From modelharness
Use when deciding whether to spawn subagents — explicit rules for when delegation pays off and when direct work is faster. Opus 4.8 under-delegates by default; these rules correct that.
How this skill is triggered — by the user, by Claude, or both
Slash command
/modelharness:delegation-triggersThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Opus 4.8 is documented to under-reach for subagents. Apply these rules instead of
Opus 4.8 is documented to under-reach for subagents. Apply these rules instead of intuition.
npx claudepluginhub vitaliikapliuk/modelharness --plugin modelharnessPatterns and principles for orchestrating parallel subagent execution: work decomposition (fan-out/fan-in, map-reduce), isolation, result synthesis, and failure handling. Use when a task splits into independent subtasks.
Dispatches parallel subagents for 2+ independent tasks with no shared state. Use when tasks are well-defined and have no sequential dependency.
Guides subagent dispatch decisions: when to delegate vs work inline, structuring delegation prompts, parallel fan-out sizing, and dispatching verifier agents.