grokodex-x-search

grokodex-x-search is a skill for Claude Code from anlostsheep/grokodex. It costs 62 tokens per session (1,359 once invoked), scanned A, original, MIT.

A search skill for finding recent public posts and discussions on X (formerly Twitter) through local Grok. It supports ordinary keyword searches and searches based on meaning or topic.

In plain words
What is it for?
Use it to find posts by topic or handle, check what people are saying, investigate public reaction, or limit results to specific dates.
Why use it?
It helps answer questions about current reactions, posts, people, and discussions on X without using a general web search.

Skill for Claude Code

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

Part of the grokodex plugin — 6 skills shipped together

Good fit Use it to find posts by topic or handle, check what people are saying, investigate public reaction, or limit results to specific dates.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/anlostsheep/grokodex/grokodex-x-search
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 anlostsheep/grokodex --skill grokodex-x-search
Clone the repo
git clone --depth 1 https://github.com/anlostsheep/grokodex

Made for: Claude Code.

Or install grokodex, the plugin that ships this one along with the rest of its 6 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.

agentmods badge for grokodex-x-search

README.md
[![agentmods](https://agentmods.dev/badge/skills/anlostsheep/grokodex/grokodex-x-search/github.svg)](https://agentmods.dev/skills/anlostsheep/grokodex/grokodex-x-search)
Your own site
<a href="https://agentmods.dev/skills/anlostsheep/grokodex/grokodex-x-search"><img src="https://agentmods.dev/badge/skills/anlostsheep/grokodex/grokodex-x-search/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.

agentmods 80×15 button for grokodex-x-search

Your own site · 80×15
<a href="https://agentmods.dev/skills/anlostsheep/grokodex/grokodex-x-search"><img src="https://agentmods.dev/badge/skills/anlostsheep/grokodex/grokodex-x-search.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,359 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00062 $0.01359
Opus 5 $0.00031 $0.00679
Sonnet 5 $0.00012 $0.00272
Haiku 4.5 $0.00006 $0.00136

Measured 11d ago against content hash 7a2435757242, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

grokodex-x-search 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 11d 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.

plugins/grokodex/skills/grokodex-x-search/SKILL.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Search X (Twitter) through a constrained headless Grok task (read-only; no repo edits; never full shell inherit).

When to use

  • User wants recent posts, sentiment, or discussion on X about a topic
  • Looking up posts by people / handles
  • Semantic “what are people saying about …” vs keyword queries
  • Not for general coding → grokodex-run
  • Not for image generation → grokodex-imagine

Tool preference

  1. Call MCP tool grok_x_search (logical name; Claude may show an mcp__… prefix).
  2. Do not use a terminal/shell tool to run grok for X search.
  3. Do not pass inherit / host_sandbox / codex_sandbox (tool always runs restricted-x-search).

How to fill arguments

Arg Required Default How to set
query yes Natural-language question or keywords
mode no see discipline semantic = meaning/topic; keyword = exact-ish terms (prefer for vague “news/hot today”)
limit no 5 How many hits to return (bridge caps at 50)
from_date no YYYY-MM-DD inclusive start; set to today for “today’s news”
to_date no YYYY-MM-DD inclusive end; set to today for “today’s news”
usernames no Array of handles (with or without @) to bias/limit authors
cwd no host cwd Working directory
timeout_ms no 90000 (bridge short path) Raise only if needed after narrowing query
model no CLI default Only if user requests a model

Choosing mode

  • keyword — cashtags, slogans, hashtags, and vague “today’s interesting news/hot posts” (use with today’s dates)
  • semantic — “what are people saying about library X”, product launches, clear topical questions

Query tips

  • Include time intent in from_date/to_date rather than only in prose when possible.
  • Prefer usernames for “from @foo and @bar”.
  • Keep limit small (3–10) for chat readability unless user wants more.

Read the full file on GitHub · 114 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. 11d ago First seen · 114 lines · 62 tokens per session scan A 7a2435757242

Subscribe to this mod's changes

grokodex-x-search is a skill published in the GitHub repository anlostsheep/grokodex (2 stars, last pushed 1mo ago), licensed MIT. It adds 62 tokens to every session and 1,359 once invoked, about $0.0003 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 2026-08-31.