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 NicolaiSchmid/agent-skills --skill exa-searchgit clone --depth 1 https://github.com/NicolaiSchmid/agent-skillsWrote 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/nicolaischmid/agent-skills/exa-search)<a href="https://agentmods.dev/skills/nicolaischmid/agent-skills/exa-search"><img src="https://agentmods.dev/badge/skills/nicolaischmid/agent-skills/exa-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.
<a href="https://agentmods.dev/skills/nicolaischmid/agent-skills/exa-search"><img src="https://agentmods.dev/badge/skills/nicolaischmid/agent-skills/exa-search.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00032 | $0.02829 |
| Opus 5 | $0.00016 | $0.01414 |
| Sonnet 5 | $0.00006 | $0.00566 |
| Haiku 4.5 | $0.00003 | $0.00283 |
Grade A, and why
exa-search scanned grade A with 1 finding 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 11d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- curl How it starts
The opening of the file, as written. The whole thing — 339 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Exa Web Search
Search the web using Exa's AI-powered search API. Exa provides semantic search capabilities optimized for AI applications.
Configuration
Config file: ~/.config/exa-search/config.json
{
"api_key": "your-exa-api-key-here"
}
Getting an API key
- Go to https://dashboard.exa.ai/api-keys
- Sign up or log in to your Exa account
- Create a new API key
Troubleshooting config
If requests fail, verify the config:
# Check config exists and is valid JSON
cat ~/.config/exa-search/config.json | jq .
# Test connection
curl -s -X POST "https://api.exa.ai/search" \
-H "x-api-key: $(jq -r .api_key ~/.config/exa-search/config.json)" \
-H "Content-Type: application/json" \
-d '{"query": "test", "numResults": 1}' | jq '.results | length'
Common issues:
401 Unauthorized: API key is invalid → get a new key from dashboardConnection refused: Network issue or API is downnullor parse error: Config file is missing or malformed
If config is broken, guide the user to provide their Exa API key, then create/update the config:
mkdir -p ~/.config/exa-search
cat > ~/.config/exa-search/config.json << 'EOF'
{
"api_key": "USER_PROVIDED_API_KEY"
}
EOF
Endpoint Selection Guide
Choose the appropriate endpoint based on user intent:
| Endpoint | Use When |
|---|---|
/search |
Need to find web pages, research topics, or get content from multiple sources |
/contents |
Have specific URLs and need to extract their full content |
/answer |
Need a direct, concise answer to a factual question |
/research/v1 |
Need in-depth research with structured output, multi-step analysis, or comprehensive reports |
API Examples
Load API key
EXA_API_KEY=$(jq -r .api_key ~/.config/exa-search/config.json)
1. Search (/search)
Semantic search with optional content extraction. Returns results with their contents.
# Basic search
curl -s -X POST "https://api.exa.ai/search" \
-H "x-api-key: $EXA_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"query": "latest developments in AI agents",
"numResults": 10
}' | jq '.results[] | {title, url, publishedDate}'
# Search with content extraction
curl -s -X POST "https://api.exa.ai/search" \
-H "x-api-key: $EXA_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"query": "best practices for RAG systems",
"numResults": 5,
"contents": {
"text": true,
"highlights": {
"numSentences": 3,
"highlightsPerUrl": 2
},
"summary": {}
}
}' | jq '.results[] | {title, url, summary, highlights}'
# Search with date filters and domain restrictions
curl -s -X POST "https://api.exa.ai/search" \
-H "x-api-key: $EXA_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"query": "OpenAI announcements",
"numResults": 10,
"startPublishedDate": "2024-01-01T00:00:00.000Z",
"includeDomains": ["openai.com", "techcrunch.com", "theverge.com"],
"contents": {
"text": {"maxCharacters": 1000},
"summary": {}
}
}' | jq
# Search with category filter
curl -s -X POST "https://api.exa.ai/search" \
-H "x-api-key: $EXA_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"query": "transformer architecture papers",
"numResults": 10,
"category": "research paper",
"contents": {
"text": true,
"summary": {}
}
}' | jq
# Deep search for comprehensive results
curl -s -X POST "https://api.exa.ai/search" \
-H "x-api-key: $EXA_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"query": "climate change mitigation strategies",
"type": "deep",
"numResults": 20,
"contents": {
"text": true,
"summary": {}
}
}' | jq
What ships with it
1 file 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.
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.
- 11d ago First seen · 339 lines · 32 tokens per session scan A d04c6357a7cf
exa-search is a skill published in the GitHub repository NicolaiSchmid/agent-skills (2 stars, last pushed 7mo ago), licensed MIT. It adds 32 tokens to every session and 2,829 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
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…