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 markdavidgan/apple-dev-skills --skill privacy-manifestgit clone --depth 1 https://github.com/markdavidgan/apple-dev-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/markdavidgan/apple-dev-skills/privacy-manifest)<a href="https://agentmods.dev/skills/markdavidgan/apple-dev-skills/privacy-manifest"><img src="https://agentmods.dev/badge/skills/markdavidgan/apple-dev-skills/privacy-manifest/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/markdavidgan/apple-dev-skills/privacy-manifest"><img src="https://agentmods.dev/badge/skills/markdavidgan/apple-dev-skills/privacy-manifest.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 | $0.00097 | $0.01905 |
| Opus 5.5 | $0.00039 | $0.00762 |
| Sonnet 5.5 | $0.00019 | $0.00381 |
| Haiku 4.5 | $0.00010 | $0.00191 |
Grade A, and why
privacy-manifest 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Privacy Manifests & Required-Reason APIs
Declare data use and justify required-reason APIs so the build passes App Review. Missing or incomplete manifests cause hard rejections (ITMS-91053, ITMS-91061) at upload/processing time — often after a "successful" upload (see asc-submission async failures). Run this before submitting.
A privacy manifest is a property list named PrivacyInfo.xcprivacy added to a target (and required in each SDK/framework, not just the app). It declares four things.
The four keys
<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
<plist version="1.0">
<dict>
<key>NSPrivacyTracking</key>
<false/> <!-- true only if you track per App Tracking Transparency -->
<key>NSPrivacyTrackingDomains</key>
<array/> <!-- domains used for tracking; MUST be empty if NSPrivacyTracking is false -->
<key>NSPrivacyCollectedDataTypes</key>
<array>
<dict>
<key>NSPrivacyCollectedDataType</key>
<string>NSPrivacyCollectedDataTypeCrashData</string>
<key>NSPrivacyCollectedDataTypeLinked</key>
<false/> <!-- linked to user identity? -->
<key>NSPrivacyCollectedDataTypeTracking</key>
<false/> <!-- used to track? -->
<key>NSPrivacyCollectedDataTypePurposes</key>
<array>
<string>NSPrivacyCollectedDataTypePurposeAppFunctionality</string>
</array>
</dict>
</array>
<key>NSPrivacyAccessedAPITypes</key>
<array>
<dict>
<key>NSPrivacyAccessedAPIType</key>
<string>NSPrivacyAccessedAPICategoryUserDefaults</string>
<key>NSPrivacyAccessedAPITypeReasons</key>
<array>
<string>CA92.1</string> <!-- access only to data written by this app -->
</array>
</dict>
</array>
</dict>
</plist>
NSPrivacyTracking(Bool) — does the app/SDK track per ATT?NSPrivacyTrackingDomains(array) — domains that perform tracking. Must be empty ifNSPrivacyTrackingis false. Find them with the App Privacy Report / Instruments Network instrument.NSPrivacyCollectedDataTypes(array) — what data you collect, whether it's linked to identity, whether it's used for tracking, and the purposes. This feeds the App Store privacy nutrition label.NSPrivacyAccessedAPITypes(array) — each required-reason API category you call, plus approved reason codes.
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 · 135 lines · 97 tokens per session scan A 0e8272590c6b
privacy-manifest is a skill published in the GitHub repository markdavidgan/apple-dev-skills (5 stars, last pushed 2mo ago), licensed MIT. It adds 97 tokens to every session and 1,905 once invoked, about $0.0004 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 2026-09-03.
privacy-manifest compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| privacy-manifestmarkdavidgan/apple-dev-skills | Skill | 5 | 2mo ago | MIT | A | 97 | 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 |
| asc-metadata-syncrorkai/app-store-connect-cli-skills | Skill | 1.1k | yesterday | MIT | A | 47 | Claude Code |
| asc-submission-healthrorkai/app-store-connect-cli-skills | Skill | 1.1k | yesterday | MIT | A | 82 | Claude Code |
| asc-release-flowrorkai/app-store-connect-cli-skills | Skill | 1.1k | yesterday | MIT | A | 71 | Claude Code |