action-boundary

Community

Enforce agent boundaries and scope.

Authorbuchananwill
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This skill enforces mandated boundaries for agents in multi-agent teams, preventing scope creep and cross-concern contamination by ensuring actions stay within defined mandates and that read-only roles are respected.

Core Features & Use Cases

  • Declare your boundary. Your agent definition states what you do and do not do. Honour it exactly.
  • Stay in your lane. If you notice an issue outside your mandate, do not report it. A separate agent with that mandate will catch it.
  • Read-only means read-only. Reviewers or planners never modify files.
  • Follow the plan, not instincts. Do not add features outside the plan; note any uncertainty.
  • Flag, don't fix. If something is outside your scope, mention it in a Notes section instead of taking action.

Quick Start

Declare your boundary in the agent definition and follow the plan exactly, reporting any boundary violations rather than acting outside your mandate.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: action-boundary
Download link: https://github.com/buchananwill/ue-claude-scaffold/archive/main.zip#action-boundary

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.