mini-swarm-onboard

name	mini-swarm-onboard
description	Quick CGG onboarding through governed triangulation — three agents debate which CGG mechanic matters most. CENTROID: quick governed-triangulation onboarding demonstration IS: - single-arena three-agent debate with narrator commentary - live CGG mechanic exposure compressed to ~10 minutes - dry-run surfacing of arena spec and task DAG before execution IS NOT: collapse_zones: - production arena (demo-scoped; never produces real governance pressure or CogPRs) - doctrine author (demonstrates existing mechanics; never modifies them) - extended course (single arena only — the multi-chapter course is /homeskillet-academy) - runtime reshape surface (narrates agent spawns; never restructures runtime) sibling_overlaps: - /homeskillet-academy (deeper multi-chapter course) - /stage (real arena orchestration — mini-swarm is a demo variant) WHEN: - on first-exposure demo within a ~10 minute window - when a visitor asks "what does governed triangulation look like" - when a fast CGG pitch without full academy scaffold is desired NOT WHEN: - as a production arena (use /stage) - for extended pedagogy across multiple mechanics (use /homeskillet-academy) - without CGG runtime surfaces installed (pre-flight will refuse) RELATES TO: - /homeskillet-academy (extended course — mini-swarm is the trailer; academy is the full screening) - /stage (real arena orchestration — mini-swarm is the demo; /stage carries the production weight) - /init-governance (install prereq — runtime must be bootstrapped before mini-swarm can run) ARGS: stance: dispatch off_envelope: proceed-with-note # off_envelope rationale: /mini-swarm-onboard's default is "full narrated run." # Undeclared-arg most commonly means "run the default demo" rather than caller # confusion — proceed-with-note preserves demo flow. core_dispatch_rays: - "" → full run with narration gates - "--quick" → compressed narration (single-line summaries) - "--dry-run" → print arena spec and task DAG, then exit secondary_modulation_axes: - pacing: guided | rapid
tools	Read, Grep, Glob, Agent, Bash
trigger	/mini-swarm-onboard

/mini-swarm-onboard — Learn CGG by Watching Governance in Action

Three agents debate "Which CGG mechanic is most valuable?" while a narrator explains what is happening at each stage. The user learns governed triangulation by observation, not instruction.

Invocation

• /mini-swarm-onboard — full run with narration gates
• /mini-swarm-onboard --quick — compressed narration (single-line summaries)
• /mini-swarm-onboard --dry-run — print the arena spec and exit

Pre-flight Checks

Before executing, verify:

1. CGG skills directory exists: check for cgg-runtime/skills/ relative to the zone root
2. CGG agents directory exists: check for cgg-runtime/agents/ relative to the zone root
3. Audit-logs directory exists: check for audit-logs/ at the zone root (create audit-logs/arenas/pressure-reports/ if missing)
4. Stage directory exists: check for stage/shows/ at the zone root (create if missing)
5. Template exists: verify stage/templates/arenas/mini-swarm-onboard/ contains spec.md, tasks.yaml, scoring.yaml, prompt.txt

If any check fails, report what is missing and suggest running /init-governance or /init-gun.

Execution Steps

Step 1: Pre-flight

Run the pre-flight checks above. Report status to user:

Mini-Swarm Onboard — pre-flight
  CGG skills:    OK
  CGG agents:    OK
  audit-logs:    OK
  stage dir:     OK
  template:      OK

Step 2: Dry-run gate

If --dry-run is set:

1. Read the arena spec from stage/templates/arenas/mini-swarm-onboard/spec.md
2. Read the task DAG from stage/templates/arenas/mini-swarm-onboard/tasks.yaml
3. Print both to the user
4. Exit

Step 3: Generate show ID and directory

1. Generate show ID: mini-swarm-onboard-YYYYMMDDTHHMMSS (use current timestamp)
2. Create show directory: