An onboarding guide for x-use, a tool that connects an AI client to X accounts. It checks the installation, connects the required server, and collects account settings such as cookies, topics, and writing style.

Use it when installing x-use, adding an X account, or getting started. It helps verify the browser and related dependencies, register the connection, and configure the account.

It removes the need to understand setup files, server registration, or cookie exports before using x-use. It also guides account setup through questions instead of manual configuration.

x-use-setup — Skill for Claude Code and Codex by ihuzaifashoukat

Install

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.

Any agent

npx skills add ihuzaifashoukat/x-use --skill x-use-setup

Clone the repo

git clone --depth 1 https://github.com/ihuzaifashoukat/x-use

Made for: Claude Code, Codex.

Or install x-use, the plugin that ships this one along with the rest of its 4 skills.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/ihuzaifashoukat/x-use/x-use-setup/github.svg)](https://agentmods.dev/skills/ihuzaifashoukat/x-use/x-use-setup)

Your own site

<a href="https://agentmods.dev/skills/ihuzaifashoukat/x-use/x-use-setup"><img src="https://agentmods.dev/badge/skills/ihuzaifashoukat/x-use/x-use-setup/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/ihuzaifashoukat/x-use/x-use-setup"><img src="https://agentmods.dev/badge/skills/ihuzaifashoukat/x-use/x-use-setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 754 The whole file, excluding the scripts and references it only reads on demand.

Security scan B 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.

Model	Per session	Once invoked
Fable 5.1	$0.00064	$0.00754
Opus 5	$0.00032	$0.00377
Sonnet 5	$0.00013	$0.00151
Haiku 4.5	$0.00006	$0.00075

Measured 9d ago against content hash 569746b07f28, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade B, and why

x-use-setup scanned grade B 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 9d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

- Codex (`~/.codex/config.toml`):

plugins/x-use/skills/x-use-setup/SKILL.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

x-use setup

Goal: a working account, configured conversationally. The user should never edit a config file by hand. Work through these steps in order, skipping any that are already done, and confirm each before moving on.

1. Verify the install

Run x-use doctor. It checks Chrome/driver, cookies, LLM key, proxies.
If x-use is not found: pip install x-use-mcp, then re-run doctor.
If the MCP server is not registered in this client yet, register it, then ask the user to restart the client:
- Claude Desktop (claude_desktop_config.json): {"mcpServers": {"x-use": {"command": "x-use", "args": ["mcp"]}}}
- Claude Code: claude mcp add x-use -- x-use mcp
- Codex (~/.codex/config.toml): [mcp_servers.x-use] with command = "x-use", args = ["mcp"]

2. Account + cookies

Ask: "What should this account be called (a short id like main or brand)?" Then explain cookie export:

Install a cookie-export browser extension (e.g. "Cookie-Editor").
Log into x.com in that browser, open the extension on x.com, Export as JSON.
Save the file somewhere on this machine and give me the path.

Then call add_account(account_id, cookie_file=<path>). The file is validated and copied server-side; cookie values never pass through the chat. Verify with get_account_health(account); cookie status should be valid.

3. Niche and keywords

Ask: "What niche are you in, which keywords should I watch, and whose posts do you want to engage with (profiles)?" Apply with update_account(account, target_keywords=[...], competitor_profiles=[...]).

4. Persona

Ask how they want to sound. Offer the three starter personas from presets/personas/ (builder, founder, curator) as starting points, let the user pick or dictate their own, then apply with update_account(account, persona=<text>). Keep it under 4000 chars, markdown, covering: voice, topics, reply style, what to avoid, 1-2 example replies.

5. Optional extras (only if relevant)

Multi-account: repeat from step 2, and ask about proxies, added with add_proxy(pool, proxy_url) and assign with update_account(account, proxy="pool:<name>").
Background automation (unattended "auto" text): needs one OpenAI-compatible key in config/settings.json under llm (api_key, base_url, model). Interactive use needs no key at all.

Read the full file on GitHub · 67 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.

9d ago First seen · 67 lines · 64 tokens per session scan B 569746b07f28

Subscribe to this mod's changes

x-use-setup is a skill published in the GitHub repository ihuzaifashoukat/x-use (165 stars, last pushed 21d ago), licensed MIT. It adds 64 tokens to every session and 754 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

LLM Marketing and SEO ai-agents automation browser-automation selenium twitter-automation

x-use-setup

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade B, and why

Reads agent configuration directoriesmediumAgent snooping

How it starts

x-use setup

1. Verify the install

2. Account + cookies

3. Niche and keywords

4. Persona

5. Optional extras (only if relevant)

What this file has done since we first saw it

Other skills, from other repositories

network-sink-skill

unresolved-boundary-skill

stdout-logging-skill

dws

package-author

taiyi-integration