swarm-design-architecture

Swarm Architecture Design

Overview

Parallel adversarial research. Multiple advocate agents each build the strongest honest case for one technology option while challenging competitors. Produces balanced trade-off analysis that fights the anchoring bias of single-researcher exploration.

Core principle: One researcher anchors on whichever technology they explore first. Advocates who must challenge each other cannot.

This skill extends the groundwork:design-architecture workflow. Steps 1-2 and 5-6 follow that skill exactly. Step 3 (Research) is replaced by the swarm research phase. Step 4 (Iterate Decisions) is enhanced with aggregated adversarial findings.

Pre-flight: Model Recommendation

Your current effort level is {{effort_level}}.

Skip this step silently if effort is high, xhigh, or max (the scale is low < medium < high < xhigh < max, so xhigh and max are already above high) AND you are Opus (1M context). If effort is low or medium (i.e. below high), you MUST show the recommendation prompt — regardless of model. If you are not Opus (1M context), you MUST show the recommendation prompt - regardless of effort level.

Otherwise → use AskUserQuestion:

{
  "questions": [{
    "question": "Do you want to switch? Adversarial prompt design and cross-decision conflict synthesis benefit from deeper reasoning.\n\nTo switch: cancel, run `/model opus[1m]` and `/effort high`, then re-invoke this skill.",
    "header": "Recommended: Opus (1M context) at high effort",
    "options": [
      { "label": "Continue" },
      { "label": "Cancel — I'll switch first" }
    ],
    "multiSelect": false
  }]
}

If the user selects "Cancel — I'll switch first": output the switching commands above and stop. Do not proceed with the skill.

When to Use

Use swarm architecture instead of standard architecture when:

• Multiple viable technology options exist for 2+ decision areas
• Competing NFRs make trade-offs non-obvious
• Previous architecture attempts anchored on the first option explored
• The team wants evidence-backed comparison before choosing