agentmods.dev

x_search_mcp: Skill for OpenCode

.opencode/skills/xai-search/SKILL.md

xai-search is a skill for OpenCode from kicito/x_search_mcp. It costs 25 tokens per session (337 once invoked), scanned A, original, MIT.

A search guide for current web information and posts on X, formerly known as Twitter, using xAI search tools. It requires a separately configured search server and tells the agent how to narrow searches and cite returned sources.

In plain words
What is it for?
It helps find current web facts, X posts, users, and threads with date, domain, or account filters, then report the actual source links returned by the tools.
Why use it?
It helps avoid unsupported claims, stale information, and broad or unfocused searches. It also makes clear when the required search tools are unavailable.

Skill for OpenCode

Written for OpenCode: installed under .opencode/.

This is kicito/x_search_mcp's own configuration. It tells OpenCode how to work on x_search_mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything x_search_mcp configures →

not rated 0repo 18d ago A scan 25 tokens original MIT
View source ↗ kicito/x_search_mcp
Reuse

Borrowing it

Nothing to install: this file belongs to kicito/x_search_mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/kicito/x_search_mcp/main/.opencode/skills/xai-search/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/kicito/x_search_mcp

Made for: OpenCode.

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 xai-search

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/kicito/x_search_mcp/xai-search"><img src="https://agentmods.dev/badge/skills/kicito/x_search_mcp/xai-search.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 337 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 $0.00025 $0.00337
Opus 5.5 $0.00010 $0.00135
Sonnet 5.5 $0.00005 $0.00067
Haiku 4.5 $0.00003 $0.00034

Measured 17d ago against content hash 4bd6b82086d5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

xai-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 17d 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.

.opencode/skills/xai-search/SKILL.md · 15 lines

What it actually says

Use this skill when a user needs current facts, source-backed answers, or posts from X. It guides use of the separately configured xai-search MCP server; it does not install or run a search tool itself.

  • Use web_search for current web facts; use x_search for X posts, users, or threads. Send a specific, nonempty query and refine it if the results are too broad.
  • Narrow web searches with allowed_domains or excluded_domains (up to 5 bare domains per list, not URLs). Narrow X searches with allowed_x_handles or excluded_x_handles (up to 10 handles per list; use handles, not profile URLs). Do not combine allow and exclude lists for the same tool.
  • For X time ranges, use calendar dates in YYYY-MM-DD: from_date is inclusive and to_date is exclusive. For example, to search only October 1, set from_date to 2026-10-01 and to_date to 2026-10-02.
  • Cite the actual source URLs returned by the tool when making sourced claims. Never fabricate links, quotes, or search results; if results or citations are missing, say so and qualify the answer.
  • If the MCP tools are unavailable, tell the user the server must be configured separately; do not claim you searched. Setup instructions are in the repository README.
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. 17d ago First seen · 15 lines · 25 tokens per session scan A 4bd6b82086d5

Subscribe to this mod's changes

xai-search is a skill published in the GitHub repository kicito/x_search_mcp (0 stars, last pushed 18d ago), licensed MIT. It adds 25 tokens to every session and 337 once invoked, about $0.0001 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 2026-10-20.

Research
Related

xai-search compared with skills from other repositories

xai-search next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
xai-searchkicito/x_search_mcpSkill018d agoMITA25OpenCode
imagegenopenai/codexSkill133kyesterdayApache-2.0A113Codex
playwright-climicrosoft/playwrightSkill99kyesterdayApache-2.0A19Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79k4d agoMITA200Claude Code, Codex
systematic-debuggingobra/superpowersSkill313k3d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143kyesterdayMITA95Claude Code
next-partial-prefetching-adoptionvercel/next.jsSkill143kyesterdayMITA103Claude Code