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 oxy-hq/oxygen --skill oxy-app-visual-identitygit clone --depth 1 https://github.com/oxy-hq/oxygenWrote 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/oxy-hq/oxygen/oxy-app-visual-identity)<a href="https://agentmods.dev/skills/oxy-hq/oxygen/oxy-app-visual-identity"><img src="https://agentmods.dev/badge/skills/oxy-hq/oxygen/oxy-app-visual-identity/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/oxy-hq/oxygen/oxy-app-visual-identity"><img src="https://agentmods.dev/badge/skills/oxy-hq/oxygen/oxy-app-visual-identity.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 | $0.00143 | $0.01298 |
| Opus 5.5 | $0.00057 | $0.00519 |
| Sonnet 5.5 | $0.00029 | $0.00260 |
| Haiku 4.5 | $0.00014 | $0.00130 |
Grade A, and why
oxy-app-visual-identity 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Customer-app visual identity (icon + art), unified
A custom app has exactly two pictures, and there is one way to source and render each — everywhere. Do not grow a second mechanism per surface.
Scope: platform rendering only. This is how oxy sources + renders app pictures.
How an app author declares icon/art and ships the asset files is a customer-apps
concern — see the hello-oxy example + the customer-app-development skill in the
customer-apps repo, not here. The field contract itself is defined once in
OxyAppManifest (+ the SDK manifest type); this skill only references it. Keep
authoring how-to out of here so the two don't drift.
The single source of truth
Both pictures come only from the bundle's oxy-app.json manifest, as relative
paths inside the bundle:
| Manifest field | Meaning | API field | Rendered as |
|---|---|---|---|
icon |
the app glyph/favicon (a small square mark) | icon_url |
24px object-contain mark beside the name / rail tile |
art |
the app screenshot/preview (a wide image) | art_url |
h-40 w-full object-cover card image |
The API turns each relative path into a same-origin URL: <app canonical url>/<path>,
after safe_relative_art_path rejects anything that escapes the bundle (.., absolute,
off-origin, \\, ?, #). The homepage helper is
manifest_card_fields + CustomAppSummary::from_model_with_manifest in
crates/app/src/server/api/workspace_custom_apps.rs. Reuse that helper — do not
re-derive URLs by hand.
Non-negotiables
- Manifest is the ONLY source. Do not add a
<url>/favicon.icofetch, a headless-browser screenshot capture, anicon/art/screenshot/faviconDB column, or any per-surface image derivation. If a picture isn't in the manifest, the app has no picture — render the fallback, not a second lookup. (There is deliberately no screenshot capture yet;artis author-supplied only.) - The homepage's manifest approach is canonical; every other surface follows it.
Admin adopts what the homepage shows, never the reverse. The old admin-only
AppFavicon(<url>/favicon.ico) mechanism is removed — admin readsicon_urlfrom the API like the homepage does. - One shared render component per picture.
AppMark(icon → monogram fallback: the name's initial in a tile) andAppArt(art → initial-letter tile fallback). Both the launcher and the admin browser import the same components. A new surface showing an app icon importsAppMark; it does not hand-roll an<img>+ fallback. - Fallbacks, not blanks. No
icon_url→ monogram (never nothing). Noart_url→ letter tile. Both fallbacks derive fromapp.name[0]and usebg-primary/10+text-primary, so a picture-less app still reads as a first-class card. - List endpoints resolve manifests in BATCH. Any endpoint returning many apps
(admin
list_apps/list_my_apps, homepagelist_custom_apps) must resolve the per-app manifest with a single batched load (joinpublished_build_id→app_builds.manifest_json, plusapps.manifest_override), never an N+1 per-app read. Manifest resolution is metadata: a failure yields empty icon/art, never a 500.
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 · 79 lines · 143 tokens per session scan A bd4925775bee
oxy-app-visual-identity is a skill published in the GitHub repository oxy-hq/oxygen (203 stars, last pushed yesterday), licensed Apache-2.0. It adds 143 tokens to every session and 1,298 once invoked, about $0.0006 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 2026-10-14.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
glance-canonical-layouts
Use this skill to create home screen widgets using Jetpack Glance Canonical Layouts from the Android Platform Samples project, or when asked to implement standard widget layout patterns (including Check List, Image Grid, Snap Scrolling, and Standard Toolbar).
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.