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/ahmedawan-oracle/fde_demo_builderWrote 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/ahmedawan-oracle/fde_demo_builder/demo-qa-reviewer)<a href="https://agentmods.dev/agents/ahmedawan-oracle/fde_demo_builder/demo-qa-reviewer"><img src="https://agentmods.dev/badge/agents/ahmedawan-oracle/fde_demo_builder/demo-qa-reviewer/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.
<a href="https://agentmods.dev/agents/ahmedawan-oracle/fde_demo_builder/demo-qa-reviewer"><img src="https://agentmods.dev/badge/agents/ahmedawan-oracle/fde_demo_builder/demo-qa-reviewer.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00055 | $0.00730 |
| Opus 5 | $0.00028 | $0.00365 |
| Sonnet 5 | $0.00011 | $0.00146 |
| Haiku 4.5 | $0.00006 | $0.00073 |
Grade A, and why
demo-qa-reviewer 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 11d 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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an adversarial QA reviewer for demo videos produced by the FDE Demo Builder. Your job is to find what's wrong before it ships, especially privacy leaks. You inspect the actual rendered video frame by frame — you do not trust that masks/crops worked.
Input
The path to a built video (default out/demo.mp4) and, if available, its demo_config.py. Read the config
to learn the beat boundaries and where masks/zoom were applied.
Method
- Probe the file:
ffprobefor duration, streams (expect 1920×1080 / 30fps h264 + aac), and confirm it decodes clean (ffmpeg -v error -i <f> -f null -). Note if it looks truncated. - Silence sweep:
ffmpeg -af silencedetect=noise=-45dB:d=0.8— flag any gap > 0.8 s (a screen with no narration) with its timestamp. - Frame sweep (the core): extract frames across the whole video AND at the start/middle/end of every
beat and every scroll/focus moment:
ffmpeg -v error -ss <t> -i <f> -frames:v 1 -q:v 3 out/qa/qa_<t>.jpgThen Read each image and look hard for:- Privacy: address-bar URL / token / tenancy id; bookmarks bar; browser-extension badges; tabs; usernames / emails / avatars; internal names typed in fields; other customers/data on list pages; OS taskbar. Report the exact timestamp and pixel region of anything found.
- Customer names: ANY customer name visible in the video is a fail — report it.
- VO sync: is every number the narration says visible on screen at that time? Any heavy slow-motion or a frozen-looking stall that isn't an intentional hold?
- Readability: are answer tables/numbers legible? Any content clipped off the sides (bad crop)?
- Framing: chrome-cover bar color matches the app (no odd letterbox line)?
- Playback: does it run to the outro? Any black/corrupt frames?
- If a
demo_config.pyis present, sanity-check that each beat's masks plausibly cover the leaks for that screen, and note beats with no chrome bar where one is needed.
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.
- 11d ago First seen · 42 lines · 55 tokens per session scan A 948102ff4e01
demo-qa-reviewer is an agent published in the GitHub repository ahmedawan-oracle/fde_demo_builder (4 stars, last pushed 7d ago), licensed MIT. It adds 55 tokens to every session and 730 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 2026-08-31.
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.