tavily-search

tavily-search is a skill for Claude Code, Codex from xg-gh-25/SwarmAI. It costs 66 tokens per session (2,695 once invoked), scanned A, original, MIT.

An internet search and content-extraction tool powered by the Tavily API. It searches across the web, ranks results, extracts content from known URLs, and can produce AI-generated answers.

In plain words
What is it for?
Use it for web searches, current-information queries, extracting content from URLs, and research workflows that need ranked results.
Why use it?
It removes the need to find every relevant page manually when researching a topic. It can also collect content from several URLs in one workflow.

Skill for Claude CodeCodex

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

Good fit Use it for web searches, current-information queries, extracting content from URLs, and research workflows that need ranked results.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/xg-gh-25/swarmai/s_tavily-search
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 xg-gh-25/SwarmAI --skill s_tavily-search
Clone the repo
git clone --depth 1 https://github.com/xg-gh-25/SwarmAI

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 tavily-search

README.md
[![agentmods](https://agentmods.dev/badge/skills/xg-gh-25/swarmai/s_tavily-search/github.svg)](https://agentmods.dev/skills/xg-gh-25/swarmai/s_tavily-search)
Your own site
<a href="https://agentmods.dev/skills/xg-gh-25/swarmai/s_tavily-search"><img src="https://agentmods.dev/badge/skills/xg-gh-25/swarmai/s_tavily-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.

agentmods 80×15 button for tavily-search

Your own site · 80×15
<a href="https://agentmods.dev/skills/xg-gh-25/swarmai/s_tavily-search"><img src="https://agentmods.dev/badge/skills/xg-gh-25/swarmai/s_tavily-search.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,695 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 15 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Privilege Escalation · line 31
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
  • high Privilege Escalation · line 306
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
  • medium Data Exfiltration · line 43
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Data Exfiltration · line 46
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Data Exfiltration · line 94
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Data Exfiltration · line 97
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Data Exfiltration · line 153
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Data Exfiltration · line 199
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Data Exfiltration · line 214
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Data Exfiltration · line 231
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Data Exfiltration · line 255
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Data Exfiltration · line 261
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Data Exfiltration · line 46
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Data Exfiltration · line 97
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Data Exfiltration · line 153
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00066 $0.02695
Opus 5 $0.00033 $0.01347
Sonnet 5 $0.00013 $0.00539
Haiku 4.5 $0.00007 $0.00269

Measured 9d ago against content hash e231e833313f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

tavily-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 9d 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 -s -X POST https://api.tavily.com/search \
backend/skills/s_tavily-search/SKILL.md · 338 lines

How it starts

The opening of the file, as written. The whole thing — 338 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Why? WebFetch can only grab a single known URL. Tavily searches the entire web, returns ranked results with relevance scores, and can generate AI-powered answers -- all in one API call. Essential for answering "what's the latest on X?" or powering research workflows.


Quick Start

"Search the web for latest AI agent frameworks"
"What's the latest news about OpenAI?"
"Extract the main content from these 5 URLs"

Setup

Requires TAVILY_API_KEY environment variable.

# Check if set
echo $TAVILY_API_KEY

# If not, set it (get key from https://app.tavily.com)
export TAVILY_API_KEY=tvly-your-key-here

Free tier: 1,000 API credits/month. Basic search = 1 credit. Advanced search = 2 credits.


API Reference

Search

POST https://api.tavily.com/search

curl -s -X POST https://api.tavily.com/search \
  -H "Authorization: Bearer $TAVILY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "query": "latest AI agent frameworks 2026",
    "search_depth": "basic",
    "max_results": 5,
    "include_answer": "basic"
  }'

Parameters:

Parameter Type Default Description
query string (required) Search query
search_depth string basic basic (fast, 1 credit) or advanced (thorough, 2 credits)
max_results int 5 Number of results (0-20)
include_answer bool/string false true, "basic", or "advanced" -- returns AI-generated answer
include_raw_content bool/string false true, "markdown", or "text" -- returns full page content
topic string general "general" or "news"
time_range string none "day", "week", "month", "year"
country string none ISO country code to boost results (e.g., "us", "tw", "cn")
include_images bool false Return related images
exclude_domains array none Domains to exclude (e.g., ["pinterest.com"])
include_domains array none Limit search to specific domains

Read the full file on GitHub · 338 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. 9d ago First seen · 338 lines · 66 tokens per session scan A e231e833313f

Subscribe to this mod's changes

tavily-search is a skill published in the GitHub repository xg-gh-25/SwarmAI (44 stars, last pushed yesterday), licensed MIT. It adds 66 tokens to every session and 2,695 once invoked, about $0.0003 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 2026-09-03.