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 gaelic-ghost/socket --skill inspect-macos-persistencegit 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/inspect-macos-persistence)<a href="https://agentmods.dev/skills/gaelic-ghost/socket/inspect-macos-persistence"><img src="https://agentmods.dev/badge/skills/gaelic-ghost/socket/inspect-macos-persistence/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/gaelic-ghost/socket/inspect-macos-persistence"><img src="https://agentmods.dev/badge/skills/gaelic-ghost/socket/inspect-macos-persistence.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 | $0.00048 | $0.00481 |
| Opus 5.5 | $0.00019 | $0.00192 |
| Sonnet 5.5 | $0.00010 | $0.00096 |
| Haiku 4.5 | $0.00005 | $0.00048 |
Grade A, and why
inspect-macos-persistence 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 1mo 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 — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Inspect macOS Persistence
Overview
Inventory registered and file-backed persistence, then correlate it with loaded runtime state and installation history. Read files and official service state; never manage launchd by editing its internal state.
Read references/macos-persistence-surfaces.md for prioritized surfaces and evidence fields.
Workflow
- Record host/build, user domains, event timeline, and the suspected executable or label.
- Record whether the system is a physical Mac or macOS guest, plus the guest's restore image/build, VM tool/framework, integrations, baseline/reset state, and known virtualization artifacts.
- Inventory user-visible registrations.
- Review Login Items and background-item state, profiles, extensions, browser add-ons, and app-managed helpers.
- Inventory launch services.
- Inspect user/system LaunchAgents and LaunchDaemons as files and query service state through
launchctlread operations. - Record label, domain, program/arguments, working directory, environment, sockets, keep-alive/start conditions, owner/permissions, signer, and loaded PID/status.
- Inspect user/system LaunchAgents and LaunchDaemons as files and query service state through
- Inspect adjacent persistence.
- Review shell startup files, scheduled jobs, package receipts/scripts, privileged helpers, system/network extensions, authorization plugins, and current platform-specific surfaces justified by evidence.
- Correlate provenance and runtime.
- Identify parent installer/app, creation/change time, signature/notarization, executable hash, running process ancestry, files, network, and logs.
- Classify each item.
- Expected, suspicious, confirmed malicious, disabled/orphaned, or unresolved; explain evidence and impact.
- Keep guest-observed persistence distinct from physical-host proof when anti-VM, hardware, recoveryOS, kernel/system-extension, or device behavior may differ.
- Preserve before containment.
- Record files and service state before using official
launchctl bootoutor app/uninstaller paths in the containment workflow.
- Record files and service state before using official
What ships with it
2 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.
- 1mo ago First seen · 36 lines · 48 tokens per session scan A e5e462e13e33
inspect-macos-persistence is a skill published in the GitHub repository gaelic-ghost/socket (7 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 48 tokens to every session and 481 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 2026-09-03.
Other skills, from other repositories
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…
pipeline
Use when the user asks to take a substantial feature from an initial idea through implementation in one mostly autonomous run.
turbo-pipeline
Use when the user wants a feature built end to end after answering one round of questions and then being left alone — "turbo", "ask me once, then just build it", "I'll answer up front, don't come back to me", "decide the rest yourself". Not for a run that wants a spec approval and no tests (superb:fast-pipeline), one…
pipeline-auto
Use when the user wants a substantial feature taken from idea through implementation in one run with as little interruption as possible ("just build it", "don't keep asking me"), or when controlling such a run and a worker question, quorum responses, the drift budget, a human decision, a review class or a completeness…
bug-fix
Use when a bug, regression, or unexpected behaviour is reported and the user wants it fixed end to end — "why is X broken", "this stopped working after Y", "fix this crash". Also use when a symptom is known but its cause is not. Not for building new behaviour, and not for a change whose cause is already proven.
fast-pipeline
Use when the user wants a feature built quickly with low token cost and few interruptions, approves a spec once, and says no automated tests should be written because they will test it manually — "fast pipeline", "go fast, no tests, I'll test it myself", "don't keep asking me". Not for a run that should write or keep…