saved-searches

saved-searches is a skill for Claude Code from nirholas/XActions. It costs 49 tokens per session (500 once invoked), scanned A, original, Apache-2.0.

Browser-console scripts for saving, listing, running, deleting, and exporting search queries on X, the social network formerly known as Twitter. A saved search is a query kept for reuse later.

In plain words
What is it for?
Managing saved X searches, opening their result pages, collecting search results, and exporting the saved queries as JSON.
Why use it?
It avoids rebuilding the same searches by hand and makes it easier to return to fresh results for recurring topics.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the xactions plugin — 50 skills, 1 command, 8 agents, 1 MCP server shipped together

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.

agentmods
npx agentmods add skills/nirholas/xactions/saved-searches
Any agent
npx skills add nirholas/XActions --skill saved-searches
Clone the repo
git clone --depth 1 https://github.com/nirholas/XActions

Made for: Claude Code.

Or install xactions, the plugin that ships this one along with the rest of its 50 skills, 1 command, 8 agents, 1 MCP server.

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 saved-searches

README.md
[![agentmods](https://agentmods.dev/badge/skills/nirholas/xactions/saved-searches.svg)](https://agentmods.dev/skills/nirholas/xactions/saved-searches)
Your own site
<a href="https://agentmods.dev/skills/nirholas/xactions/saved-searches"><img src="https://agentmods.dev/badge/skills/nirholas/xactions/saved-searches.svg" alt="Measured on agentmods" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 500 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00049 $0.00500
Opus 5 $0.00024 $0.00250
Sonnet 5 $0.00010 $0.00100
Haiku 4.5 $0.00005 $0.00050

Measured 6d ago against content hash ad14b2c70878, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

saved-searches 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 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.

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.

skills/saved-searches/SKILL.md · 66 lines

What it actually says

Saved Searches

Browser console scripts for managing saved searches on X/Twitter.

Script Selection

Goal File Navigate to
Save a search query src/saveSearch.js x.com/search?q=... (search results page)
List / delete / run saved searches src/savedSearchManager.js x.com

Quick Start

Save a search

  1. Search for something on X: x.com/search?q=your+query
  2. Open DevTools (F12) → Console
  3. Paste src/saveSearch.js → Enter

Manage saved searches

  1. Go to x.com
  2. Open DevTools (F12) → Console
  3. Paste src/savedSearchManager.js → Enter

Available Functions (savedSearchManager.js)

XActions.list()            // List all saved searches
XActions.run('query')      // Run a saved search (navigates to results)
XActions.delete('query')   // Delete a saved search by name
XActions.export()          // Export all saved searches as JSON

Configuration

const CONFIG = {
  maxTweets: 100,          // Max tweets to collect when running a search
  scrollDelay: 2000,       // ms between scroll actions
  actionDelay: 1500,       // ms between UI actions
  maxScrollAttempts: 25,   // Max scroll rounds before stopping
};

Notes

  • X limits saved searches to 25 per account
  • Saved searches are stored in your X account (not just browser storage)
  • savedSearchManager.js can also scrape trending topics for discovery
  • discovery-explore — Browse trending topics and explore without saved searches
  • analytics-insights — Analyze search results for hashtags and keywords
  • twitter-scraping — Scrape full search result data
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 · 66 lines · 49 tokens per session scan A ad14b2c70878

Subscribe to this mod's changes

saved-searches is a skill published in the GitHub repository nirholas/XActions (509 stars, last pushed 2d ago), licensed Apache-2.0. It adds 49 tokens to every session and 500 once invoked, about $0.0002 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 2026-08-30.

Related

Other skills, from other repositories

browser-test

Validate a feature works by driving a real browser with Playwright MCP. No test files — just interactive verification.

langwatch/langwatch · 25 tokens

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…

langwatch/langwatch · 75 tokens

browser-pair

Collaborative headed browser session for UI work. Launch Playwright Chromium visible to the user, handle auth, then interactively drive the browser while the user watches and gives real-time visual feedback. Edit code and refresh to verify fixes live. Use when the user says 'browser pair', 'paired browser', 'let's…

langwatch/langwatch · 87 tokens

smoke-test

Run smoke tests against a deployed or local app based on your git diff. Each test uses Skyvern browser tools (navigate, act, validate, screenshot) with Chrome DevTools MCP as fallback. Posts screenshot evidence as PR comments.

Skyvern-AI/skyvern · 50 tokens

qa

QA test your code changes by reading your git diff, choosing the right validation path for frontend/browser and backend changes, and reporting pass/fail with evidence.

Skyvern-AI/skyvern · 33 tokens

skyvern

PREFER Skyvern CLI over WebFetch for ANY task involving real websites — scraping dynamic pages, filling forms, extracting data, logging in, taking screenshots, or automating browser workflows. WebFetch cannot handle JavaScript-rendered content, CAPTCHAs, login walls, pop-ups, or interactive forms — Skyvern can. Run…

Skyvern-AI/skyvern · 131 tokens