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 skills add aiatelie/ai-atelie --skill exportgit clone --depth 1 https://github.com/aiatelie/ai-atelieWrote 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/skills/aiatelie/ai-atelie/export)<a href="https://agentmods.dev/skills/aiatelie/ai-atelie/export"><img src="https://agentmods.dev/badge/skills/aiatelie/ai-atelie/export/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/skills/aiatelie/ai-atelie/export"><img src="https://agentmods.dev/badge/skills/aiatelie/ai-atelie/export.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 | $0.00043 | $0.02205 |
| Opus 5.5 | $0.00017 | $0.00882 |
| Sonnet 5.5 | $0.00009 | $0.00441 |
| Haiku 4.5 | $0.00004 | $0.00220 |
Grade A, and why
export 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 1mo 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 — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Export
The user wants to take an element from the active design canvas and save it for use in another tool — usually a video editor (DaVinci Resolve, FCP, Premiere, CapCut), sometimes a presentation tool. Pick the right format, call the matching capability, then write a single short sentence.
Critical: do not narrate file creation
The host renders an ArtifactCard inline in the chat for every successful export — thumbnail + filename + size + Download / Preview / Discuss buttons. You don't need to tell the user what you saved or where it landed; the card already shows that. Your reply is a one-sentence header explaining the choice, not a status report.
Bad — narrates what the user can already see:
I've saved the cat banner as a PNG file at exports/cat-banner.png. The file is 2.3MB and 3840×2160 pixels with a transparent background. You can download it using the link.
Good — confirms intent + invites iteration:
Cat banner as a 2× transparent PNG — should work straight on a Resolve overlay track.
Better — confirms + offers next step via mcp__ask-user__ask_user:
Saved as a 2× transparent PNG. Want me to also drop a 4K version for hero use? (then call ask_user with kind:"enum", options:["Yes, 4K too", "No, this is enough"])
Capabilities
These are the tools the host registry exposes. Whatever runtime you're in (MCP today, OpenAI tools later), the names and arg shapes are identical. They all return an artifact envelope:
{ "ok": true, "kind": "image|video|html-graphics|lottie", "filename": "...", "url": "...", "mime": "...", "bytes": N, "metadata": { ... } }
export_element— PNG or JPEG via real headless Chromium. Captures everything the browser actually renders (canvas, video, backdrop-filter, mix-blend-mode all work).export_ograf—.ograf.zipbundle for DaVinci Resolve 21+'s native HTML graphics import.
(More may be registered — check the tool list. Video / Lottie may have landed by the time you read this.)
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.
- 1mo ago First seen · 150 lines · 43 tokens per session scan A f7eb3a4673c6
export is a skill published in the GitHub repository aiatelie/ai-atelie (11 stars, last pushed 4mo ago), licensed MIT. It adds 43 tokens to every session and 2,205 once invoked, about $0.0002 per session on Opus 5.5. 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
open-design-landing
Produce a world-class single-page editorial landing site in the Atelier Zero visual language (Monocle / Apartamento / Études editorial collage) — the same aesthetic OpenDesign uses for its own marketing surface. The agent fills a typed inputs.json from a brand brief, optionally generates 16 collage assets via…
design-brief
Parse a structured design brief written in I-Lang protocol format into a concrete design spec. Eliminates ambiguity from vague requests like "make it professional" by requiring explicit dimensions: palette, typography, layout, mood, density, and constraints. Trigger keywords: "design brief", "create a design brief"…
critique
Run a 5-dimension expert design review on any HTML artifact in the project — Philosophy / Visual hierarchy / Detail / Functionality / Innovation, each scored 0–10. Outputs a single self-contained HTML report with a radar chart, evidence-backed scores, and three lists: Keep / Fix / Quick-wins. Use when the brief asks…
kami-landing
Produce a print-grade single-page kami (紙 / 纸) document — warm parchment canvas, ink-blue accent, serif at one weight, no italic, no cool grays. The output reads like a professional white paper or studio one-pager, not an app UI. Multilingual by design (EN · zh-CN · ja). One self-contained HTML file, zero dependencies.
open-design-landing-deck
OpenDesign's brand-story deck for partners and press: why it exists, what it believes, and where design is going. Built as a decision-grade marketing & GTM deck for partners, press, community.
tweaks
Wrap any HTML artifact with a side panel of live, parameterized controls — accent color, type scale, density, motion, theme — that rewrite CSS custom properties in real time and persist to localStorage. Lets the user explore variants of a design without re-prompting the agent. Use when the brief asks for "variants"…