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 mwd1234/ios-agentic-skills --skill privacygit clone --depth 1 https://github.com/mwd1234/ios-agentic-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/mwd1234/ios-agentic-skills/privacy)<a href="https://agentmods.dev/skills/mwd1234/ios-agentic-skills/privacy"><img src="https://agentmods.dev/badge/skills/mwd1234/ios-agentic-skills/privacy/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/mwd1234/ios-agentic-skills/privacy"><img src="https://agentmods.dev/badge/skills/mwd1234/ios-agentic-skills/privacy.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 | $0.00039 | $0.01805 |
| Opus 5.5 | $0.00016 | $0.00722 |
| Sonnet 5.5 | $0.00008 | $0.00361 |
| Haiku 4.5 | $0.00004 | $0.00180 |
Grade A, and why
privacy 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 — 238 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Privacy & Permissions Audit
Verify Info.plist purpose strings, permission prompts, and data handling. Ensure least-privilege and clear disclosures.
When to use this skill
- Before App Store submission (required for App Privacy labels)
- When adding new permissions (camera, microphone, location, etc.)
- When reviewing data collection practices
- After adding analytics or third-party SDKs
Quick Reference: Required Purpose Strings
| Permission | Info.plist Key | When Required |
|---|---|---|
| Camera | NSCameraUsageDescription |
Photo/video capture |
| Microphone | NSMicrophoneUsageDescription |
Audio recording |
| Photo Library (read) | NSPhotoLibraryUsageDescription |
Accessing photos |
| Photo Library (add) | NSPhotoLibraryAddUsageDescription |
Saving photos only |
| Location (in-use) | NSLocationWhenInUseUsageDescription |
Location while app open |
| Location (always) | NSLocationAlwaysAndWhenInUseUsageDescription |
Background location |
| Bluetooth | NSBluetoothAlwaysUsageDescription |
BLE device connection |
| HealthKit | NSHealthShareUsageDescription |
Reading health data |
| Tracking (ATT) | NSUserTrackingUsageDescription |
Cross-app tracking/IDFA |
| Notifications | N/A (runtime prompt) | Push/local notifications |
| Haptics | N/A | No permission needed |
Step 1: Info.plist Audit
1.1 Find All Purpose Strings
# iOS app
rg 'UsageDescription' YourApp/Info.plist 2>/dev/null || echo "Check Xcode target Info tab"
# Watch app
rg 'UsageDescription' "YourApp Watch App/Info.plist" 2>/dev/null
1.2 Purpose String Localization
# Check for InfoPlist.strings in both targets
find YourApp -name "InfoPlist.strings" 2>/dev/null
find "YourApp Watch App" -name "InfoPlist.strings" 2>/dev/null
HIG Requirement: Purpose strings must:
- Explain why the app needs permission (not just "uses X")
- Be user-friendly, not technical
- Be localized for all supported languages
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 · 238 lines · 39 tokens per session scan A a5ee3de7d27e
privacy is a skill published in the GitHub repository mwd1234/ios-agentic-skills (50 stars, last pushed 9mo ago), licensed MIT. It adds 39 tokens to every session and 1,805 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 2026-08-30.
privacy compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| privacymwd1234/ios-agentic-skills | Skill | 50 | 9mo ago | MIT | A | 39 | Claude Code, Codex |
| play-policy-insightsandroid/skills | Skill | 10k | yesterday | Apache-2.0 | A | 66 | Claude Code |
| account-deletionrshankras/claude-code-apple-skills | Skill | 864 | 2d ago | MIT | A | 57 | Claude Code |
| consent-flowrshankras/claude-code-apple-skills | Skill | 864 | 2d ago | MIT | A | 54 | Claude Code |
| app-store-reviewsafaiyeh/app-store-review-skill | Skill | 443 | 21d ago | MIT | A | 76 | Claude Code, Codex |
| gplay-submission-checkshanamizuki/solopreneur | Skill | 156 | 3d ago | MIT | A | 45 | Claude Code |
| appstore-review-checkerluongnv89/skills | Skill | 145 | yesterday | MIT | A | 42 | Claude Code |