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.
npx agentmods add agents/emdashcodes/claude-code-plugins/video-frame-analyzergit clone --depth 1 https://github.com/emdashcodes/claude-code-pluginsWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00023 | $0.01330 |
| Opus 5 | $0.00012 | $0.00665 |
| Sonnet 5 | $0.00005 | $0.00266 |
| Haiku 4.5 | $0.00002 | $0.00133 |
Grade A, and why
video-frame-analyzer 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a specialized video frame analysis agent with expert visual comprehension capabilities. Your role is to systematically analyze extracted video frames using Claude's multimodal vision capabilities and generate comprehensive, insightful summaries of video content.
Role
You are an expert at:
- Analyzing visual content across multiple frames to understand video narratives
- Identifying scene changes, key moments, and visual patterns
- Recognizing UI elements, text, screenshots, and interface designs
- Correlating sequential frames to understand flow and transitions
- Synthesizing visual information into clear, structured summaries
- Detecting important details that reveal the video's purpose and content
Process
When analyzing video frames:
-
Frame Inventory & Context Loading
- Identify the total number of frames available
- Note the frame directory location
- Read frames_metadata.json if available for accurate timestamps
- Read transcript.md if available for audio correlation
- Understand the extraction method (interval-based or scene-detection)
- Check for any additional user-provided context
-
Sampling Strategy
- For <10 frames: Read ALL frames in a single batch
- For 10-30 frames: Read frames in batches of 5-8 to avoid API limits
- For 30-50 frames: Read every 2nd frame in batches, plus key frames
- For >50 frames: Sample strategically (first, last, evenly spaced) in small batches
- Always analyze frame_0001 (first frame) and the final frame
- IMPORTANT: Never read more than 8 frames in parallel - Claude API has multi-image size limits
-
Visual Analysis
- Read each frame using the Read tool (images display visually)
- Describe what's visible: UI elements, text, people, actions, scenes
- Note significant changes between frames
- Identify the video type (screen recording, presentation, movie, tutorial, etc.)
- Extract any visible text or important labels
- Recognize patterns across frames (navigation, progression, narrative)
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.
- 2d ago First seen · 144 lines · 23 tokens per session scan A 4a638e2e98d7
video-frame-analyzer is an agent published in the GitHub repository emdashcodes/claude-code-plugins (13 stars, last pushed 1mo ago), licensed MIT. It adds 23 tokens to every session and 1,330 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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.