Use subagent-design

Decompose a task into an orchestrator and subagents

Decompose a task into an orchestrator and subagents — one-mission role cards with typed output contracts, a topology (pipeline / parallel / judge panel) chosen with a reason, context-isolation rationale, and a verification stage that is never a generator.

Reach for it when the user wants to fan work out across multiple agents, design a multi-agent workflow or orchestration, or asks "should this be one agent or several".

Install it

npx skilldrop-cli install subagent-design                 # Claude Code, your user folder
npx skilldrop-cli install subagent-design --project       # Claude Code, this repo
npx skilldrop-cli install subagent-design --ide cursor    # or kiro, codex, antigravity, copilot

It is part of the AI engineering pack: --pack ai-engineering installs it with its neighbours.

Ask for it

Say it the way you would to a colleague. Requests like these route to it:

• "Should this task be one agent or several?"
• "Design a multi-agent workflow to audit all our repos"
• "My agent fan-out produces mush — help me add contracts and verification"
• "Pipeline or parallel for this multi-stage agent job?"

Requests like these belong to a different skill, so it shouldn't answer them:

• "Design the loop with exit criteria and human gates for this automation"
• "Set a token budget for our agent workflows"
• "Run a council review on this architecture decision"

If another skill answers instead, ask for this one by name: "use subagent-design".

Check what you get

A good result:

• The fan-out is justified by one of the three reasons, by name — or the plan says "one agent" and means it.
• Every mission is one sentence with no "and". Two jobs, two cards.
• Every output contract is typed. A reader could write the JSON schema from the card.
• Isolation lines are explicit — each card says what the agent is denied and why.
• The topology has its reason attached, and any barrier names the cross-item dependency that earns it.
• Verification is adversarial and separate — never the generator, never "the orchestrator double-checks".
• The budget line exists — per-agent tier + fleet cap, sourced or tagged.

Use something else when

• Designing the loop that wraps the fan-out (caps, gates, exits) — agent-loop-design
• Setting the spend policy — agent-budget
• Running a multi-perspective review right now — council-review is the panel, ready-made
• Implementing one story — feature-implement-loop

Next

• SKILL.md, the instructions the agent reads
• Its page on the site
• Related: agent-budget, agent-loop-design, council-review, devils-advocate, feature-implement-loop

Edit this page on GitHub · View source