xmcp: Instructions file for Claude Code

CLAUDE.md

xmcp CLAUDE.md is an instructions file for Claude Code from vibeforge1111/xmcp. It costs 1,270 tokens per session, scanned A, original, MIT.

A project instruction file for XMCP, including rules for retrieving articles from X, formerly known as Twitter. It says those articles must be rendered in a browser before their content can be read.

In plain words
What is it for?
Use it when working on XMCP or when an AI assistant must fetch and read an X article.
Why use it?
It prevents agents from using methods that return incomplete article content and tells them which retrieval tool to use.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is vibeforge1111/xmcp's own configuration. It tells Claude Code how to work on xmcp 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 xmcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to vibeforge1111/xmcp. 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/vibeforge1111/xmcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/vibeforge1111/xmcp

Made for: Claude Code.

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 xmcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/vibeforge1111/xmcp/claude-md.svg)](https://agentmods.dev/instructions/vibeforge1111/xmcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/vibeforge1111/xmcp/claude-md"><img src="https://agentmods.dev/badge/instructions/vibeforge1111/xmcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,270 This file is loaded in full into every session.
When invoked 1,270 The same file — it is already loaded in full.
Security scan A 1 finding. 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 $0.01270 $0.01270
Opus 5 $0.00635 $0.00635
Sonnet 5 $0.00254 $0.00254
Haiku 4.5 $0.00127 $0.00127

Measured 6d ago against content hash df7ae3d8da59, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

xmcp CLAUDE.md scanned grade A with 1 finding 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 6d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

Regular HTTP requests (WebFetch, curl, requests) will NOT work for X articles because:
CLAUDE.md · 175 lines

How it starts

The opening of the file, as written. The whole thing — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.

XMCP - AI Agent Instructions

This file provides instructions for AI agents (Claude, GPT, etc.) using the XMCP.

CRITICAL: Article Fetching Requires Playwright

IMPORTANT: When fetching X/Twitter articles, you MUST use the get_article tool which uses Playwright.

Regular HTTP requests (WebFetch, curl, requests) will NOT work for X articles because:

  • X articles require JavaScript to render
  • Simple HTTP returns empty/incomplete content
  • The get_article tool uses Playwright to properly render the page

Correct Usage

# When user asks to read an X article:
1. Use get_article tool with the URL
2. DO NOT use WebFetch - it will fail
3. DO NOT try to scrape with requests - it will fail

Example

User: "Read this article: https://x.com/elonmusk/status/123456789"

CORRECT:

result = await get_article("https://x.com/elonmusk/status/123456789")
# Returns: {title, author, content, url}

WRONG:

# These will NOT work for X articles:
WebFetch("https://x.com/...")  # Fails - needs JS
requests.get("https://x.com/...")  # Fails - needs JS

Available Tool Groups

The MCP has 8 tool groups. Which are available depends on the configured profile.

Check What's Enabled

The profile is set via X_MCP_PROFILE environment variable:

  • researcher (default): read-only, safe for automation
  • creator: can post and engage
  • manager: full account control
  • automation: everything including DMs

Group Reference

Group Key Tools When to Use
research search_twitter, get_user_profile, get_article Finding information, monitoring
engage favorite_tweet, retweet, bookmark_tweet Engaging with content
publish post_tweet, create_thread, quote_tweet Creating content
social follow_user, block_user, mute_user Managing relationships
conversations get_conversation, get_replies Reading threads
lists create_list, get_list_tweets List management
dms send_dm, get_dm_conversations Direct messages

Read the full file on GitHub · 175 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. 6d ago First seen · 175 lines · 1,270 tokens per session scan A df7ae3d8da59

Subscribe to this mod's changes

xmcp CLAUDE.md is an instructions file published in the GitHub repository vibeforge1111/xmcp (18 stars, last pushed 7mo ago), licensed MIT. It adds 1,270 tokens to every session, about $0.0064 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

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 · 5,182 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

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

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

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 · 7,104 tokens