exa-best-practices

exa-best-practices is a skill for Claude Code, Codex from exa-labs/exa-cursor-plugin. It costs 37 tokens per session (421 once invoked), scanned A, original, MIT.

A reference guide for using Exa web-search tools. Exa is a service for finding and reading web pages, and the guide covers tool choice, search wording, citations, and troubleshooting.

In plain words
What is it for?
Use it to choose between web search and URL fetching, refine queries, cite source URLs, and diagnose unavailable tools.
Why use it?
It helps produce better searches and properly sourced answers when using Exa.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to choose between web search and URL fetching, refine queries, cite source URLs, and diagnose unavailable tools.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/exa-labs/exa-cursor-plugin/exa-best-practices
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 exa-labs/exa-cursor-plugin --skill exa-best-practices
Clone the repo
git clone --depth 1 https://github.com/exa-labs/exa-cursor-plugin

Made for: Claude Code, Codex.

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 exa-best-practices

README.md
[![agentmods](https://agentmods.dev/badge/skills/exa-labs/exa-cursor-plugin/exa-best-practices.svg)](https://agentmods.dev/skills/exa-labs/exa-cursor-plugin/exa-best-practices)
Your own site
<a href="https://agentmods.dev/skills/exa-labs/exa-cursor-plugin/exa-best-practices"><img src="https://agentmods.dev/badge/skills/exa-labs/exa-cursor-plugin/exa-best-practices.svg" alt="Measured on agentmods" height="20"></a>
Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 421 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 $0.00037 $0.00421
Opus 5 $0.00018 $0.00211
Sonnet 5 $0.00007 $0.00084
Haiku 4.5 $0.00004 $0.00042

Measured 7d ago against content hash 44db9324dcb3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

exa-best-practices 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.

skills/exa-best-practices/SKILL.md · 41 lines

What it actually says

Exa Best Practices

Tool Selection

Need Tool When
Web search web_search_exa Current info, news, research, general questions, code examples
Read a URL web_fetch_exa Extract content from a known URL

Citation Standards

When using Exa search results, always cite sources:

  • Inline citations: Every fact or claim should reference its source
  • Source URLs: Include the actual URL, not just the title
  • Sources section: End responses with a list of all sources used
  • Never fabricate URLs: Only cite URLs that appear in search results

Search Quality Tips

  1. Natural language queries work better than keyword stuffing
  2. Be specific — include dates, names, versions when relevant
  3. Multiple queries with different phrasings improve coverage
  4. Adjust result count to match the depth needed (3-5 quick, 10-20 deep)

Getting Started

  1. Get your API key at https://dashboard.exa.ai/api-keys
  2. Add the MCP server in Cursor Settings → MCP
  3. Start searching with /exa-search or /exa-fetch

Troubleshooting

  • Tools not available: Check if the Exa MCP server is installed. If web_search_exa or web_fetch_exa are not in your tool list, stop and request the user to: (1) run /exa-setup in Cursor to add the MCP server, and (2) go to Cursor Settings → Tools & MCP and make sure Exa is toggled on (green).
  • No results: Try rephrasing the query or broadening search terms
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. 7d ago First seen · 41 lines · 37 tokens per session scan A 44db9324dcb3

Subscribe to this mod's changes

exa-best-practices is a skill published in the GitHub repository exa-labs/exa-cursor-plugin (6 stars, last pushed 5mo ago), licensed MIT. It adds 37 tokens to every session and 421 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens