delegation

Construct delegation prompts with protocol injection and downstream context blocks.

2|Updated Apr 4, 2026
One-click install
npx skills add https://github.com/Nickalus12/Loom --skill delegation-nickalus12
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: delegation
Source: https://github.com/Nickalus12/Loom/tree/main/claude/skills/delegation
Command: npx skills add https://github.com/Nickalus12/Loom --skill delegation-nickalus12

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Enable reliable orchestration by constructing consistent delegation prompts for subagents, enforcing pre-work protocols and clear handoffs.

Core Features & Use Cases

  • Protocol injection of the base agent protocol and filesystem safety rules to every delegation prompt, ensuring consistent pre-work formatting.
  • Context chain construction and downstream context propagation to maintain alignment across phases.
  • Clear downstream consumer declarations and strict scope boundaries to prevent unsafe modifications and ensure auditable outputs.
  • Structured templates and decision rules to guide subagents through deterministic task execution.

Quick Start

Craft a delegation prompt for Phase 2 that injects the base and safety protocols, includes Phase 1 downstream context, and declares the downstream consumer.

Frequently Asked Questions about delegation

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I ensure subagent delegation prompts include all required context?

Subagent delegation requires constructing consistent delegation prompts that enforce pre-work protocols. You inject base agent protocols and filesystem safety rules, then include all required downstream_context blocks to maintain alignment across phases.

What is a downstream_context block in subagent orchestration?

A downstream_context block is a structured data segment propagated from one phase to the next. It maintains alignment by ensuring subsequent subagents receive the required context from previous phases or explicit placeholders for missing dependencies.

How do I enforce filesystem safety rules when orchestrating subagents?

You enforce filesystem safety by injecting strict scope boundaries and absolute file path requirements into every delegation prompt. This prevents unsafe modifications and ensures all subagent outputs are predictable and auditable.

Can I use structured templates for deterministic subagent task execution?

Yes, structured templates and decision rules guide subagents through deterministic task execution. These templates enforce clear handoffs, downstream consumer declarations, and explicit validation steps for predictable outputs.

What are the limitations of manual context propagation between subagents?

Manual context propagation often leads to missing downstream_context blocks and inconsistent pre-work formatting. Without enforced protocol injection, subagents lose alignment across phases, resulting in unauditable outputs and unsafe file modifications.