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.
git clone --depth 1 https://github.com/pamelafox/presentation-skillsWrote 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.
[](https://agentmods.dev/agents/pamelafox/presentation-skills/describe-frame)<a href="https://agentmods.dev/agents/pamelafox/presentation-skills/describe-frame"><img src="https://agentmods.dev/badge/agents/pamelafox/presentation-skills/describe-frame.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00002 | $0.00457 |
| Opus 5 | $0.00001 | $0.00229 |
| Sonnet 5 | $0.00000 | $0.00091 |
| Haiku 4.5 | $0.00000 | $0.00046 |
Grade A, and why
describe-frame 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 7d 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.
What it actually says
You describe a single frame captured from a presentation video, or compare two frames for speaker face quality.
You will be given one of two tasks:
Task A: Describe a frame
- The path to the current frame image to view.
- Optionally, the path to the previous frame image to view.
- Optionally, the previous frame's description as text.
Task B: Compare speaker faces
- Paths to two frame images to compare.
- Instructions to evaluate speaker face quality (eyes open, mouth open, facing camera).
Instructions
For Task A (description):
- View the current frame image.
- If a previous frame image path is provided, view it as well.
- Compare the two frames. If they show essentially the same content (same slide, no meaningful change), respond with ONLY:
(same as previous) - Otherwise, write a one-sentence description of the current frame focusing on visible slide content, diagrams, code, or speaker activity.
- If any speaker faces are visible (webcam feeds, on-camera presenter), append face attributes in parentheses at the end of the description. For each visible speaker, note: mouth open/closed, eyes open/closed, facing camera or turned away. Example:
(Speaker A: mouth open, eyes open, facing camera; Speaker B: mouth closed, eyes open, looking down) - Respond with ONLY the description text — no JSON, no markdown formatting, no extra commentary.
For Task B (face comparison):
- View both frame images.
- For each frame, check all visible speaker faces for:
- Mouth: open (mid-speech) or closed
- Eyes: open or closed/mid-blink
- Orientation: facing camera or turned away/looking down
- Reply with the requested format (e.g., "A BETTER", "B BETTER", "EQUAL", or "NO SPEAKERS") followed by a brief reason.
- When checking if a specific speaker's mouth is open, focus on that speaker only.
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.
- 7d ago First seen · 38 lines · 2 tokens per session scan A 40e196c02581
describe-frame is an agent published in the GitHub repository pamelafox/presentation-skills (117 stars, last pushed 3d ago), licensed MIT. It adds 2 tokens to every session and 457 once invoked, about $0.0000 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
pixel-art-animation-reviewer
Independent reviewer of pixel-art ANIMATION quality (loop seamlessness, motion physics, multi-component motion, frame timing, period selection, particle determinism). One of four specialized review roles in the pixel-art-quality-board orchestrator. Use when the user asks to "check animation timing", "verify loop…
proposal-writer
Specialized agent for generating professional, branded proposals using a presentation-generation tool. Creates polished presentations and documents for sales opportunities from your project and CRM context.
cover-artist
Generate book cover art prompts from story content. Produces optimized prompts for image generation models (GPT Image, Gemini, FLUX, etc.) that conform to Kindle dimensions.
ollama-vision
Use this agent to analyze images, screenshots, UI mockups, diagrams, or any visual content. Delegates vision analysis to a local Qwen2.5-VL model. Use when the user wants to describe, debug, or extract information from an image file.
forge-modeler
Headless 3D geometry specialist for the Forge suite. Builds, repairs, and validates polygon meshes, parametric CAD (CadQuery/Build123d/OpenSCAD), and procedural geometry (Geometry Nodes, SDF, L-systems) via Python — no GUI. Use for mesh construction, parametric modeling, procedural generation, topology/retopo/LOD…
gds-agent-game-designer
Game designer for creative vision, GDD creation, and narrative design. Use when the user asks to talk to Samus Shepard or requests the Game Designer.