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 exa-labs/exa-cursor-plugin --skill exa-web-searchgit clone --depth 1 https://github.com/exa-labs/exa-cursor-pluginWrote 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/exa-labs/exa-cursor-plugin/exa-web-search)<a href="https://agentmods.dev/skills/exa-labs/exa-cursor-plugin/exa-web-search"><img src="https://agentmods.dev/badge/skills/exa-labs/exa-cursor-plugin/exa-web-search.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00049 | $0.00573 |
| Opus 5 | $0.00024 | $0.00287 |
| Sonnet 5 | $0.00010 | $0.00115 |
| Haiku 4.5 | $0.00005 | $0.00057 |
Grade A, and why
exa-web-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 7d 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web Search (Exa)
Search the web for: $ARGUMENTS
Tool
Use web_search_exa for all web search requests.
When to Use
- Current events, news, recent developments
- Fact-checking or verifying claims
- Finding articles, blog posts, documentation
- Any question where the answer may have changed since training data cutoff
- General research and information gathering
- Code examples, API docs, and library usage
Trigger phrases: "search for", "find me", "look up", "what is", "find articles about", "research", "any recent", or any question that may need current information.
How to Search
web_search_exa accepts:
query(string, required) — natural language search querynumResults(number, optional) — how many results to return
Query Tips
- Write queries as natural language statements, not keywords
- Be specific: "latest React 19 server components changes" beats "react updates"
- Include time context when relevant: "2026 AI regulation proposals"
- For broad topics, run 2-3 queries with different phrasings and merge results
Tuning Results
- Quick lookup →
numResults: 3-5 - Standard research →
numResults: 5-10(default) - Deep dive →
numResults: 10-20
Output Format
For every claim or fact, cite the source inline:
- Lead with the direct answer
- Support with specific facts, numbers, dates
- Cite every fact with its source URL
- End with a Sources section listing all URLs used
Before You Start
Check if Exa MCP is installed by confirming web_search_exa is available in your tool list.
If the MCP Server Is Not Connected
You (the AI) must:
- Stop immediately — do NOT search the web yourself, do NOT use websearch, and do NOT try to answer the query from your own knowledge.
- Inform the user that Exa MCP is not connected.
Request the user to:
- Run the
/exa-setupcommand in Cursor to add the Exa MCP server. - Go to Cursor Settings → Tools & MCP and make sure Exa is toggled on (green).
- Retry their search after completing the above steps.
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.
- 7d ago First seen · 70 lines · 49 tokens per session scan A 9668b3cff3f5
exa-web-search is a skill published in the GitHub repository exa-labs/exa-cursor-plugin (6 stars, last pushed 4mo ago), licensed MIT. It adds 49 tokens to every session and 573 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 2026-08-31.
Other skills, from other repositories
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
interactive-login
How to complete browser/interactive logins (aws / gh / glab / gcloud). The platform backgrounds the login poller so it survives the human's browser round-trip — and when that does NOT work.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
azure-messaging-webpubsub-java
Build real-time web applications with Azure Web PubSub SDK for Java. Use when implementing WebSocket-based messaging, live updates, chat applications, or server-to-client push notifications.
google-safe-browsing
Prevent and fix Google Safe Browsing "Dangerous site" flags. Use when launching a public web app, buying/picking a domain, building a login or signup page, or when any site shows a red "Dangerous site" / "Deceptive site" warning in Chrome, Brave, Safari, Firefox, or Edge. Triggers on "dangerous site", "deceptive…