search

search is a command for Claude Code from twelvelabs-io/twelve-labs-claude-code-plugin. It costs 14 tokens per session (2,087 once invoked), scanned A, original, MIT.

A command for searching indexed videos with text, an image, a registered entity, or combinations of these inputs.

In plain words
What is it for?
Use it to search for scenes, actions, on-screen text, image matches, or appearances of a registered person or object.
Why use it?
It lets you locate matching video content without knowing the exact wording or timestamp in advance.

Command for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/me/photos/building.jpg.

Part of the twelvelabs plugin — 10 skills, 11 commands, 2 hooks, 1 MCP server shipped together

Good fit Use it to search for scenes, actions, on-screen text, image matches, or appearances of a registered person or object.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add twelvelabs-io/twelve-labs-claude-code-plugin
Claude Code
/plugin install twelvelabs

Made for: Claude Code.

Or install twelvelabs, the plugin that ships this one along with the rest of its 10 skills, 11 commands, 2 hooks, 1 MCP server.

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 search

README.md
[![agentmods](https://agentmods.dev/badge/commands/twelvelabs-io/twelve-labs-claude-code-plugin/search/github.svg)](https://agentmods.dev/commands/twelvelabs-io/twelve-labs-claude-code-plugin/search)
Your own site
<a href="https://agentmods.dev/commands/twelvelabs-io/twelve-labs-claude-code-plugin/search"><img src="https://agentmods.dev/badge/commands/twelvelabs-io/twelve-labs-claude-code-plugin/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 search

Your own site · 80×15
<a href="https://agentmods.dev/commands/twelvelabs-io/twelve-labs-claude-code-plugin/search"><img src="https://agentmods.dev/badge/commands/twelvelabs-io/twelve-labs-claude-code-plugin/search.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,087 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.
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 $0.00014 $0.02087
Opus 5 $0.00007 $0.01043
Sonnet 5 $0.00003 $0.00417
Haiku 4.5 $0.00001 $0.00209

Measured 8d ago against content hash 39e7c46faa4a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

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 8d 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.

commands/search.md · 246 lines

How it starts

The opening of the file, as written. The whole thing — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/twelvelabs:search - Search Videos

Search your indexed videos using text, images, entities, or combinations. TwelveLabs interprets your query to find matching content based on visual elements, actions, sounds, and on-screen text.

Usage

/twelvelabs:search <text query> [index-id]
/twelvelabs:search <image-url-or-path> [index-id]
/twelvelabs:search <image-url-or-path> <text query> [index-id]
/twelvelabs:search <@entity_id> [action description] [index-id]

User provided: $ARGUMENTS

Arguments

  • text query - Natural language description of what you're looking for
  • image-url-or-path - A publicly accessible image URL or absolute local file path
  • <@entity_id> - Entity ID wrapped in <@ and > for entity recognition search
  • action description - Optional text to combine with entity or image search
  • index-id - Optional. ID of a specific index to search. If not provided, searches the default index.

Examples

Text Search

/twelvelabs:search a person walking through a forest
/twelvelabs:search red car driving fast
/twelvelabs:search someone giving a presentation
/twelvelabs:search text showing "hello world"

Image Search (requires Marengo 3.0)

/twelvelabs:search https://example.com/car.jpg
/twelvelabs:search /Users/me/photos/building.jpg

Composed Search (image + text, requires Marengo 3.0)

/twelvelabs:search https://example.com/car.jpg red color
/twelvelabs:search /Users/me/photos/building.jpg at night

Entity Search (requires Marengo 3.0)

/twelvelabs:search <@abc123>
/twelvelabs:search <@abc123> is giving a presentation

Instructions for Claude

When the user invokes /twelvelabs:search, the query is provided in $ARGUMENTS. Follow these steps:

Step 1: Validate Input

Check that $ARGUMENTS is not empty. If empty:

Please provide a search query, image, or entity ID.

Usage:
  /twelvelabs:search <text query>
  /twelvelabs:search <image-url-or-path>
  /twelvelabs:search <image-url-or-path> <text query>
  /twelvelabs:search <@entity_id> [action]

Read the full file on GitHub · 246 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. 8d ago First seen · 246 lines · 14 tokens per session scan A 39e7c46faa4a

Subscribe to this mod's changes

search is a command published in the GitHub repository twelvelabs-io/twelve-labs-claude-code-plugin (23 stars, last pushed 3mo ago), licensed MIT. It adds 14 tokens to every session and 2,087 once invoked, about $0.0001 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.