What is exa-deep-search?

A deep web-research workflow that searches for, extracts, and compares high-quality public sources through Exa. It produces focused findings suitable for checking and citing.

Use it for topic investigation, company research, source discovery, and research briefs. It can support answers that need current, comparable, citation-ready evidence.

It reduces the time spent finding relevant sources among broad search results. It helps keep current evidence, source quality, and publication dates visible during research.

exa-deep-search — Skill for Claude Code and Codex by sandbaseai

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 sandbaseai/sandbase-skills --skill exa-deep-search

Clone the repo

git clone --depth 1 https://github.com/sandbaseai/sandbase-skills

Made for: Claude Code, Codex.

Or install sandbase-skills, the plugin that ships this one along with the rest of its 97 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/sandbaseai/sandbase-skills/exa-deep-search/github.svg)](https://agentmods.dev/skills/sandbaseai/sandbase-skills/exa-deep-search)

Your own site

<a href="https://agentmods.dev/skills/sandbaseai/sandbase-skills/exa-deep-search"><img src="https://agentmods.dev/badge/skills/sandbaseai/sandbase-skills/exa-deep-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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/sandbaseai/sandbase-skills/exa-deep-search"><img src="https://agentmods.dev/badge/skills/sandbaseai/sandbase-skills/exa-deep-search.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,615 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. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00047	$0.01615
Opus 5	$0.00023	$0.00807
Sonnet 5	$0.00009	$0.00323
Haiku 4.5	$0.00005	$0.00161

Measured 11d ago against content hash 8ed3bc5a60a8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

exa-deep-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 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.

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.

marketing/exa-deep-search/SKILL.md · 143 lines

How it starts

The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Exa Deep Search

Turn Exa search into a focused, source-backed research brief. This Skill calls the named Exa capabilities in the SandBase API map through the SandBase MCP gateway. In a SandBase Agent, run the capabilities directly. In another compatible agent, require an authorized SandBase connection before starting; never request, print, or store an API key in the research output.

Read example workflows when the user needs a starting prompt or wants to understand the output.

Operating principles

Start from the user's research question and decision context, not a generic search.
Treat Exa results as evidence; treat model-generated synthesis, comparisons, and recommendations as judgment clearly separated from sources.
Select search depth, time window, domains, and geography deliberately. State any assumption rather than silently defaulting.
Optimize for source quality, recency, and relevance — not quantity.
Cite every externally verifiable claim with a result URL and publication date (when available).
Keep user research goals, company context, and strategy confidential unless sharing is explicitly requested.

Workflow

1. Frame the research question

Collect or infer: the topic or entity, time window, geography, trusted or excluded domains, audience for the deliverable, and how findings will be used. Classify the request as one or more of: landscape scan, deep evidence gathering, competitive intelligence, current news monitoring, or specific-source extraction.

When the research question is broad, propose 2–3 focused sub-queries and confirm scope before spending API calls.

2. Select and call SandBase capabilities

Read the SandBase API map before selecting tools. Use the listed tool_name through the SandBase gateway:

Call sandbase_describe_tool for the selected tool_name and read its current input schema.
Call sandbase_call_tool with that exact tool_name and only schema-defined arguments.
Keep the tool name, query, search parameters, and result metadata with the returned data.

Read the full file on GitHub · 143 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.

11d ago First seen · 143 lines · 47 tokens per session scan A 8ed3bc5a60a8

Subscribe to this mod's changes

exa-deep-search is a skill published in the GitHub repository sandbaseai/sandbase-skills (151 stars, last pushed 2d ago), licensed Apache-2.0. It adds 47 tokens to every session and 1,615 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 2026-08-30.

Research agent-skills ai-agents codex-skills deepseek deepseek-harness marketing-automation

skill

Ten native DSH tools give a text-only agent eyes. Use these structured tools directly; do not shell out to the bundled Python scripts or reproduce their implementation. Vision API credentials and model settings are managed by the plugin, so tool calls do not receive credentials.

Anionex/dsh-vision-toolkit · 0 tokens

modsearch

Plug-in web search, X (Twitter) search, and page fetch for models without native web access. Use whenever the task needs current information, external facts, source links, posts from X, or the content of a specific URL, and the active model/harness has no native search or fetch tool. Runs the modsearch CLI to return…

liustack/modsearch · 99 tokens

exa-deep-search