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/tosin2013/helmdeck/helmdeck-hyperframes-authoringnpx skills add tosin2013/helmdeck --skill helmdeck-hyperframes-authoringgit clone --depth 1 https://github.com/tosin2013/helmdeckWhat 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 | $0.00132 | $0.03453 |
| Opus 5 | $0.00066 | $0.01726 |
| Sonnet 5 | $0.00026 | $0.00691 |
| Haiku 4.5 | $0.00013 | $0.00345 |
Grade A, and why
helmdeck-hyperframes-authoring 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 — 264 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hyperframes authoring — render-deterministic rules
When you write composition HTML/CSS/JS for hyperframes, the renderer seeks to each frame index rather than playing the timeline forward. Anything that depends on continuous wall-clock time, animation history, or post-paint DOM mutation breaks during seek — even if it looks perfect in hyperframes preview. Upstream tracks this as "the hardest class of bug in agent-authored compositions". The rules below collapse to one principle: everything must be reconstructible from the timeline's current totalTime() alone.
Before you write any composition: the four rules to remember
- One GSAP timeline per composition, registered synchronously, keyed by
data-composition-id. - Layout in HTML/CSS (final visible state); animate with
gsap.from()into that state. - No
setTimeout,setInterval,requestAnimationFrame,repeat: -1, or post-paint DOM mutation. - All assets local (no Google Fonts CDN, no S3 URLs, no jsdelivr except GSAP itself).
The structural contract
Timeline registration
Every composition ends its <script> with this exact shape:
const tl = gsap.timeline({ paused: true });
// ... synchronous tl.from() / tl.to() / tl.addLabel() calls ...
window.__timelines = window.__timelines || {};
window.__timelines["<composition-id>"] = tl; // ← KEY MUST EQUAL data-composition-id ATTRIBUTE
The <composition-id> key MUST exactly match the data-composition-id attribute on the composition's root <div>. If they differ, the timeline is registered but never auto-attached to the parent — the composition renders as static last-frame.
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 · 264 lines · 132 tokens per session scan A 08838a84d077
helmdeck-hyperframes-authoring is a skill published in the GitHub repository tosin2013/helmdeck (4 stars, last pushed 8d ago), licensed Apache-2.0. It adds 132 tokens to every session and 3,453 once invoked, about $0.0007 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 skills, from other repositories
ffmpeg
Process audio and video with the ffmpeg / ffprobe CLIs — convert, trim, extract audio, resize, change format, make GIFs, inspect media. Use for any audio/video transformation.
imagemagick
Edit and convert images with the ImageMagick magick CLI — resize, crop, convert format, compress, rotate, montage, annotate. Use for any still-image transformation.
image-gen
Generate images from text prompts via DashScope/Qwen. Use when creating, drawing, or illustrating images.
aov-mingyu-api
通过 aov.cc 公开 API 调用命理、占卜和一站式提示词能力。用于需要八字排盘、紫微斗数排盘、六爻、梅花易数、奇门遁甲、大六壬、小六壬、塔罗、三山国王灵签、黄历择日、雷诺曼、星盘，或直接返回可交给 AI 解读的完整提示词的任务。.
unicli-repair
Evidence-driven repair workflow for a broken Uni-CLI adapter. Trigger on a failed unicli envelope, a quarantined adapter, or an explicit adapter-repair request. Classifies non-source failures, edits only the reported adapter path, and uses the original command as a bounded oracle.
unicli-operate
Compatibility guide for unicli operate. Prefer unicli browser, which now exposes the same operator surface plus broker/session diagnostics.