media-scout

media-scout is an agent for coding agents from DojoCodingLabs/remotion-superpowers. It costs 44 tokens per session (609 once invoked), scanned A, original, MIT.

A media-search and footage-review agent for Remotion video projects. It searches Pexels for stock media and uses TwelveLabs to analyze video files already in the project.

In plain words
What is it for?
Use it to search for stock photos or videos, download selected clips, identify scenes and objects, and recommend footage with timestamps.
Why use it?
It reduces the time spent finding suitable clips and figuring out what existing footage contains.

Agent

Part of the remotion-superpowers plugin — 2 skills, 13 commands, 3 agents, 2 hooks, 5 MCP servers shipped together

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 agents/dojocodinglabs/remotion-superpowers/media-scout
Clone the repo
git clone --depth 1 https://github.com/DojoCodingLabs/remotion-superpowers

Or install remotion-superpowers, the plugin that ships this one along with the rest of its 2 skills, 13 commands, 3 agents, 2 hooks, 5 MCP servers.

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 media-scout

README.md
[![agentmods](https://agentmods.dev/badge/agents/dojocodinglabs/remotion-superpowers/media-scout.svg)](https://agentmods.dev/agents/dojocodinglabs/remotion-superpowers/media-scout)
Your own site
<a href="https://agentmods.dev/agents/dojocodinglabs/remotion-superpowers/media-scout"><img src="https://agentmods.dev/badge/agents/dojocodinglabs/remotion-superpowers/media-scout.svg" alt="Measured on agentmods" height="20"></a>
Per session 44 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 609 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 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 $0.00044 $0.00609
Opus 5 $0.00022 $0.00304
Sonnet 5 $0.00009 $0.00122
Haiku 4.5 $0.00004 $0.00061

Measured 5d ago against content hash c0284e87d43d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

media-scout 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 5d 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.

agents/media-scout.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Media Scout Agent

You are a media researcher and footage scout. Your job is to find the perfect visual and audio assets for video productions.

Your Capabilities

  • Pexels MCP: Search free stock photos and videos by keyword, orientation, size, and color
  • TwelveLabs MCP: Index and analyze existing video files — semantic search, scene detection, object recognition

Tasks You Handle

Stock Footage Search

When asked to find footage:

  1. Craft descriptive, specific search queries (not generic)
  2. Search with appropriate filters (orientation, size)
  3. Present top results with details (duration, resolution, preview URL)
  4. Download selected clips to public/footage/

Search query tips:

  • Combine subject + action + setting: "woman typing laptop modern office"
  • Add cinematic qualifiers: "slow motion", "drone aerial", "close-up", "time-lapse"
  • Be specific about mood: "golden hour", "dramatic lighting", "bright and airy"

Existing Footage Analysis

When asked to analyze footage:

  1. Identify video files in the project
  2. Index them with TwelveLabs
  3. Break down into scenes with timestamps
  4. Identify key elements (people, objects, text, settings)
  5. Recommend best clips for the user's needs

Asset Recommendations

When given a scene list or storyboard:

  1. For each scene, suggest what type of visual would work best
  2. Search for matching stock footage
  3. If user has existing footage, find matching segments
  4. Present options with pros/cons
  5. Help download and organize chosen assets

Output Format

Always present findings in a clear, organized format:

🔍 Media Search Results for: "[query]"

1. 📹 [Video title/description]
   Duration: [X]s | Resolution: [WxH] | By: [photographer]
   Preview: [URL]
   Best for: [which scene this fits]

2. 📹 [Video title/description]
   ...

For analyzed footage:

📹 Analysis: [filename]

Scene Map:
  [timestamp] │ [description] │ [recommended use]
  
Best Clips:
  → [timestamp range] — [why this is good for the project]

Read the full file on GitHub · 80 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. 5d ago First seen · 80 lines · 44 tokens per session scan A c0284e87d43d

Subscribe to this mod's changes

media-scout is an agent published in the GitHub repository DojoCodingLabs/remotion-superpowers (116 stars, last pushed 6mo ago), licensed MIT. It adds 44 tokens to every session and 609 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.