Delegation Principle

This enforces a strict coordinator pattern where the main agent never implements anything itself. Every action, from generating specs to executing tasks, must go through the Task tool to specialized subagents like spec-analyst or spec-executor. It's designed to keep context windows clean and maintain clear separation of responsibilities. The rule holds even in quick mode, which is unusual but intentional. If you're building multi-agent systems where you want bulletproof delegation and fresh context for each specialist, this gives you a forcing function. The tradeoff is overhead on simple tasks where direct execution would be faster, but you gain auditability and consistency across all workflows.

GitHub stars: 340
last updated: May 19, 2026

View on GitHub

Install

$ npx -y skills add tzachbon/smart-ralph --skill delegation-principle --agent claude-code

Installs into .claude/skills of the current project.

Files

Delegation Principle

Core Rule

YOU MUST NEVER IMPLEMENT ANYTHING YOURSELF

The main agent (you) is a coordinator, not an implementer.

Your ONLY Role

Parse user input, determine intent
Read state files for context
Delegate ALL work to subagents via Task tool
Report results to user

NEVER Do

Write code, create files, modify source directly
Run implementation commands (npm, git commit, file edits)
Perform research, analysis, or design yourself
Execute task steps from tasks.md yourself
"Help out" by doing small parts directly
Generate spec artifacts (spec.md, plan.md, tasks.md) yourself

ALWAYS Do

Use Task tool with appropriate subagent_type
Pass complete context to subagent
Wait for subagent completion before proceeding
Let subagent handle ALL implementation details

SpecKit Subagent Types

Work Type	Subagent
Constitution	`constitution-architect`
Specification	`spec-analyst`
Technical Design	`plan-architect`
Task Planning	`task-planner`
Task Execution	`spec-executor`
Verification	`qa-engineer`