메뉴
Show/route/grow/audit the agent squads — the roster, playbooks, active routing, and onboarding config.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Domain Engineering diagnostic — shows what the classifier decides for an objective (CMIS/DAS/profile/skills/mode). Observation-only; never mutates or blocks.
Business-driven methodology entry point — classify (intake), create/advance an Operation or Business work context, and drive the intake → operation → nested-workflow flow. Host-neutral; dry-run by default.
Workflow Navigator — shows the current phase, deliverables, and next commands for an ADR-0057 workflow. Read-only; never mutates state.
Start a focused session on one objective — locks scope, blocks opportunistic refactors.
Deterministic QA gate (ADR-0055) — run the project suite; green + complete acceptance criteria ⇒ qa-approve testing cards into conclusion; red ⇒ report (and qa-reject only attributable failures).
L6 — autonomous feature pipeline. Drives the full squad: design → implement → review → test → log. Checkpoints can be manual or automatic.
| name | source-command-squad |
| description | Show/route/grow/audit the agent squads — the roster, playbooks, active routing, and onboarding config. |
Use this skill when the user asks to run the migrated source command squad.
The sub-agents are organized into squads (see contextkit/squads/README.md):
devteam (constructive — build + review), qa-team (adversarial — verify behaviour),
security-team (AppSec & infrastructure), compliance-team (privacy & laws),
ops-team (CI/CD workflows), design-team (UI/UX design), growth-team (acquisition & retention),
and agent-forge (custom capability packaging).
Act on $ARGUMENTS:
Run node contextkit/tools/scripts/squad.mjs list (agents + briefings) and read contextkit/squads/README.md.
Analyze active git modifications or keyword intent and dynamically map to the correct squad, agent, and playbook:
node contextkit/tools/scripts/squad.mjs route <task-or-path>
It queries the squads-registry to identify the target postures and suggests custom agent scaffolding from agent-forge if third-party libraries (e.g. Stripe, Redis) lack dedicated agent coverage.
Persist the detected posture in the current session ledger after a deliberate routing decision:
node contextkit/tools/scripts/squad.mjs activate <task-or-path>
Use this with the L5 guard after /simulate-impact when a high-risk path requires an active security/compliance/ops posture.
Scaffold the tier-2 rich briefing, then fill it:
node contextkit/tools/scripts/squad.mjs brief <agent>
Add a new squad (e.g. support-team, data-team) and update the manifest roster.
Scaffold the 8 default squad playbooks under contextkit/workflows/playbooks/squads/ based on stack detection:
node contextkit/tools/scripts/squad.mjs generate-playbooks
These are synced/preserved across engine updates (ADR-0054).