subagent-contract

Standardize delegation between orchestrators and subagents with a universal result contract.

2|Updated Jan 16, 2026
One-click install
npx skills add https://github.com/MysMon/Spec-Workflow-Toolkit --skill subagent-contract
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: subagent-contract
Source: https://github.com/MysMon/Spec-Workflow-Toolkit/tree/main/skills/core/subagent-contract
Command: npx skills add https://github.com/MysMon/Spec-Workflow-Toolkit --skill subagent-contract

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Standardized contracts between orchestrators and subagents reduce miscommunication, enable predictable inputs and outputs, and define clear error handling and result formats for delegation systems.

Core Features & Use Cases

  • Universal result structure for subagent outputs to enable reliable aggregation
  • Blockers reporting and recoverable-error signaling to guide orchestration
  • Pre-submission verification to ensure references and assumptions are valid
  • Aggregation protocol to combine multiple subagent results into a cohesive summary
  • Clear interaction rules to protect context and minimize drift across phases (exploration, design, review, implementation)

Quick Start

To begin, define a task for the orchestrator and return results using the standardized subagent-contract format.

Frequently Asked Questions about subagent-contract

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

FAQPage Schema
How do I standardize communication between an orchestrator and multiple subagents?

You can standardize communication by defining a universal contract that specifies consistent inputs, outputs, and error handling to ensure reliable delegation across exploration, design, review, and implementation phases.

What is the best way to aggregate results from multiple subagents?

Aggregating subagent results requires a standardized protocol that combines universal result structures into a cohesive summary, ensuring consistent inputs and predictable outputs across delegation tasks.

How does error handling work in subagent delegation?

Subagent delegation handles errors through standardized contract mechanisms for blockers reporting and recoverable-error signaling, which guide the orchestrator's response and prevent miscommunication during task execution.

How do I prevent hallucinations and validate file references in subagent outputs?

You prevent hallucinations by applying pre-submission verification and strict file-reference validation defined in the contract, ensuring references and assumptions are valid before returning results to the orchestrator.

Can I use a single contract for subagent tasks across exploration, design, and review phases?

Yes, a single standardized contract applies across exploration, design, review, and implementation phases, defining clear interaction rules that protect context and minimize drift throughout the delegation workflow.

Why do my subagent aggregation results have unpredictable formats and missing context?

Unpredictable aggregation formats occur when subagents lack a universal result structure. Implementing a standardized contract enforces consistent outputs, blockers reporting, and pre-submission verification to ensure reliable aggregation.