed 1y ago), licensed MIT. It adds 1,367 tokens to every session, about $0.0068 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
mcp-task-manager CLAUDE.md
Instructions for blizzy78/mcp-task-manager, covering task manager mcp server, what the project is about, mcp specification compliance, high level view of the architecture and core components.
mcp-task-manager basic-tests.instructions.md
Instructions for blizzy78/mcp-task-manager: Keep tests simple. We only need a basic test suite. Only add or change what's really needed. Only test a few edge cases, not all exotic ones. Test code coverage of 100% is ideal, but not required.
mcp-task-manager run-tests.instructions.md
Instructions for blizzy78/mcp-task-manager: The command to run tests only is pnpm test. The command to run tests with code coverage is pnpm test:coverage.
askdb AGENTS.md
Instructions for mgorabbani/askdb, covering agent guidelines, environment, how to run, project structure and code style.
askdb CLAUDE.md
Instructions for mgorabbani/askdb, covering key paths, tech stack and rules.
joplin-server-vector-memory GEMINI.md
Gemini CLI instructions for adamoutler/joplin-server-vector-memory, covering joplin server vector memory mcp - gemini methodology, 1. code discovery & context gathering, 2. refactoring & code quality, 3. execution & testing and 4. architectural rules.