exa-research

exa-research is a skill for Claude Code from ejirocodes/agent-skills. It costs 89 tokens per session (611 once invoked), scanned A, original, MIT.

A research and answer toolkit for Exa.ai, a web-search service. It can generate answers with citations and perform deeper searches that return summaries.

In plain words
What is it for?
It supports question answering with source links, deep research, citation handling, streaming answers, and automated research reports.
Why use it?
It helps connect answers to their web sources and reduces the work of expanding searches and summarizing results by hand.

Skill for Claude Code

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

Part of the exa plugin — 4 skills shipped together

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.

agentmods
npx agentmods add skills/ejirocodes/agent-skills/exa-research
Any agent
npx skills add ejirocodes/agent-skills --skill exa-research
Clone the repo
git clone --depth 1 https://github.com/ejirocodes/agent-skills

Made for: Claude Code.

Or install exa, the plugin that ships this one along with the rest of its 4 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 exa-research

README.md
[![agentmods](https://agentmods.dev/badge/skills/ejirocodes/agent-skills/exa-research.svg)](https://agentmods.dev/skills/ejirocodes/agent-skills/exa-research)
Your own site
<a href="https://agentmods.dev/skills/ejirocodes/agent-skills/exa-research"><img src="https://agentmods.dev/badge/skills/ejirocodes/agent-skills/exa-research.svg" alt="Measured on agentmods" height="20"></a>
Per session 89 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 611 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00089 $0.00611
Opus 5 $0.00044 $0.00305
Sonnet 5 $0.00018 $0.00122
Haiku 4.5 $0.00009 $0.00061

Measured 6d ago against content hash 211dffd86338, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

exa-research 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 6d 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.

exa/skills/exa-research/SKILL.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Exa Research & Answer API

Quick Reference

Topic When to Use Reference
Answer API Q&A with citations, grounded responses answer-api.md
Deep Search Smart query expansion, high-quality summaries deep-search.md
Citations Source attribution, verification citations.md

Essential Patterns

Answer API (Python)

from exa_py import Exa

exa = Exa()

response = exa.answer(
    "What are the key features of Python 3.12?",
    text=True
)

print(response.answer)
for citation in response.citations:
    print(f"Source: {citation.url}")

Streaming Answers

stream = exa.answer(
    "Explain the benefits of microservices architecture",
    stream=True
)

for chunk in stream:
    print(chunk.text, end="", flush=True)

# Access citations after streaming
print("\nSources:", stream.citations)

Deep Search with Summaries

results = exa.search_and_contents(
    "latest developments in quantum computing",
    type="neural",
    num_results=10,
    summary=True,
    use_autoprompt=True  # Smart query expansion
)

for result in results.results:
    print(f"{result.title}")
    print(f"Summary: {result.summary}")

When to Use

Feature Use Case Output
Answer API Direct Q&A needing citations Answer + source URLs
Deep Search Query expansion + summaries Enhanced search results
Exa Research Long-form async reports Structured JSON/Markdown

Common Mistakes

  1. Not using streaming for long answers - Use stream=True for better UX on complex questions
  2. Ignoring citations - Always include response.citations for verifiable responses
  3. Missing text=True - Answer API needs content access; include text=True
  4. Over-complex queries - Answer API works best with clear, focused questions
  5. Not validating citations - Check citation.url exists before displaying to users

Read the full file on GitHub · 85 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 6d ago First seen · 85 lines · 89 tokens per session scan A 211dffd86338

Subscribe to this mod's changes

exa-research is a skill published in the GitHub repository ejirocodes/agent-skills (6 stars, last pushed 2mo ago), licensed MIT. It adds 89 tokens to every session and 611 once invoked, about $0.0004 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

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens