coordinate-external-ag…
Coordinate independently operated external agents through durable handoffs. Use when work crosses hosts, sessions, accounts, services, queues, boards, pull…
Contain an active or credible incident across hosts, identities, applications, cloud resources, networks, or data. Use when access, execution, exfiltration, fraud, destruction, or repeated compromise needs authorized interruption.
$ npx -y skills add gaelic-ghost/socket --skill contain-security-incident --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/contain-security-incidentContext preview
The summary Claude sees to decide when to auto-load this skill.
Contain an active or credible incident across hosts, identities, applications, cloud resources, networks, or data. Use when access, execution, exfiltration, fraud, destruction, or repeated compromise needs authorized interruption.
name: contain-security-incident description: Contain an active or credible incident across hosts, identities, applications, cloud resources, networks, or data. Use when access, execution, exfiltration, fraud, destruction, or repeated compromise needs authorized interruption.
Interrupt the validated path of harm with the smallest effective action, then verify the containment. Do not confuse a blocked symptom with eradication or recovery.
Read [references/containment-plan.md](references/containment-plan.md) before making disruptive changes.
1. Confirm incident lead, authority, current scope, harm path, critical services, evidence priorities, and emergency contacts. 2. Model containment choices.
3. Sequence actions.
4. Apply approved changes.
5. Verify containment.
6. Expand scope carefully.
7. Define exit criteria.
Return containment objective, options/tradeoffs, actions/results, verification, residual access, business impact, temporary controls, rollback, and next-phase criteria.
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,…