agentleFS
BlockRunAIBlockRunAI/blockrun-mcp/skills/search/SKILL.md

search

Skill389 starsChanged 23 days agoMITView on GitHub

Use when the user wants real-time web or news results with AI-summarized answers and citations — Grok Live Search via BlockRun. Cheapest path for "what just happened" questions where freshness beats neural-semantic ranking.

54 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use fetch, integrate and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • jtfasulo7Skill

    fetch

    Use this skill when the user wants to retrieve a URL without a full browser session: fetch HTML or JSON from static pages, inspect status codes or headers, follow redirects, or get page source for simple scraping. Prefer it over a browser when JavaScript rendering and page interaction are not needed. Supports proxies and redirect control.

    Also in 3 projects that use this

  • modeled-information-formatSkill

    integrate

    This skill should be used when the user asks to "integrate mnemonic", "wire plugin", "add memory to plugin", "enable memory capture in plugin", "integrate memory operations", "add mnemonic protocol", "remove mnemonic integration", "rollback plugin integration", or "migrate legacy memory sections". It wires mnemonic memory capture and recall workflows into other Claude Code plugins using sentinel markers.

    Also in 3 projects that use this

  • soilmassSkill

    export

    Animation export configurations including format selection, resolution, framerate, quality, and optimization settings. Use when rendering animations for web, mobile, video, or social media. Provides tokens for all export parameters across Lottie, GIF, video, and sprite sheet formats.

    Also in 4 projects that use this

  • rogue-dev-studioSkill

    monitoring

    Claude monitoring and usage tracking tools (UV, claude-monitor, claude-usage-cli). Use when the project needs this capability or the user / team manifest asks for it. Use for specialized `monitoring` work when listed in TEAM.yaml or explicitly requested.

    Also in 3 projects that use this

  • DockerSkill

    write

    Write or edit reader-facing technical prose for immediate comprehension. Use for documentation, PR titles and descriptions, release notes, design documents, user-facing explanations, and substantive comments. Also use when asked to make writing clearer, more natural, less AI-generated, or easier to read. For documentation fixes, handles edits, formatting, self-review, and commits after research identifies what to change. Do not use for code-only tasks with no prose deliverable.

    Also in 3 projects that use this

  • JaimeGBASkill

    ingest

    Digest an external source (article, paper, transcript, URL, book chapter) and integrate its content into the knowledge base

    Also in 4 projects that use this

The file

Files
SKILL.md

Live Search (Grok)

Real-time web + news search with AI-summarized results and citations. Flat $0.081 per call on Base ($0.08 + $0.001 network fee; $0.08 on Solana), at any max_results — verified against live 402 quotes 2026-10-06. Best for fresh queries; for semantic / neural research use blockrun_exa instead.

How to Call from MCP

blockrun_search({ body: {
  query: "what's the consensus on the Fed's next move",
  sources: ["web", "news"],
  max_results: 10
}})

Body Shape

FieldRequiredTypeNotes
queryyesstringNatural-language search query
sourcesnostring[]Subset of ["web","news"]. Default: ["web"] — pass both for news coverage. There is no X/Twitter source (removed upstream 2026-07-05; asking for "x" is refused before payment). Does NOT multiply price.
max_resultsnonumber1–50, default 10. Does not change the price — ask for as many sources as the question needs.
from_datenostringYYYY-MM-DD lower bound on result date
to_datenostringYYYY-MM-DD upper bound

When to Reach for Which Source

User intentsources setting
Breaking news / today's headlines["news"]
Social / X sentimentnot served — there is no X source; use ["news","web"] and say so, or blockrun_exa for a targeted crawl
Backgrounder / explainer / docs["web"]
General "find current info" question["web","news"] (omitting it searches the web only)

Worked Examples

1. "What's the latest on the ETH ETF approval timeline?"

blockrun_search({ body: { query: "Ethereum ETF approval SEC", sources: ["news","web"], max_results: 8 } })

Cost: $0.081.

2. "What happened in Solana's latest outage?"

blockrun_search({ body: { query: "Solana outage today", sources: ["news","web"], max_results: 15 } })

Cost: $0.081. There is no X/Twitter source: sources: ["x"] is refused before payment with the live list, so do not promise "what X is saying" — say what the news and web say.

3. "Background on Pectra upgrade, last 90 days only"

blockrun_search({ body: {
  query: "Ethereum Pectra upgrade",
  sources: ["web","news"],
  from_date: "2026-02-17"
}})

Cost: $0.081 (the default 10 sources — same price as any other count).

search vs exa — Pick the Right Tool

Use caseTool
"What's happening right now?" — freshness mattersblockrun_search
"Find the canonical paper on X" — semantic relevance mattersblockrun_exa
"Pull the full text of these 5 URLs" — content fetchblockrun_exa contents
"Cited answer to a question"both work; blockrun_exa answer is grounded in pre-indexed corpus, blockrun_search searches the live web

Notes

  • Returns AI-summarized text + a list of sources with URLs. The summary is one paragraph; sources let you drill in.
  • One flat price per call. Neither sources nor max_results changes it: the upstream decides how many searches to run, so the count never drove the cost (repriced 2026-09-29).
  • Date filters are strict — results outside the window are dropped, not down-ranked.

Reference

  • Endpoint: POST /v1/search
  • Upstream: xAI Grok Live Search

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.