frame-describer

frame-describer is an agent for Claude Code from jordanrendric/claude-video-vision. It costs 36 tokens per session (184 once invoked), scanned A, original, MIT.

An agent that turns video frames into factual text descriptions, including people, visible text, objects, surroundings, and changes between frames.

In plain words
What is it for?
Summarising what appears in extracted frames, recording timestamps, describing interfaces or captions, and tracking visual changes.
Why use it?
Text descriptions preserve the important visual information when sending or processing every image would use too many tokens.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the claude-video-vision plugin — 1 skill, 2 commands, 1 agent shipped together

Good fit Summarising what appears in extracted frames, recording timestamps, describing interfaces or captions, and tracking visual changes.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/jordanrendric/claude-video-vision/frame-describer
About the project

Claude Code Video Vision is a plugin that lets Claude Code inspect videos by extracting image frames and producing timestamped audio transcriptions. It supports YouTube URLs and uses Gemini, local Whisper, or OpenAI processing backends, while the catalogue entries provide its commands, agent, and skill.

jordanrendric/claude-video-vision · 1,296 stars · on GitHub

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.

Clone the repo
git clone --depth 1 https://github.com/jordanrendric/claude-video-vision

Made for: Claude Code.

Or install claude-video-vision, the plugin that ships this one along with the rest of its 1 skill, 2 commands, 1 agent.

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 frame-describer

README.md
[![agentmods](https://agentmods.dev/badge/agents/jordanrendric/claude-video-vision/frame-describer/github.svg)](https://agentmods.dev/agents/jordanrendric/claude-video-vision/frame-describer)
Your own site
<a href="https://agentmods.dev/agents/jordanrendric/claude-video-vision/frame-describer"><img src="https://agentmods.dev/badge/agents/jordanrendric/claude-video-vision/frame-describer/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 frame-describer

Your own site · 80×15
<a href="https://agentmods.dev/agents/jordanrendric/claude-video-vision/frame-describer"><img src="https://agentmods.dev/badge/agents/jordanrendric/claude-video-vision/frame-describer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 184 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 $0.00036 $0.00184
Opus 5 $0.00018 $0.00092
Sonnet 5 $0.00007 $0.00037
Haiku 4.5 $0.00004 $0.00018

Measured 13d ago against content hash f2d510489248, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

frame-describer 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 13d 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/frame-describer.md · 24 lines

What it actually says

Frame Describer

You receive video frames as images. For each frame, write a concise but detailed description covering:

  • People: appearance, actions, expressions, gestures
  • Text on screen: any visible text, code, UI elements, captions
  • Objects: key objects, their state, spatial relationships
  • Setting: environment, lighting, location
  • Changes: if you can see what changed from the previous frame, note it

Format each description as:

Frame at [timestamp] — [1-3 sentence description covering the above]

Be factual and specific. Don't interpret intent — describe what you see.

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. 13d ago First seen · 24 lines · 36 tokens per session scan A f2d510489248

Subscribe to this mod's changes

frame-describer is an agent published in the GitHub repository jordanrendric/claude-video-vision (1,296 stars, last pushed 1mo ago), licensed MIT. It adds 36 tokens to every session and 184 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.