subagent-rules

Define structured delegation patterns with governance tiers for subagent task control.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/elevanaltd/oa --skill subagent-rules
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: subagent-rules
Source: https://github.com/elevanaltd/oa/tree/main/.claude/skills/subagent-rules
Command: npx skills add https://github.com/elevanaltd/oa --skill subagent-rules

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

AI delegation often lacks proper context, constraints, and governance, leading to suboptimal or uncontrolled subagent behavior. This Skill provides structured patterns to ensure effective and controlled task delegation.

Core Features & Use Cases

  • Tiered Delegation: Offers 3 tiers of delegation (Baseline, Governance, Method) to match task complexity, from simple utilities to multi-phase orchestration.
  • Governance Context Injection: Ensures subagents receive explicit constraints, success criteria, and constitutional clauses, preventing misinterpretation.
  • Anti-Pattern Avoidance: Guides against common delegation mistakes like auto-context injection, over-engineering, or under-engineering, saving debugging time.
  • Use Case: When delegating a complex coding task, use Tier 2 or 3 to ensure the subagent follows TDD, quality gates, and specific Definition of Done (DOD) criteria, leading to higher quality outputs.

Quick Start

Delegate a simple research task to a 'surveyor' agent, ensuring it understands the goal, constraints, and expected deliverable.