X Money guide
An agent skill by cursor, from cursor/plugins. Tags: access-control, compliance, documentation, finance, security.
What it does
Read this before the first X Money action in a session and again on any X Money error, refusal, or missing capability. Covers the approval rule for every action that moves money (always ask, every time, no exceptions), how the connection works (connection code plus passkey in the X app), how to guide the user through connect, reconnect, and revoke at x.com/i/money/settings/connections, and what each failure message means.
Install
With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:
npx skills add cursor/plugins --skill 'X Money guide'Or copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):
git clone --depth 1 https://github.com/cursor/plugins
cp -r plugins/third_party/x-money/skills/x-money-guide ~/.claude/skills/'X Money guide'Safety box score
Grade D, elevated risk: 21 of 100 risk points, rated 2026-10-15. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.
This skill is a documentation-only guide for using X Money through a remote MCP server. The main risk is financial autonomy: it can send/request money and create merchant card purchases, while account actions and payment data leave the machine over the network.
| Category | Level | Why |
|---|---|---|
| Code & shell execution | 0 (none) | The shipped file is only `SKILL.md`; there are no scripts, shell commands, or evaluable code paths to run. |
| Network access | 3 (high) | It explicitly uses a remote service, `https://mcp.money.x.com/mcp`, and sends the user to X Money web/app settings for connection and revocation, so account/payment data is handled off-machine. |
| Filesystem reach | 0 (none) | The skill does not read, write, or delete local files or system paths; it only references web pages and in-app flows. |
| Secrets & credentials | 0 (none) | It says never to ask for passwords, passkeys, tokens, card numbers, or bank logins, and does not itself collect or store secrets. |
| Privilege & persistence | 0 (none) | There is no sudo, service installation, shell startup editing, or other privilege escalation behavior in the guide. |
| Instruction hijack surface | 0 (none) | The text contains behavioral guidance, but nothing that asks the agent to ignore higher-priority instructions, fetch remote instructions, or hide information from the user. |
| Irreversible actions | 3 (high) | The skill is inherently about real-money actions: it covers sending money, requesting money, paying merchants, and creating purchase cards, even though it requires a fresh approval for each action. |
| Transparency | 0 (none) | The contents are plain markdown and fully readable; there are no binaries, minified blobs, or decoded-at-runtime payloads. |
Before installing
- Confirm you are comfortable granting an agent the ability to send/request money and create card purchases, with a fresh approval required every time.
- Verify you can revoke access at `https://x.com/i/money/settings/connections` before relying on it.
- Start with read-only actions only (balances/transactions) and a small test payment if you plan to use money-moving features.
Rated 2026-10-15 by an automated review of 1 file from the skill's repository.
Source
- Repository
- cursor/plugins (all skills from this repository)
- Path
- third_party/x-money/skills/x-money-guide/SKILL.md
- Branch
- main
- Collection
- cursor
- Updated
- 2026-09-23
Related skills
- aws-iam — Provides verified corrections for IAM behaviors that AI agents frequently get wrong — policy evaluation edge cases, trust policy gotchas, STS session limits.
- hardware-compliance — Reference knowledge base on EU hardware/IoT cybersecurity law.
- security-reviewer — Identifies security vulnerabilities, generates structured audit reports with severity ratings, and provides actionable remediation guidance.
- X MCP guide — ALWAYS read this when a user connects the X plugin or any X MCP, before using any X connection, and again on any X error.
- agents-harden — Use when preparing your agent for production — IAM scoping, inbound auth (JWT, SigV4), secrets management, cold start optimization, session lifecycle.
- audit-prep-assistant — Prepares codebases for security review using Trail of Bits' checklist.