exa

exa is a skill for Claude Code, Codex from mnlt/teleport. It costs 54 tokens per session (1,405 once invoked), scanned B, original, MIT.

A web-search integration that finds recent information using meaning-based ranking, category filters, and selected websites. It can also produce answers with cited sources.

In plain words
What is it for?
Use it to research recent events, releases, papers, companies, or news. It can search within chosen domains or categories and retrieve supporting sources.
Why use it?
It helps when ordinary search results are poorly ranked or when an answer needs current, source-backed information. It avoids relying on memory for changing web content.

Skill for Claude CodeCodex

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

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/mnlt/teleport/exa.svg)](https://agentmods.dev/skills/mnlt/teleport/exa)
Your own site
<a href="https://agentmods.dev/skills/mnlt/teleport/exa"><img src="https://agentmods.dev/badge/skills/mnlt/teleport/exa.svg" alt="Measured on agentmods" height="20"></a>
Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,405 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 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 $0.00054 $0.01405
Opus 5 $0.00027 $0.00702
Sonnet 5 $0.00011 $0.00281
Haiku 4.5 $0.00005 $0.00140

Measured 4d ago against content hash d1b038dacf9e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

exa scanned grade B with 2 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 4d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

**Do NOT suggest editing `~/.claude/settings.local.json` manually.** The `teleport-setup add-key` command handles it with backup, validation, and masked input. Stop execution until the user has run the command and restar

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- **Skip for:** Language concepts from memory, debugging user's own code, known-URL fetches (just `curl`), library docs (use Context7).
skills/exa/SKILL.md · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Direct web search against Exa's REST API — no MCP required. Better than generic web search when you need recency, domain/category scoping, or synthesized answers with citations.

Usage

  • Use for: Recent events/releases, papers/companies/news by category, domain-filtered queries, answers with sources.
  • Skip for: Language concepts from memory, debugging user's own code, known-URL fetches (just curl), library docs (use Context7).

Credentials check

[ -n "$EXA_API_KEY" ] && echo "EXA_API_KEY: PRESENT" || echo "EXA_API_KEY: MISSING"

Never echo the variable directly — the value would appear in the conversation transcript. Use only the boolean pattern above.

If MISSING, respond to the user with EXACTLY this message (do NOT paraphrase, do NOT suggest manual JSON edits):

I need your exa credential. Run this in another terminal — it'll open the signup page, validate format, and save it safely with masked input:

teleport-setup add-key exa

Then restart Claude Code (/exit, then claude) and ask me again.

Do NOT suggest editing ~/.claude/settings.local.json manually. The teleport-setup add-key command handles it with backup, validation, and masked input. Stop execution until the user has run the command and restarted.

API

  • Base URL: https://api.exa.ai
  • Auth: x-api-key: $EXA_API_KEY — custom header, NOT Authorization. (Bearer works as fallback; x-api-key is canonical.)
  • Content-Type: application/json. All endpoints are POST with JSON body.
  • Every response includes requestId and costDollars — monitor per response.

Endpoints

Endpoint Purpose
/search Find URLs matching a query (neural/fast/deep/auto variants)
/contents Fetch cleaned text / highlights / summaries for URLs
/findSimilar Given a URL, find semantically similar pages
/answer One-shot Q&A — returns answer + citations in one call
/research Long-running structured research; async, returns JSON schema

Read the full file on GitHub · 108 lines

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. 4d ago First seen · 108 lines · 54 tokens per session scan B d1b038dacf9e

Subscribe to this mod's changes

exa is a skill published in the GitHub repository mnlt/teleport (8 stars, last pushed 4mo ago), licensed MIT. It adds 54 tokens to every session and 1,405 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). 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

opik-diagnose

Surface the Opik traces worth a developer's attention, ranked by signal — errors, failed tool calls, latency, regressions, and low online-eval scores — plus Diagnostics issues. Reads live/production traces via the SDK (searchtraces and agentinsights) and works with no MCP; uses the MCP issue entity when connected.…

comet-ml/opik-mcp · 147 tokens

client-scripts

Write ServiceNow client scripts (onLoad/onChange/onSubmit/onCellEdit) using gform, guser, GlideAjax, field visibility/mandatory toggles, and validation with debounced server calls.

serac-labs/serac · 45 tokens

agoragentic-transaction-assurance

Prepare, evaluate, and reconcile autonomous agent transactions without self-granting payment or owner authority. Use when an agent must bind principal authority, seller terms, payment evidence, execution, delivered outcome, and reconciliation; handle paid retries safely; or prepare an authority request for owner…

rhein1/agoragentic-integrations · 65 tokens

maya-shot-export

Pipeline stage — shot-level export: frame ranges, cameras, FBX / Alembic packaging for editorial. Use when packaging shot data for downstream departments. Not for full pipeline publish (maya-pipeline) or scene assembly (maya-scene-assembly).

dcc-mcp/dcc-mcp-maya · 60 tokens

bdd-container-update

Update the BDD test container image when its dependencies or runtime change. Determines version bump (major vs minor vs patch), rebuilds the Docker image, pushes to GitLab registry, and updates the image tag in starttest.sh. Test source (tests/, features/, scripts/, data/, conftest.py) is bind-mounted from the host…

NVIDIA-AI-Blueprints/video-search-and-summarization · 117 tokens

knowledge

Unified cross-store knowledge query. Searches MEMORY.md, Thoughtbox knowledge graph, git history, and assumption registry in parallel, returning results with provenance.

Kastalien-Research/thoughtbox · 31 tokens