Tracely is a CI/CD system for AI agents that turns failed production traces into replayable regression tests. Development teams use it to detect and group agent failures, run the resulting cases on pull requests, and block changes that reproduce those failures. The catalogue entries provide skills for operating this trace-based testing and observability workflow.
Borrowing it
Nothing to install: this file belongs to Jwuthri/Tracely-ai. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Jwuthri/Tracely-ai/master/.agents/skills/mobile-principles/SKILL.mdgit clone --depth 1 https://github.com/Jwuthri/Tracely-aiWrote 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/jwuthri/tracely-ai/mobile-principles)<a href="https://agentmods.dev/skills/jwuthri/tracely-ai/mobile-principles"><img src="https://agentmods.dev/badge/skills/jwuthri/tracely-ai/mobile-principles/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/jwuthri/tracely-ai/mobile-principles"><img src="https://agentmods.dev/badge/skills/jwuthri/tracely-ai/mobile-principles.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 | $0.00040 | $0.02515 |
| Opus 5 | $0.00020 | $0.01257 |
| Sonnet 5 | $0.00008 | $0.00503 |
| Haiku 4.5 | $0.00004 | $0.00251 |
Grade A, and why
mobile-principles 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 9d 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.
Copies of this mod
2 near-identical copies found in the catalogue:
- mobile-principles — 92% identical, 2 lines differ
- mobile-principles — 92% identical, 2 lines differ
How it starts
The opening of the file, as written. The whole thing — 290 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mobile Principles
Touch-first UX context. Loaded when mobile is detected (web mobile, iOS, Android). Concise rules here. Deep-dive in
references/.
Touch Targets
| Platform | Minimum | Recommended | Spec |
|---|---|---|---|
| Apple iOS | 44pt | 44pt + 8pt spacing | Apple HIG |
| Android | 48dp | 48dp + 8dp spacing | Material Design |
| Web mobile | 44px | 44px + 8px spacing | WCAG 2.5.5 |
Rule of thumb: any tap target smaller than the platform minimum is a usability bug, period.
The hit area can extend beyond the visible glyph (use padding, hitSlop, or a transparent inner spacer), but the interactive surface must reach the minimum. Spacing matters as much as size: two 44pt buttons touching edges are still mistappable.
No-Hover Doctrine
:hover does not exist on touch. Treating it as a primary trigger means hidden affordances on every phone. Anything reachable only by hover is, on mobile, simply gone. Visible-by-default is the rule; hover styles are a desktop enhancement, never a load-bearing interaction.
CSS - gate hover styles behind a media query:
.card { opacity: 1; transform: translateY(0); }
@media (hover: hover) and (pointer: fine) {
.card { opacity: 0.85; }
.card:hover { opacity: 1; transform: translateY(-2px); }
}
SwiftUI - tap and long-press, no pseudo-hover:
Image(systemName: "heart")
.onTapGesture { toggleLike() }
.contextMenu {
Button("Share", systemImage: "square.and.arrow.up", action: share)
Button("Report", systemImage: "flag", role: .destructive, action: report)
}
Compose - combinedClickable for tap + long-press:
Box(
modifier = Modifier
.combinedClickable(
onClick = { toggleLike() },
onLongClick = { showContextMenu() },
)
) {
Icon(Icons.Default.Favorite, contentDescription = "Like")
}
Thumb Zones (Hoober)
Steven Hoober's research shows portrait phone use is overwhelmingly one-handed or cradled, with the thumb pivoting from the bottom corner. The screen splits into reachable zones:
What ships with it
2 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.
- 9d ago First seen · 290 lines · 40 tokens per session scan A af7c1a09fb8c
mobile-principles is a skill published in the GitHub repository Jwuthri/Tracely-ai (1,216 stars, last pushed yesterday), licensed MIT. It adds 40 tokens to every session and 2,515 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
blueprint
Extract a complete specs/ directory from any frontend codebase. Covers all 12 axes needed to rebuild or migrate a frontend app. Produces 80% quality on first pass, refined to 95% through guided iteration.
design-system
Use when creating or refactoring a product UI system, shared components, themes, tokens, or dashboard styling. Keeps color, typography, spacing, states, and responsive rules coherent without introducing a large component abstraction prematurely.
3d-web-experience
Expert in building 3D experiences for the web - Three.js, React Three Fiber, Spline, WebGL, and interactive 3D scenes. Covers product configurators, 3D portfolios, immersive websites, and bringing dep.
ui
Guidance for designing user interfaces and React applications around users' ability to complete tasks. It also covers accessible and consistent interface construction.
design-taste-frontend
Anti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, and ships interfaces that do not look templated. Real design systems when applicable, audit-first on redesigns, strict pre-flight check.
temps-design-system
Build or review console UI so it reads as Temps: the paper-and-ink operator design system (@temps-sdk/ds primitives, the operator ink v1 skin, the Ledger / Detail / Settings page templates, the status vocabulary and the record recipe). Invoke when a task adds or redesigns a console screen, a landing section or a…