coordinate-external-ag…
Coordinate independently operated external agents through durable handoffs. Use when work crosses hosts, sessions, accounts, services, queues, boards, pull…
Correlate suspicious macOS process, file, network, permission, and log activity. Use for unexpected processes, downloads, open files, DNS, privacy prompts, alerts, file mutations, injected executables, and Endpoint Security evidence.
$ npx -y skills add gaelic-ghost/socket --skill inspect-macos-runtime-activity --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/inspect-macos-runtime-activityContext preview
The summary Claude sees to decide when to auto-load this skill.
Correlate suspicious macOS process, file, network, permission, and log activity. Use for unexpected processes, downloads, open files, DNS, privacy prompts, alerts, file mutations, injected executables, and Endpoint Security evidence.
name: inspect-macos-runtime-activity description: Correlate suspicious macOS process, file, network, permission, and log activity. Use for unexpected processes, downloads, open files, DNS, privacy prompts, alerts, file mutations, injected executables, and Endpoint Security evidence.
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](references/macos-runtime-evidence.md) for telemetry sources and permission boundaries.
1. Fix host/build, user/session, time window, process/artifact identity, and reported symptom.
2. Capture current process context.
3. Correlate files and registrations.
4. Correlate network behavior.
5. Inspect focused logs/events.
6. Build a timeline.
7. Assess behavior and gaps.
Return process identity/ancestry, file/network/log timeline, permissions and coverage, observed versus inferred behavior, confidence, and next action.
Stuff for Agents on macOS Promo audio: Socket Codex Marketplace Promo
Coordinate independently operated external agents through durable handoffs. Use when work crosses hosts, sessions, accounts, services, queues, boards, pull…
Assign worktree, branch, write, validation, integration, and cleanup ownership before parallel repository work. Use when a worker will inspect or modify…
Design framework-neutral agent and automation workflows before implementation. Use when choosing between Codex app automations, codex exec, Codex subagents,…
Design evaluation workflows for agent, skill, prompt, and automation behavior before implementation. Use when choosing eval cases, graders, thresholds,…
Design safe n8n workflows with deterministic routing, credentials, idempotency, recovery, local-model checks, drafts, and exact approval gates.
Coordinate bounded worker tasks with a launch envelope, report-back, escalation, and synthesis contract. Use before spawning, resuming, steering, cancelling,…