subagent-guide
CommunityCoordinate subagents safely with guided prompts.
Software Engineering#subagents#prompting#agent-coordination#zero-context#sanity-check#worktree-isolation
AuthorMoonBoi9001
Version1.0.0
Installs0
System Documentation
What problem does it solve?
Subagents start with zero context about the current project, problem, or conversation. They cannot ask clarifying questions — they work with what you provide. The quality of their output directly correlates with the completeness of your prompt.
Core Features & Use Cases
- Critical Context Principle: prompts should include all necessary information to operate without asking for clarifications.
- Critical Thinking Requirement: prompts must include sanity checks, domain awareness, and guardrails to prevent flawed implementations.
- Worktree Isolation guidance: use isolation: "worktree" when launching multiple agents against the same repository.
- Model Selection and Coding Standards: follow the latest Opus model guidance and CODING-STANDARDS.md for implementation and safety.
Quick Start
Describe the task, constraints, and success criteria in a single, comprehensive prompt before delegating any work to a subagent.
Dependency Matrix
Required Modules
None requiredComponents
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: subagent-guide Download link: https://github.com/MoonBoi9001/claude-code-cli-tools/archive/main.zip#subagent-guide Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.