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 tutur3u/platform --skill tuturuuu-satellite-app-uxgit clone --depth 1 https://github.com/tutur3u/platformWrote 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/tutur3u/platform/tuturuuu-satellite-app-ux)<a href="https://agentmods.dev/skills/tutur3u/platform/tuturuuu-satellite-app-ux"><img src="https://agentmods.dev/badge/skills/tutur3u/platform/tuturuuu-satellite-app-ux/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/tutur3u/platform/tuturuuu-satellite-app-ux"><img src="https://agentmods.dev/badge/skills/tutur3u/platform/tuturuuu-satellite-app-ux.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00025 | $0.00680 |
| Opus 5.5 | $0.00010 | $0.00272 |
| Sonnet 5.5 | $0.00005 | $0.00136 |
| Haiku 4.5 | $0.00003 | $0.00068 |
Grade A, and why
tuturuuu-satellite-app-ux 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 13d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tuturuuu Satellite App UX
Core Workflow
Use this skill for standalone app surfaces under apps/* that behave like
satellite apps rather than sections inside apps/web.
For shell or auth changes, trace the target app's relevant proxy.ts, providers,
workspace layout, navigation, or app-session routes. A local UI change does not
require a full shell audit.
App Shell Checklist
- Use
@tuturuuu/satelliteproviders, i18n helpers, constants, and app-session helpers where the app already follows that pattern. - Keep auth target names consistent across proxy, verify-token, refresh, logout, and server session reads.
- Preserve workspace route shapes and locale handling. New dashboard routes need navigation aliases, icons, permissions or access gates, and empty states.
- Build the actual app workspace as the first screen. Avoid marketing-style landing pages for operational apps.
- Prefer a focused app shell with clear primary navigation, search/filter tools, and compact repeated actions over a generic dashboard card wall.
- Add strings to the owning app's English and Vietnamese bundles. If shared UI strings are added, update every app bundle that ships that shared surface.
Data And Mutation Rules
- Use TanStack Query for client fetching/mutation.
- Put shared app API clients behind
packages/internal-api/src/*when code is reused outside one route. - Do not add raw client-side app API fetches.
- Check shared clients' actual paths when configuring API fallbacks. Mind's
workspace selector uses Web-owned
/api/workspaces/*as well as/api/v1/*; its/api/*fallback preserves local product and auth handlers. Regression:apps/mind/src/next-config.test.tsexercises Next's rewrite matcher. - Keep protected data reads and writes behind server-owned APIs. Do not expose privileged Supabase access to satellite clients.
Cross-App Parity
For Calendar or Finance, assume the standalone app and the apps/web
counterpart move together unless the user explicitly scopes an exception.
What ships with it
1 file 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.
- 13d ago Changed 4e0fcbdfa06e
- 14d ago Changed · +4 lines 813c747f27db
- 1mo ago Changed · -1 lines 95c88e5abb30
- 2mo ago Changed · -31 tokens per session 38b29feaeb0e
- 2mo ago First seen · 68 lines · 56 tokens per session scan A ecb18ede651c
tuturuuu-satellite-app-ux is a skill published in the GitHub repository tutur3u/platform (54 stars, last pushed today), licensed Apache-2.0. It adds 25 tokens to every session and 680 once invoked, about $0.0001 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 2026-09-03.
tuturuuu-satellite-app-ux compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| tuturuuu-satellite-app-uxtutur3u/platform | Skill | 54 | today | Apache-2.0 | A | 25 | Codex |
| magic-uimagicuidesign/magicui | Skill | 23k | yesterday | MIT | A | 56 | Claude Code, Codex |
| frontend-engineerbuiphucminhtam/forgewright | Skill | 49 | 6d ago | none | A | 55 | Claude Code |
| shadcnshadcn-ui/ui | Skill | 127k | yesterday | MIT | A | 113 | Claude Code, Codex, Cursor |
| export-component-to-other-repointernet-development/nextjs-css-agent-components | Skill | 218 | 6d ago | MIT | A | 106 | Claude Code, Codex |
| ui-beatsnikhils4/ui-beats | Skill | 235 | 2mo ago | MIT | A | 62 | Claude Code, Codex |
| web-design-guidelinesagustinusnathaniel/nextarter-tailwind | Skill | 124 | 1mo ago | MIT | A | 44 | Claude Code, Codex |