exa-search

exa-search is a skill for Claude Code, Codex from mrobinson2/AzureAgentForge. It costs 123 tokens per session (648 once invoked), scanned A, original, MIT.

A semantic web-search skill that uses the Exa service to find conceptually related pages, even when they do not use the exact search words.

In plain words
What is it for?
Use it to find papers, companies, articles, and other pages related to a broad idea, then read the returned titles, links, and excerpts.
Why use it?
It helps with exploratory research where ordinary keyword matching may miss relevant results.

Skill for Claude CodeCodex

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

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/mrobinson2/azureagentforge/exa-search
Any agent
npx skills add mrobinson2/AzureAgentForge --skill exa-search
Clone the repo
git clone --depth 1 https://github.com/mrobinson2/AzureAgentForge

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-search

README.md
[![agentmods](https://agentmods.dev/badge/skills/mrobinson2/azureagentforge/exa-search.svg)](https://agentmods.dev/skills/mrobinson2/azureagentforge/exa-search)
Your own site
<a href="https://agentmods.dev/skills/mrobinson2/azureagentforge/exa-search"><img src="https://agentmods.dev/badge/skills/mrobinson2/azureagentforge/exa-search.svg" alt="Measured on agentmods" height="20"></a>
Per session 123 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 648 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 $0.00123 $0.00648
Opus 5 $0.00062 $0.00324
Sonnet 5 $0.00025 $0.00130
Haiku 4.5 $0.00012 $0.00065

Measured 6d ago against content hash db43482cf49c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

exa-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 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.

apps/hermes/overrides/skills/playbooks/exa-search/SKILL.md · 60 lines

What it actually says

exa-search is a CLI on $PATH that queries the Exa neural search API and returns results in the same ddgs-compatible JSON shape as brave-search — an array of {title, href, body} — so it's a drop-in alongside the other search tools.

When to use which search backend

Backend Best for
exa-search Conceptual / semantic / exploratory queries: "frameworks like LangGraph", "research on agent memory", "find articles arguing X". Neural search finds relevant pages even when they don't contain your exact words.
brave-search Fresh / breaking / exact-term queries: news, a specific product page, a known title, anything time-sensitive.

When a question has both an exploratory and a freshness angle, run both and merge — they surface different pages.

Usage

# Naive form:
exa-search "open-source agent frameworks with durable execution"

# ddgs-compatible form (same flags as brave-search), e.g. 8 results:
exa-search text -k "open-source agent frameworks" -m 8 -o json

Output is a JSON array; each element has title, href, and body (a short text excerpt from the page). Parse it the same way you parse brave-search output.

Behavior and exit codes

Exit Meaning
0 Success — JSON array on stdout (may be [] if Exa found nothing).
1 EXA_API_KEY is not set. The wrapper can't run without it.
2 Empty query.
3 / 4 Exa API error (non-2xx) or a transport failure — a clear message is printed to stderr.

Environment

Variable Purpose
EXA_API_KEY Required. Exa API key (free tier ~1,000 searches/month). In Azure deploys it is mounted from the exa-api-key Key Vault secret when exa_search_enabled = true.

If exa-search exits 1, Exa isn't configured in this environment — fall back to brave-search.

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 · 60 lines · 123 tokens per session scan A db43482cf49c

Subscribe to this mod's changes

exa-search is a skill published in the GitHub repository mrobinson2/AzureAgentForge (21 stars, last pushed yesterday), licensed MIT. It adds 123 tokens to every session and 648 once invoked, about $0.0006 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 2026-08-30.

Related

Other skills, from other repositories

tomllm-format

.tomllm / .tomllmd = valid TOML + enriched # comment conventions for LLM context.

elasticdotventures/_b00t_ · 27 tokens

release

Cut a versioned release and publish everos to PyPI via the tag-triggered workflow.

EverMind-AI/EverOS · 20 tokens

agentfield-use

Whenever you have a discrete task to perform — one the user delegated, or one that arose inside your own work — check FIRST whether an installed AgentField agent covers it, and offload to it by default when one does. Coverage, not task size, is the test: even a small job goes to a covering agent. The check is cheap …

Agent-Field/agentfield · 259 tokens

datadesigner-docs

Maintain the NeMo Data Designer Fern docs site under fern/. Use for any documentation change. Triggered by: "edit docs", "add doc page", "update docs", "rename page", "fix broken link", "add redirect", "preview docs", "publish docs", "regenerate notebooks", "update dev note", any request that touches fern/.

NVIDIA-NeMo/DataDesigner · 80 tokens

neuron-evaluation-engineer

Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…

neuron-core/neuron-ai · 77 tokens

neuron-structured-output

Design and implement structured output classes for Neuron AI agents using SchemaProperty attributes and validation rules. Use this skill when the user mentions structured output, JSON schema extraction, data validation, output classes, DTOs for AI responses, extracting structured data from LLM, or configuring property…

neuron-core/neuron-ai · 104 tokens