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 aka-kika/akakika-skills --skill macos-permissions-privacygit clone --depth 1 https://github.com/aka-kika/akakika-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/aka-kika/akakika-skills/macos-permissions-privacy)<a href="https://agentmods.dev/skills/aka-kika/akakika-skills/macos-permissions-privacy"><img src="https://agentmods.dev/badge/skills/aka-kika/akakika-skills/macos-permissions-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/aka-kika/akakika-skills/macos-permissions-privacy"><img src="https://agentmods.dev/badge/skills/aka-kika/akakika-skills/macos-permissions-privacy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 6 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 3 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Rogue Agent · line 8 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Rogue Agent · line 36 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Rogue Agent · line 51 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Rogue Agent · line 162 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Rogue Agent · line 196 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00060 | $0.02222 |
| Opus 5 | $0.00030 | $0.01111 |
| Sonnet 5 | $0.00012 | $0.00444 |
| Haiku 4.5 | $0.00006 | $0.00222 |
Grade A, and why
macos-permissions-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 12d 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 — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.
macOS Permissions & Privacy
Request only what the app needs now, explain why before the system asks, and give every denied state a recovery path. On macOS the permission landscape (TCC) is a patchwork — each permission has its own API, its own Info.plist key, and its own failure mode; the map below is most of the work.
When to use
Use this skill when the user says:
- permission / permission prompt / TCC
- Accessibility access, Screen Recording, Full Disk Access, Input Monitoring
- Automation / Apple Events / "wants to control"
- access files, contacts, calendar, camera, microphone
- app can't see the folder / operation not permitted
- privacy settings / privacy copy
- sandbox entitlements for user data
Do not use this skill for notification permission specifically (see macos-notifications) or for iOS-only flows like App Tracking Transparency.
Core rule
Explain before the system prompts. Request at the moment of need.
Request the narrowest thing that works. Every denied state has a
visible recovery path.
The permission map
The column you'll consult most. "Prompt?" = can the app trigger a system dialog, or must the user flip a switch in System Settings themselves?
| Need | API to check/request | Info.plist usage string | Prompt? |
|---|---|---|---|
| Files the user picks | NSOpenPanel / drag-in + security-scoped bookmarks |
— | Picker is consent |
| Desktop / Documents / Downloads (programmatic) | just access it; system prompts once | — | Yes, automatic |
| Network volumes / removable | same | — | Yes, automatic |
| Full Disk Access | none — attempt access, detect failure | — | No — Settings only |
| Accessibility (control UI, event taps) | AXIsProcessTrustedWithOptions |
— | Prompt opens Settings |
| Screen Recording | CGPreflightScreenCaptureAccess() / CGRequestScreenCaptureAccess() |
— | Once; then Settings |
| Input Monitoring | IOHIDCheckAccess(.listenEvent) / IOHIDRequestAccess |
— | Yes |
| Automation (Apple Events) | AEDeterminePermissionToAutomateTarget |
NSAppleEventsUsageDescription |
Yes, per target app |
| Camera / Microphone | AVCaptureDevice.requestAccess(for:) |
NSCameraUsageDescription / NSMicrophoneUsageDescription |
Yes |
| Contacts | CNContactStore.requestAccess |
NSContactsUsageDescription |
Yes |
| Calendar / Reminders | EKEventStore.requestFullAccessToEvents() |
NSCalendarsFullAccessUsageDescription |
Yes |
| Location | CLLocationManager.requestWhenInUseAuthorization |
NSLocationUsageDescription |
Yes |
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.
- 12d ago First seen · 211 lines · 60 tokens per session scan A 103071b5822f
macos-permissions-privacy is a skill published in the GitHub repository aka-kika/akakika-skills (10 stars, last pushed 2d ago), licensed MIT. It adds 60 tokens to every session and 2,222 once invoked, about $0.0003 per session on Opus 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.
Other skills, from other repositories
vercel-react-native-skills
React Native and Expo best practices for building performant mobile apps. Use when building React Native components, optimizing list performance, implementing animations, or working with native modules. Triggers on tasks involving React Native, Expo, mobile performance, or native platform APIs.
firebase-messaging
Use when setting up Firebase Cloud Messaging, managing permissions and tokens, handling background/foreground notification taps, or dispatching messages server-side (HTTP v1).
firebase-app-check
Use when implementing app attestation, configuring App Check providers, setting up debug tokens, enabling backend enforcement, or managing token refresh.
flutter-app-architecture
Use when scaffolding a project, refactoring into layers, creating view models/repositories, configuring dependency injection, or implementing unidirectional data flow (MVVM).
firebase-ai
Use when setting up firebaseai, generating text/chat with Gemini, streaming AI output, building multimodal prompts, or handling AI errors.
firebase-crashlytics
Use when implementing crash reporting, capturing fatal/non-fatal errors, recording isolate/async exceptions, customizing reports, or uploading obfuscated symbols.