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 agentmods add skills/gaelic-ghost/socket/macos-privacy-permissions-workflownpx skills add gaelic-ghost/socket --skill macos-privacy-permissions-workflowgit clone --depth 1 https://github.com/gaelic-ghost/socketWrote 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/gaelic-ghost/socket/macos-privacy-permissions-workflow)<a href="https://agentmods.dev/skills/gaelic-ghost/socket/macos-privacy-permissions-workflow"><img src="https://agentmods.dev/badge/skills/gaelic-ghost/socket/macos-privacy-permissions-workflow.svg" alt="Measured on agentmods" 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 | $0.00054 | $0.01209 |
| Opus 5 | $0.00027 | $0.00605 |
| Sonnet 5 | $0.00011 | $0.00242 |
| Haiku 4.5 | $0.00005 | $0.00121 |
Grade A, and why
macos-privacy-permissions-workflow 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 yesterday.
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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
macOS Privacy Permissions Workflow
Purpose
Identify the protected operation, responsible executable, and current public authorization contract before changing code or asking the person to change Privacy & Security settings. Keep project declarations, user consent, managed policy, and runtime success as separate evidence.
When To Use
- Use for macOS privacy authorization failures, permission prompts, Settings entries,
tccutil reset, PPPC policy, and responsible-code attribution. - Use for Accessibility, Automation, Developer Tools, screen/system-audio recording, Input Monitoring, camera, microphone, personal data, Files and Folders, Full Disk Access, App Management, and other current macOS privacy classes.
- Do not use private TCC APIs or database details as an application implementation contract.
Single-Path Workflow
- Record the exact attempted operation, target resource or process, timestamp, user/session, error domain/code/message, and whether the evidence came from the host, a guest, or a physical Mac.
- Resolve the responsible code: executable path, bundle identifier, Team ID, designated requirement, signing state, parent/launcher, helper or XPC boundary, and whether the artifact changed. Read
references/responsible-code-and-attribution.md. - Apply the Apple docs gate through
explore-apple-swift-docs. Record the host macOS version/build and selected SDK/Xcode, then verify the current framework API and settings name. Do not promote an internal service string to a public API. - Select the class in
references/permission-class-matrix.md. Inspect the relevant usage description, entitlement/capability, sandbox state, helper identity, and final signed artifact without treating any declaration as consent. - Preflight or read status using the class's documented public API when one exists. Preserve
.notDetermined, restricted or managed, denied, limited, and authorized states instead of collapsing them to Boolean access. - Request only from the user action that needs access and only when the public API supports requesting. Explain the operation, system UI, denial behavior, later Settings path, and any relaunch/helper restart/logout requirement.
- For Settings-managed classes such as Full Disk Access, describe the user or MDM decision and the narrow responsible executable. Never invent a self-grant API or grant a broad terminal, IDE, or agent host without explaining its broader authority.
- Read
references/prompting-settings-reset-and-mdm.mdbefore resetting or managing state. Treattccutil resetas test-state removal, never grant or general status inspection. - Reproduce the original operation after the required lifecycle transition. Record the status/preflight result, actual operation result, responsible executable, mutations and approvals, reset/rollback path, and remaining uncertainty.
- Use the minimum fixture in
references/validation-fixtures.md. Obtain explicit approval immediately before any visible prompt, System Settings change, logout, or live-host permission mutation.
What ships with it
6 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.
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.
- yesterday First seen · 71 lines · 54 tokens per session scan A 5f2512698db1
macos-privacy-permissions-workflow is a skill published in the GitHub repository gaelic-ghost/socket (7 stars, last pushed 9d ago), licensed Apache-2.0. It adds 54 tokens to every session and 1,209 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 2026-09-03.
Other skills, from other repositories
pipeline
Use when the user wants a feature idea taken end-to-end in one autonomous run — phrases like "run the whole pipeline", "take this feature from idea to finished branch", "brainstorm then build it autonomously", "do everything from idea to merged", "implement all phases without stopping". Triggers when they want…
craft
Use when a product idea is still vague and needs to become a clear definition of what to build — "let's craft an app like X", "help me define what I actually want", "clarify this idea before we plan it". Also use before planning or implementation when requirements, UX, domain behaviour, or technical preferences have…
financial-statement-analysis
Reads a set of financial statements and establishes what changed and why — fluctuation analysis against prior period and against budget, profitability, liquidity, solvency and efficiency ratios, benchmarking, and the non-GAAP measures presented alongside them. Use this to interpret results, review a counterparty's or…
youtube-producer
Plans, packages, and scripts long-form video for retention and channel growth — idea selection, titles and thumbnails, script structure, and diagnosing why a video or channel underperforms. Use this for video ideas, packaging, scripting, a retention teardown, or channel strategy — including when someone describes a…
scenario-planning
Plans under genuine uncertainty — building scenarios, identifying which assumptions are load-bearing, setting early-warning indicators, and stress-testing a plan against futures rather than forecasting one. Use this when a decision depends on something unknowable, when a plan assumes conditions that may not hold…
ai-ml-governance
Governs models and AI systems in production — intended use, evaluation, monitoring, human oversight, documentation, and the decision to deploy or retire. Use this before deploying a model or AI feature, when defining evaluation criteria, when a model's behavior has drifted, when assessing AI risk or regulatory…