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 skills add nirholas/XActions --skill xactions-mcp-servergit clone --depth 1 https://github.com/nirholas/XActionsWrote 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/skills/nirholas/xactions/xactions-mcp-server)<a href="https://agentmods.dev/skills/nirholas/xactions/xactions-mcp-server"><img src="https://agentmods.dev/badge/skills/nirholas/xactions/xactions-mcp-server/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.
<a href="https://agentmods.dev/skills/nirholas/xactions/xactions-mcp-server"><img src="https://agentmods.dev/badge/skills/nirholas/xactions/xactions-mcp-server.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00096 | $0.00903 |
| Opus 5.5 | $0.00038 | $0.00361 |
| Sonnet 5.5 | $0.00019 | $0.00181 |
| Haiku 4.5 | $0.00010 | $0.00090 |
Grade A, and why
xactions-mcp-server 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 1mo 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
XActions MCP Server
The definitive free Twitter/X MCP server. 154 tools for AI agents.
Quick Start
{
"mcpServers": {
"xactions": {
"command": "npx",
"args": ["xactions-mcp"],
"env": {
"XACTIONS_SESSION_COOKIE": "your_auth_token_here"
}
}
}
}
Setup
1. Get auth_token
DevTools (F12) -> Application -> Cookies -> x.com -> copy auth_token value
2. Configure your client
Claude Desktop:
xactions mcp-config --client claude --write
Cursor:
xactions mcp-config --client cursor --write
Windsurf / VS Code:
xactions mcp-config --client windsurf --write
xactions mcp-config --client vscode --write
3. Restart your client
Available Tools (68+)
Scraping
x_get_profile, x_get_followers, x_get_following, x_get_non_followers, x_get_tweets, x_search_tweets, x_get_thread, x_download_video
Actions
x_follow, x_unfollow, x_unfollow_non_followers, x_post_tweet, x_like, x_retweet, x_delete_tweet, x_reply, x_bookmark, x_get_bookmarks, x_clear_bookmarks, x_auto_like, x_engage
Analysis
x_detect_unfollowers, x_best_time_to_post, x_analyze_sentiment, x_monitor_reputation, x_reputation_report, x_competitor_analysis, x_brand_monitor
Profile & Settings
x_update_profile, x_get_settings, x_toggle_protected, x_get_blocked, x_check_premium
Content
x_post_thread, x_create_poll, x_schedule_post, x_publish_article
Discovery
x_get_trends, x_get_explore
Messaging
x_send_dm, x_get_conversations, x_export_dms
AI (requires OPENROUTER_API_KEY)
x_analyze_voice, x_generate_tweet, x_rewrite_tweet, x_summarize_thread
Advanced
- Streaming:
x_stream_start/stop/list/pause/resume/status/history - Workflows:
x_workflow_create/run/list/actions - Social Graph:
x_graph_build/analyze/recommendations/list - Portability:
x_export_account/migrate_account/diff_exports
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.
- 1mo ago Changed 6a30886429d5
- 1mo ago First seen · 111 lines · 96 tokens per session scan A 3dddac084f58
xactions-mcp-server is a skill published in the GitHub repository nirholas/XActions (594 stars, last pushed today), licensed Apache-2.0. It adds 96 tokens to every session and 903 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
drive-the-ui
Drive the page the user has open through live UI actions. List the actions a page accepts, call them with typed payloads, and read the live state including unsaved edits. Use when the user is looking at a page you can operate, such as the evaluations workbench, and a change should happen in front of them rather than…
browser-test
Check that a feature works by walking its scenarios in a real browser and writing a pass/fail report with evidence. A recipe over haven browser: no test files, no browser commands of its own. Use when someone says 'browser test', 'verify this in the browser', 'walk the scenarios', 'check the feature live', or hands…
haven-auth
Sign in to this worktree's stack as admin or a seeded login with haven browser login --as, which writes a Playwright storage-state file and never prints the password. Use when someone says 'haven auth', 'haven browser login --as', 'sign in as admin', 'log in as a seeded user', 'storage state', 'a signed-in session for…
haven-orb
Read what a person sent from the haven orb on the app page: haven orb feedback notes with selector, viewport, console and requests, and haven orb console|network. Use when someone says 'haven feedback', 'haven page console', 'haven orb feedback', 'the haven orb', 'read the notes I left', 'resolve the feedback', 'wait…
browser-telemetry-and-errors
What the small browser support packages are for and when feature code uses them: packages/react-rum (browser traces, error spans, navigation spans; the host starts it, features do not), packages/error-views (HandledErrorState, HandledErrorAlert, FormServerError, AggregateReadOnlyGate, resolveErrorCopy), the error…
browser-pair
Iterate on UI with a person watching and giving live visual feedback. Pointer skill: the person uses their own tab on the stack and the haven orb; you read their notes and check fixes with haven browser. Use when the user says 'browser pair', 'paired browser', 'let's look at this together', 'open chromium', or wants…