image-search

image-search is a skill for Claude Code from twelvelabs-io/twelve-labs-claude-code-plugin. It costs 51 tokens per session (987 once invoked), scanned A, original, MIT.

A video-search method that uses a reference image together with optional words to find similar scenes or objects in indexed videos.

In plain words
What is it for?
It helps find videos matching a picture, locate similar visual content, or refine an image search with details such as an object's color.
Why use it?
Image and text together can narrow results more precisely than either an image or a broad text search alone. It requires videos indexed with Twelve Labs' Marengo 3.0 system.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

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

Good fit It helps find videos matching a picture, locate similar visual content, or refine an image search with details such as an object's color.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/twelvelabs-io/twelve-labs-claude-code-plugin/image-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 twelvelabs-io/twelve-labs-claude-code-plugin --skill image-search
Clone the repo
git clone --depth 1 https://github.com/twelvelabs-io/twelve-labs-claude-code-plugin

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 image-search

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/twelvelabs-io/twelve-labs-claude-code-plugin/image-search"><img src="https://agentmods.dev/badge/skills/twelvelabs-io/twelve-labs-claude-code-plugin/image-search.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 987 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 $0.00051 $0.00987
Opus 5 $0.00026 $0.00494
Sonnet 5 $0.00010 $0.00197
Haiku 4.5 $0.00005 $0.00099

Measured 10d ago against content hash e44941aeb026, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

image-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 10d 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.

skills/image-search/SKILL.md · 127 lines

How it starts

The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Search indexed videos using an image combined with optional text for more precise results. The text narrows image-based results — for example, an image of a car plus "red color" finds only red versions of that car model.

When to Use This Skill

Use this skill when the user:

  • Provides a reference image and wants to find similar content in videos
  • Wants to combine an image with text to refine results ("find this but in blue")
  • Asks to search with a picture or screenshot
  • Wants to locate specific objects/scenes matching a visual reference

Prerequisites

  • Videos must be indexed with Marengo 3.0 (composed search requires Marengo 3.0)
  • A reference image: either a publicly accessible URL or a local file path

Instructions

Step 1: Get the Image and Query

From the user's request, extract:

  • Image: A publicly accessible URL or an absolute path to a local image file
  • Text query (optional): Additional text to refine the image search

Step 2: Call the Search Tool

Image-only search (find content similar to the image):

With a URL:

Tool: mcp__twelvelabs-mcp__search
Parameters:
  queryMediaUrl: "<image URL>"
  queryMediaType: "image"

With a local file:

Tool: mcp__twelvelabs-mcp__search
Parameters:
  queryMediaFile: "<absolute path to image file>"
  queryMediaType: "image"

Composed search (image + text refinement):

With a URL:

Tool: mcp__twelvelabs-mcp__search
Parameters:
  query: "<text description>"
  queryMediaUrl: "<image URL>"
  queryMediaType: "image"

With a local file:

Tool: mcp__twelvelabs-mcp__search
Parameters:
  query: "<text description>"
  queryMediaFile: "<absolute path to image file>"
  queryMediaType: "image"

To search a specific index, add indexId.

Step 3: Display Results

Format results the same way as regular text search:

For each video with matching segments, display:

  • Filename of the video (if available)
  • URL of the video stream (if available)
  • Bulleted list of start and end times for matching segments

Read the full file on GitHub · 127 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. 10d ago First seen · 127 lines · 51 tokens per session scan A e44941aeb026

Subscribe to this mod's changes

image-search is a skill published in the GitHub repository twelvelabs-io/twelve-labs-claude-code-plugin (23 stars, last pushed 3mo ago), licensed MIT. It adds 51 tokens to every session and 987 once invoked, about $0.0003 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

webgl-holographic-foil

A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.

nexu-io/open-design · 41 tokens

general-video

Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…

heygen-com/hyperframes · 92 tokens

html-ppt-hermes-cyber-terminal

OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.

nexu-io/open-design · 53 tokens

html-ppt-taste-brutalist

16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).

nexu-io/open-design · 78 tokens

diagnostic-stem-delivery

Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.

HKUDS/OpenSpace · 23 tokens

chengfeng-check-updates

An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.

Agentchengfeng/chengfeng-videocut-skills · 120 tokens