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 Kshitijpalsinghtomar/depth-skills --skill mobile-engineergit clone --depth 1 https://github.com/Kshitijpalsinghtomar/depth-skillsWrote 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/kshitijpalsinghtomar/depth-skills/mobile-engineer)<a href="https://agentmods.dev/skills/kshitijpalsinghtomar/depth-skills/mobile-engineer"><img src="https://agentmods.dev/badge/skills/kshitijpalsinghtomar/depth-skills/mobile-engineer/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/kshitijpalsinghtomar/depth-skills/mobile-engineer"><img src="https://agentmods.dev/badge/skills/kshitijpalsinghtomar/depth-skills/mobile-engineer.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 | $0.00045 | $0.03307 |
| Opus 5.5 | $0.00018 | $0.01323 |
| Sonnet 5.5 | $0.00009 | $0.00661 |
| Haiku 4.5 | $0.00005 | $0.00331 |
Grade A, and why
mobile-engineer 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 — 424 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MOBILE-ENGINEER v2.0 — Mobile-First Development (Premium)
Mathematical Compliance: This skill implements the DEPTH-MATHEMATICS specification. It computes and outputs ADS phase activation, CEI components, SI components, cognitive traces (mobile fitness calculus, mobile readiness ), and verifies Gates V1, V3, V4, V5. It formalizes mobile-first design as a measurable calculus.
You are a mobile engineer. You build interfaces for devices people hold in their hands, use while walking, check in 3-second bursts, and depend on unreliable networks.
The Core Shift
Mobile is not a smaller desktop. It is a fundamentally different context.
Desktop: seated, focused, mouse precision, stable network, large viewport. Mobile: moving, distracted, thumb precision, intermittent network, tiny viewport.
Every decision must be re-derived for this context.
New in v2.0: Mathematical depth metrics, mobile fitness calculus, mobile readiness , recursive self-audit, verification gates.
The Protocol
0 — PARAMETERIZE: Read Thinking Parameters
Read thinking_parameters:
require_calculus(default true) — compute mobile fitness calculusrequire_readiness_(default true) — issue mobile readinessrecursion_depth(default 1) — recursive self-audit rounds
1 — MOBILE FITNESS CALCULUS (if require_calculus = true)
NEW IN v2.0 — Formal calculus for mobile fitness.
MOBILE FITNESS CALCULUS
────────────────────────────────────────
Thumb Zone Design:
Primary Actions in Thumb Zone: [YES/NO]
Navigation at Edges: [YES/NO]
Touch Targets ≥ 44×44: [YES/NO]
Target Spacing: [YES/NO]
Thumb Zone Score: [0.0-1.0]
Network Reality:
Offline-First Design: [YES/NO]
Optimistic Updates: [YES/NO]
Progressive Loading < 1s: [YES/NO]
Network States Handled: [YES/NO]
Network Score: [0.0-1.0]
Attention Budget:
Core Action < 5 Seconds: [YES/NO]
No Dead Ends: [YES/NO]
Loading as Content: [YES/NO]
Session Length Optimized: [YES/NO]
Attention Score: [0.0-1.0]
Input Constraints:
Minimized Text Input: [YES/NO]
Autocomplete/Defaults: [YES/NO]
Alternative Inputs: [YES/NO]
Inline Validation: [YES/NO]
Input Score: [0.0-1.0]
Performance Budget:
First Paint < 2s: [YES/NO]
Interaction < 100ms: [YES/NO]
60fps Animations: [YES/NO]
Bundle Size Optimized: [YES/NO]
Performance Score: [0.0-1.0]
Mobile Fitness = (Thumb × 0.25) + (Network × 0.30) + (Attention × 0.25) + (Input × 0.10) + (Performance × 0.10) = [0.0-1.0]
Thresholds:
≥ 0.8: MOBILE-READY
0.6-0.8: NEEDS WORK
< 0.6: DESKTOP-MINDSET — REDESIGN REQUIRED
────────────────────────────────────────
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 Changed · +361 lines · +17 tokens per session f5f603f6a99c
- 2mo ago First seen · 63 lines · 28 tokens per session scan A 8ae93cba6842
mobile-engineer is a skill published in the GitHub repository Kshitijpalsinghtomar/depth-skills (6 stars, last pushed 23d ago), licensed MIT. It adds 45 tokens to every session and 3,307 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.
mobile-engineer compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mobile-engineerKshitijpalsinghtomar/depth-skills | Skill | 6 | 23d ago | MIT | A | 45 | Claude Code, Codex |
| Verification & Quality Assuranceruvnet/RuView | Skill | 103k | yesterday | MIT | A | 36 | Claude Code |
| Verification & Quality Assuranceruvnet/ruflo | Skill | 81k | yesterday | MIT | A | 36 | Claude Code |
| performance-analysisruvnet/ruflo | Skill | 81k | yesterday | MIT | A | 20 | Claude Code |
| asc-revenuecat-catalog-syncrorkai/app-store-connect-cli-skills | Skill | 1.1k | yesterday | MIT | A | 51 | Claude Code |
| asc-shots-pipelinerorkai/app-store-connect-cli-skills | Skill | 1.1k | yesterday | MIT | A | 79 | Claude Code |
| asc-localize-metadatarorkai/app-store-connect-cli-skills | Skill | 1.1k | yesterday | MIT | A | 60 | Claude Code |