agent-conduct

Enforces product isolation and peer quality check rules across squad agents.

2|Updated Jul 24, 2026
One-click install
npx skills add https://github.com/elbruno/ElBruno.MagenticUI --skill agent-conduct-elbruno
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-conduct
Source: https://github.com/elbruno/ElBruno.MagenticUI/tree/main/.squad/templates/skills/agent-conduct
Command: npx skills add https://github.com/elbruno/ElBruno.MagenticUI --skill agent-conduct-elbruno

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? It eliminates duplicated governance rules across agent charters by centralizing two hard rules—Product Isolation and Peer Quality Check—into one shared skill loaded once by every squad agent. ## Core Features & Use Cases - Product Isolation Rule: Prevents tests, CI workflows, and product code from depending on specific squad agent names, requiring generic or parameterized values and fake test fixtures like "test-agent-1". - Peer Quality Check: Requires agents to run test suites for touched files and verify CI health before declaring work done. - Use Case: A squad of 20 agents previously duplicated these rules in every charter; now each agent loads this single shared skill, ensuring consistent governance and easier updates. ## Quick Start Load the agent-conduct skill into your agent's context so it follows the product isolation and peer quality check rules before finishing any work.

Frequently Asked Questions about agent-conduct

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

FAQPage Schema
How do I share rules across multiple AI agents?▼

Centralize duplicated rules into a single shared skill file that every agent loads once, instead of repeating them in each agent charter. This skill demonstrates the pattern with two hard rules extracted from 20 agent charters.

What is the Product Isolation Rule for agent teams?▼

The Product Isolation Rule requires that tests, CI workflows, and product code never depend on specific squad agent names. Use generic parameterized values or obviously-fake fixtures like "test-agent-1" instead of real agent names.

How do agents verify work before finishing tasks?▼

The Peer Quality Check rule requires running the test suite for files you touched and confirming your changes do not contribute to existing CI failures. Agents should also update their history.md when learning from mistakes.

Can tests reference real squad agent names?▼

No, tests must not hardcode real agent names like Flight, EECOM, or FIDO in assertions or CI configs. Use parameterized values or fake fixtures such as "TestBot" to keep product code isolated from any particular squad.

When should this governance skill not be used?▼

This skill only covers two hard rules around naming isolation and test verification. It does not replace full agent charters, domain-specific coding standards, or security review processes, which need their own dedicated guidance.