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 tungnk123/mobile-best-practices --skill assetsgit clone --depth 1 https://github.com/tungnk123/mobile-best-practicesWrote 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/tungnk123/mobile-best-practices/assets)<a href="https://agentmods.dev/skills/tungnk123/mobile-best-practices/assets"><img src="https://agentmods.dev/badge/skills/tungnk123/mobile-best-practices/assets/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/tungnk123/mobile-best-practices/assets"><img src="https://agentmods.dev/badge/skills/tungnk123/mobile-best-practices/assets.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 | $0.00113 | $0.01361 |
| Opus 5.5 | $0.00045 | $0.00544 |
| Sonnet 5.5 | $0.00023 | $0.00272 |
| Haiku 4.5 | $0.00011 | $0.00136 |
Grade A, and why
mobile-best-practices 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.
How it starts
The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mobile Best Practices
2,042 searchable best practices for Android, iOS, Flutter, and React Native. Android-first with Jetpack Compose.
How to Use
This skill does not trigger automatically. The database is only searched when you explicitly invoke it. Three ways to use it:
| Mode | How | Requires |
|---|---|---|
| AGENT | /mobile-best-practices slash command in Claude Code |
Claude Code + IDE restart |
| CLI | python3 scripts/search.py "<query>" -p android |
Python 3 |
| READER | Open CSV/markdown files directly | Nothing |
AGENT — Slash command (primary mode)
/mobile-best-practices
Restart your IDE after installing. The slash command registry is only loaded at startup — the skill will not appear until you restart.
⚠️ Some IDEs do not support slash skills (e.g. certain VS Code forks, JetBrains AI Assistant, non-Claude agents). Use CLI mode in those cases.
CLI — Terminal search
python3 scripts/search.py "<query>" -p android -n 3
Works anywhere Python 3 is available. No IDE needed.
READER — Browse files directly
No tooling required. Open the source files:
| File | Content |
|---|---|
data/platforms/android.csv |
423 Android/Compose guidelines |
data/platforms/ios.csv |
iOS/SwiftUI guidelines |
data/code-snippets.csv |
80 copy-paste code templates |
data/security.csv |
437 security practices |
references/CODE-RULES.md |
Code generation rules |
references/CHECKLIST.md |
Pre-delivery checklist |
Installation
# via npm
npx mobile-best-practices install
# or manually symlink
ln -s /path/to/mobile-best-practices ~/.claude/skills/mobile-best-practices
After installing, restart your IDE to register the /mobile-best-practices slash command.
Prerequisites
Python 3.x required. Check: python3 --version
Search
python3 scripts/search.py "<query>" --domain <domain> [-n <max_results>]
python3 scripts/search.py "<query>" --platform <platform>
python3 scripts/search.py "<query>" --domain <domain> --filter-platform <platform>
python3 scripts/search.py "<query>" --domain <domain> --compact # token-optimized output
What ships with it
47 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.
- commands/mobile-anr-crash-check.md 5.0 KB
- commands/mobile-performance-check.md 5.1 KB
- commands/mobile-security-audit.md 6.6 KB
- commands/mobile-setup-android.md 6.6 KB
- data/anti-patterns.csv 56 KB
- data/architectures.csv 24 KB
- data/code-snippets.csv 168 KB
- data/design-patterns.csv 134 KB
- data/gradle-deps.csv 17 KB
- data/libraries.csv 25 KB
- data/performance.csv 122 KB
- data/platforms/android.csv 237 KB
- data/platforms/flutter.csv 18 KB
- data/platforms/ios.csv 20 KB
- data/platforms/react-native.csv 18 KB
- data/project-templates.csv 4.7 KB
- data/reasoning-rules.csv 22 KB
- data/security.csv 244 KB
- data/testing.csv 28 KB
- data/ui-patterns.csv 28 KB
- references/CHECKLIST.md 1.8 KB
- references/CODE-RULES.md 4.2 KB
- scripts/core.py 31 KB runs code
- scripts/search.py 8.1 KB runs code
- skills/all.md 17 KB
- skills/android-xml.md 7.1 KB
- skills/android.md 14 KB
- skills/flutter.md 10 KB
- skills/ios.md 9.7 KB
- skills/react-native.md 11 KB
- templates/base/quick-reference.md 1.4 KB
- templates/base/skill-content.md 3.2 KB
- templates/platforms/agent.json 187 B
- templates/platforms/antigravity.json 317 B
- templates/platforms/claude.json 661 B
- templates/platforms/codebuddy.json 229 B
- templates/platforms/codex.json 192 B
- templates/platforms/continue.json 226 B
- templates/platforms/copilot.json 225 B
- templates/platforms/cursor.json 238 B
- templates/platforms/gemini.json 194 B
- templates/platforms/kiro.json 236 B
- templates/platforms/opencode.json 196 B
- templates/platforms/qoder.json 213 B
- templates/platforms/roocode.json 206 B
- templates/platforms/trae.json 206 B
- templates/platforms/windsurf.json 244 B
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 · 140 lines · 113 tokens per session scan A 908834ce1a23
mobile-best-practices is a skill published in the GitHub repository tungnk123/mobile-best-practices (22 stars, last pushed 8mo ago), licensed MIT. It adds 113 tokens to every session and 1,361 once invoked, about $0.0005 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 2026-08-30.
mobile-best-practices compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mobile-best-practicestungnk123/mobile-best-practices | Skill | 22 | 8mo ago | MIT | A | 113 | Claude Code, Codex |
| orca-emulator-androidstablyai/orca | Skill | 124k | today | MIT | A | 102 | Claude Code, Codex |
| glance-canonical-layoutsandroid/skills | Skill | 11k | 3d ago | Apache-2.0 | A | 56 | Claude Code |
| android-tombstone-symbolicationdotnet/skills | Skill | 6.1k | yesterday | MIT | A | 176 | Claude Code |
| flutter-devMiniMax-AI/skills | Skill | 14k | 4d ago | MIT | A | 83 | Claude Code |
| dogfoodcallstack/agent-device | Skill | 5.4k | today | MIT | A | 55 | Claude Code |
| winapp-mauimicrosoft/winappCli | Skill | 1.4k | today | MIT | A | 68 | Claude Code |