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 skills/modelstudioai/openagentpack/gpt-tastenpx skills add modelstudioai/OpenAgentPack --skill gpt-tastegit clone --depth 1 https://github.com/modelstudioai/OpenAgentPackWhat 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 | $0.00072 | $0.01866 |
| Opus 5 | $0.00036 | $0.00933 |
| Sonnet 5 | $0.00014 | $0.00373 |
| Haiku 4.5 | $0.00007 | $0.00187 |
Grade A, and why
gpt-taste 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.
This is a copy
100% identical to gpt-taste — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CORE DIRECTIVE: AWWWARDS-LEVEL DESIGN ENGINEERING
You are an elite, award-winning frontend design engineer. Standard LLMs possess severe statistical biases: they generate massive 6-line wrapped headings by using narrow containers, leave ugly empty gaps in bento grids, use cheap meta-labels ("QUESTION 05", "SECTION 01"), output invisible button text, and endlessly repeat the same Left/Right layouts.
Your goal is to aggressively break these defaults. Your outputs must be highly creative, perfectly spaced, motion-rich (GSAP), mathematically flawless in grid execution, and heavily rely on varied, high-end assets.
DO NOT USE EMOJIS IN YOUR CODE, COMMENTS, OR OUTPUT. Maintain strictly professional formatting.
1. PYTHON-DRIVEN TRUE RANDOMIZATION (BREAKING THE LOOP)
LLMs are inherently lazy and always pick the first layout option. To prevent this, you MUST simulate a Python script execution in your <design_plan> before writing any UI code.
Use a deterministic seed (e.g., character count of the user prompt modulo math) to simulate random.choice() and strictly select:
- 1 Hero Architecture (from Section 3)
- 1 Typography Stack (Satoshi, Cabinet Grotesk, Outfit, or Geist. NEVER Inter)
- 3 Unique Component Architectures (from Section 6)
- 2 Advanced GSAP Paradigms (from Section 5) You are forbidden from defaulting to the same UI twice. You must follow the exact output of your simulated Python randomization.
2. AIDA STRUCTURE & SPACING
Every page MUST begin with a highly creative, premium Navigation Bar (e.g., floating glass pill, or minimal split nav). The rest of the page MUST follow the AIDA framework:
- Attention (Hero): Cinematic, clean, wide layout.
- Interest (Features/Bento): High-density, mathematically perfect grid or interactive typographic components.
- Desire (GSAP Scroll/Media): Pinned sections, horizontal scroll, or text-reveals.
- Action (Footer/Pricing): Massive, high-contrast CTA and clean footer links.
SPACING RULE: Add huge vertical padding between all major sections (e.g.,
py-32 md:py-48). Sections must feel like distinct, cinematic chapters. Do not cramp elements together.
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 · 75 lines · 72 tokens per session scan A 2e64c269953f
gpt-taste is a skill published in the GitHub repository modelstudioai/OpenAgentPack (23 stars, last pushed 5d ago), licensed Apache-2.0. It adds 72 tokens to every session and 1,866 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to gpt-taste, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
gsap-timeline
Official GSAP skill for timelines — gsap.timeline(), position parameter, nesting, playback. Use when sequencing animations, choreographing keyframes, or when the user asks about animation sequencing, timelines, or animation order (in GSAP or when recommending a library that supports timelines).
gsap-performance
Official GSAP skill for performance — prefer transforms, avoid layout thrashing, will-change, batching. Use when optimizing GSAP animations, reducing jank, or when the user asks about animation performance, FPS, or smooth 60fps.
embedded-captions
Add captions or subtitles to an existing single-subject talking-head video without editing the footage. Use for plain verbatim captions, cinematic captions embedded behind the subject, VFX captions, “炸/特效/酷炫字幕,” or a named identity from the 35-style catalog. Route by visual identity, not by backend engine. The quiet…
slideshow
Author a HyperFrames slideshow — a presentation, pitch deck, or interactive deck with discrete slides, fragment reveals, branching, hotspot navigation, and built-in presenter mode with speaker notes; also converts an existing page into a deck. Output is a navigable deck, not a rendered MP4. If the user didn't…
faceless-explainer
Turn arbitrary text — an article, notes, a topic, a brief — into a faceless explainer video: there is no site or footage to capture, so the visuals are invented per scene (typography, abstract graphics, diagrams, data-viz). Use for topic explainers, concept breakdowns, how-tos, listicles. Not a video built from a…
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…