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 lsantosweb/codex-agents-skills-kit --skill mobile-developergit clone --depth 1 https://github.com/lsantosweb/codex-agents-skills-kitWrote 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/lsantosweb/codex-agents-skills-kit/mobile-developer)<a href="https://agentmods.dev/skills/lsantosweb/codex-agents-skills-kit/mobile-developer"><img src="https://agentmods.dev/badge/skills/lsantosweb/codex-agents-skills-kit/mobile-developer/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/lsantosweb/codex-agents-skills-kit/mobile-developer"><img src="https://agentmods.dev/badge/skills/lsantosweb/codex-agents-skills-kit/mobile-developer.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 | $0.00032 | $0.00440 |
| Opus 5.5 | $0.00013 | $0.00176 |
| Sonnet 5.5 | $0.00006 | $0.00088 |
| Haiku 4.5 | $0.00003 | $0.00044 |
Grade A, and why
mobile-developer 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 2mo 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.
What it actually says
When to use
Use this skill for:
- React Native, Expo, Flutter, iOS, Android
- mobile navigation, gestures, haptics, touch targets
- app store readiness, mobile debugging, offline sync
- native modules, device APIs, push notifications
- mobile-specific performance or UX issues
Core operating rules
- Mobile is touch-first, battery-aware, and interruption-heavy.
- Respect platform conventions instead of forcing desktop patterns into small screens.
- Ask for missing constraints before coding when the request is open-ended: platform, framework, offline needs, navigation pattern, target devices, and state management.
- Prefer secure storage for sensitive data.
- Optimize lists, animations, and startup path before polishing secondary details.
- Never declare the work complete without a real build when the environment supports it.
Mandatory design and implementation checks
- touch targets are at least 44pt on iOS or 48dp on Android
- primary actions sit in the thumb-friendly zone when feasible
- lists use efficient virtualized patterns
- loading, error, and offline states exist
- interactive elements are accessible
- secrets and tokens are not stored in plain text
- platform differences are handled intentionally
Workflow
- Confirm platform, framework, and constraints.
- Identify whether the task is architecture, bugfix, UX polish, or performance.
- Implement the smallest safe change that fits the mobile stack.
- Validate both UX and runtime impact.
- Run build/lint/test commands when available.
Build verification rule
Before saying the task is done, run the relevant build if the project environment is available:
- React Native: Android/iOS build command as applicable
- Expo:
npx expo run:*or EAS workflow if configured - Flutter:
flutter build ...
Output format
Report:
- platform and framework assumed or confirmed
- files changed
- mobile-specific UX/performance/security considerations
- checks run and results
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.
- 2mo ago First seen · 56 lines · 32 tokens per session scan A 3c8da68e11f2
mobile-developer is a skill published in the GitHub repository lsantosweb/codex-agents-skills-kit (2 stars, last pushed 7mo ago), licensed MIT. It adds 32 tokens to every session and 440 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 2026-08-31.
mobile-developer compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mobile-developerlsantosweb/codex-agents-skills-kit | Skill | 2 | 7mo ago | MIT | A | 32 | Codex |
| orca-emulator-androidstablyai/orca | Skill | 117k | yesterday | MIT | A | 102 | Claude Code, Codex |
| glance-canonical-layoutsandroid/skills | Skill | 10k | yesterday | Apache-2.0 | A | 56 | Claude Code |
| android-tombstone-symbolicationdotnet/skills | Skill | 5.8k | yesterday | MIT | A | 176 | Claude Code |
| dogfoodcallstack/agent-device | Skill | 5.3k | yesterday | MIT | A | 55 | Claude Code |
| winapp-mauimicrosoft/winappCli | Skill | 1.4k | yesterday | MIT | A | 68 | Claude Code |
| app_remixrome-os/rome | Skill | 889 | yesterday | MIT | A | 50 | Claude Code, Codex |