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-runtime-activitygit 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-runtime-activity)<a href="https://agentmods.dev/skills/gaelic-ghost/socket/inspect-macos-runtime-activity"><img src="https://agentmods.dev/badge/skills/gaelic-ghost/socket/inspect-macos-runtime-activity/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-runtime-activity"><img src="https://agentmods.dev/badge/skills/gaelic-ghost/socket/inspect-macos-runtime-activity.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 | $0.00054 | $0.00546 |
| Opus 5.5 | $0.00022 | $0.00218 |
| Sonnet 5.5 | $0.00011 | $0.00109 |
| Haiku 4.5 | $0.00005 | $0.00055 |
Grade A, and why
inspect-macos-runtime-activity 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 — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Inspect macOS Runtime Activity
Overview
Build a time-correlated view of what ran, what changed, and what communicated. Prefer focused native observations and existing telemetry over installing a broad privileged monitor on an affected host.
Read references/macos-runtime-evidence.md for telemetry sources and permission boundaries.
Workflow
- Fix host/build, user/session, time window, process/artifact identity, and reported symptom.
- Label every observation as physical-host, affected-host, or macOS-guest evidence. For a guest, record VM tool/framework, virtual hardware, restore-image/build, shares/devices/network, baseline/reset state, and virtualization artifacts that may alter behavior.
- Capture current process context.
- Record PID, executable path/hash/signature, user, parent/ancestry, arguments, environment when authorized, start time, code state, and deleted/replaced executable clues.
- Correlate files and registrations.
- Record open files, working directory, mapped images, created/modified paths, quarantine/provenance, persistence registrations, and permission failures.
- Correlate network behavior.
- Record process-to-socket mapping, local/remote endpoints, DNS, protocol clues, timing, and whether a connection completed.
- Inspect focused logs/events.
- Query relevant unified logs and existing Endpoint Security/XProtect/Gatekeeper evidence for the narrow time window.
- Record Full Disk Access, root, Endpoint Security entitlement, or other permissions required and what absence hides.
- Treat missing collection permission or unavailable event types as a telemetry gap, not evidence that the behavior did not occur. Route app-facing permission implementation to
macos-privacy-permissions-workflowand exact private-control interpretation toresearch-macos-security-control.
- Build a timeline.
- Separate user action, launch, child processes, file changes, prompts, network, persistence, detection, and termination.
- Assess behavior and gaps.
- Route binary internals, dynamic reproduction, containment, or hunting as needed.
- State anti-VM, hardware, Secure Enclave, recoveryOS, kernel/system-extension, and device-access limitations before treating guest evidence as physical-Mac proof.
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 · 37 lines · 54 tokens per session scan A 9f17584294ad
inspect-macos-runtime-activity is a skill published in the GitHub repository gaelic-ghost/socket (7 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 54 tokens to every session and 546 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
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.
bug-investigate
Use when someone wants to know WHY something is broken and has not asked for it to be fixed — "why is this happening", "what's causing this error", "find out what's wrong", "diagnose this before we decide". Also use before committing to a fix, when the cause is unknown and the decision depends on it. Not for fixing …
operating-cadence
Designs the rhythm an organization runs on — which reviews happen weekly, monthly and quarterly, what each one decides, who owns the numbers presented, and how a signal at the front line reaches the people who can act on it. Use this to set up a management operating system, fix a meeting calendar that produces no…
serena
Serena code intelligence — LSP-powered symbol navigation, diagnostics, and targeted code surgery. Activate before complex refactors, cross-file analysis, or when graph tools need symbol-level depth.
diagnose
Structured 6-phase debugging. Build feedback loop first, reproduce deterministically, hypothesize with ranked falsifiable theories, instrument one variable at a time, fix with regression test, cleanup. Use when a bug exists, tests fail unexpectedly, or behavior is wrong and cause is unknown.
fix
Plan-aware auto-fix loop after coding. Runs tests, lint, format, and graph checks. Updates plan task status. Use after execute/tdd.