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/robium-ai/robium/app-publishingnpx skills add robium-ai/robium --skill app-publishinggit clone --depth 1 https://github.com/robium-ai/robiumWrote 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/robium-ai/robium/app-publishing)<a href="https://agentmods.dev/skills/robium-ai/robium/app-publishing"><img src="https://agentmods.dev/badge/skills/robium-ai/robium/app-publishing.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 | $0.00146 | $0.01905 |
| Opus 5 | $0.00073 | $0.00953 |
| Sonnet 5 | $0.00029 | $0.00381 |
| Haiku 4.5 | $0.00015 | $0.00191 |
Grade A, and why
app-publishing 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 4d 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 — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
app-publishing
Turn a tested reference application into a public project that reads and looks like Robium without separating its story from its source. The app manifest owns runtime facts. Its portable case study owns the article and media. The website composes those sources into overview, live, guide, catalog, and social surfaces.
When to use this skill
- Publishing or refreshing a finished application on robium.ai.
- Writing or editing an app-backed article in the Robium product-lab voice.
- Producing a real-run hero, system diagram, social card, or optional conceptual illustration for an article.
- Replacing one-off public pages with the shared project identity and visual system.
- Cross-references: use
testingbefore publication,live-demofor hosted session mechanics, andskill-authorwhen changing this skill itself.
Key directives
- Delegation posture: embed + links. Embed Robium's editorial, visual, media, and repository-to-website contract here. Link to upstream project and embed patterns where they clarify delivery.
- Sound like a person who built the thing. Use direct sentences, specific
observations, and restrained judgment. Do not use em dashes, inflated
certainty, generic AI transitions, or repeated conclusions. See
references/editorial-system.md. - One app, one identity, several surfaces. Overview, live workspace, guide, cards, metadata, and source links share the app ID, project header, typography, color language, and status vocabulary.
- Real runs establish what happened. State the conditions and result plainly. Do not call every result proof or evidence. Generated art may explain a concept, but it must never resemble or replace application output.
- Facts stay with their owner. Runtime and capability truth comes from
robium-app.yaml. Article framing and media come fromdocs/case-study.md. Current public availability comes from the website. Do not create a second all-purpose page manifest. - A structure is a checklist, not a voice. Every article covers outcome, decision, system, run path, result, Robium's contribution, and limits. Its opening, section names, pacing, and emphasis should fit the application.
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 4d ago First seen · 165 lines · 146 tokens per session scan A 1f9950cf997a
app-publishing is a skill published in the GitHub repository robium-ai/robium (9 stars, last pushed 6d ago), licensed MIT. It adds 146 tokens to every session and 1,905 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
playwright-recording
Record browser interactions as video using Playwright. Use for capturing demo videos, app walkthroughs, and UI flows for Remotion videos. Triggers include recording a demo, capturing browser video, screen recording a website, or creating walkthrough footage.
lyria
Generate and validate music with Google Lyria 3 through the Gemini Interactions API. Use before calling OpenMontage googlemusic, designing Lyria 3 Clip or Pro prompts, using image-to-music or custom lyrics, choosing between Lyria 3 and Lyria RealTime, diagnosing Google music-generation failures, or preparing…
comfyui
Use when working with ComfyUI workflows in OpenMontage, including comfyuiimage/comfyuivideo/comfyuimusic, custom workflowjson/workflowpath inputs, outputnode selection, missing model setup, LoRAs, low-VRAM workflow choices, and community workflow imports.
dashscope
DashScope (Alibaba Cloud Bailian / 阿里云百炼) integration — image generation (qwen-image-2.0-pro), text-to-speech (qwen3-tts-flash), and ASR with word-level timestamps (qwen3-asr-flash-filetrans). Use when generating images via Qwen-Image, narrating via Qwen-TTS, or transcribing with word-level timestamps via Qwen-ASR.
hyperframes-animation
All animation knowledge for HyperFrames — atomic motion rules, multi-phase scene blueprints, scene transitions, broader motion-design techniques, AND the seven runtime adapters (GSAP default, plus Lottie, Three.js, Anime.js, CSS keyframes, Web Animations API, TypeGPU). Use for any motion or animation task: pick 2-4…
ltx2
AI video generation with LTX-2.3 22B — text-to-video, image-to-video clips for video production. Use when generating video clips, animating images, creating b-roll, animated backgrounds, or motion content. Triggers include video generation, animate image, b-roll, motion, video clip, text-to-video, image-to-video.