edit-agent

Create and modify Claude Code sub-agents with YAML frontmatter and tool restrictions.

19|5|Updated Jan 26, 2026
One-click install
npx skills add https://github.com/digital-stoic-org/agent-skills --skill edit-agent
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: edit-agent
Source: https://github.com/digital-stoic-org/agent-skills/tree/main/dstoic/skills/edit-agent
Command: npx skills add https://github.com/digital-stoic-org/agent-skills --skill edit-agent

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Creates and modifies Claude Code sub-agents following best practices. Use when user requests creating, updating, modifying, improving, or editing sub-agents. Triggers include "create/make/new agent", "sub-agent for X", file paths with /agents/, "update/modify/improve agent Y". Handles agent structure, YAML frontmatter (name, description, tools, model), system prompt design, tool restrictions (minimal permissions), isolated context benefits. Delegates to edit-tool orchestrator if uncertain about tool type (agent vs skill vs command vs script).

Core Features & Use Cases

  • Provides a structured template and validation process for editing or creating Claude Code sub-agents.
  • Enforces frontmatter conventions, model selection, and tool scoping to maintain isolation and safety.
  • Use cases: updating an existing sub-agent, creating a new sub-agent, adjusting tool permissions, or refining system prompts for consistency.

Quick Start

Provide a detailed plan to initiate editing or creating a sub-agent, including required details such as purpose, triggers, and tools.

Frequently Asked Questions about edit-agent

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

FAQPage Schema
How do I create a Claude Code sub-agent with the correct YAML frontmatter?

A Claude Code sub-agent requires YAML frontmatter with name, description, tools, and model fields. This structure enforces isolated context and minimal tool permissions, ensuring the agent operates safely within your workflow configuration.

What is the best way to update an existing sub-agent's system prompt and tools?

Updating a sub-agent involves refining the system prompt for consistency and adjusting tool restrictions to maintain minimal permissions. This ensures the agent maintains isolated context while following best practices for configuration modifications.

When do I need to use sub-agents instead of scripts or commands in Claude workflows?

Sub-agents are needed when you require isolated context and specific tool scoping within Claude workflows. If you are uncertain whether to use an agent, skill, command, or script, the tool type should be delegated to the edit-tool orchestrator for clarification.

How do I set up tool permissions for a new Claude Code sub-agent?

Setting up tool permissions involves defining minimal tool access in the YAML frontmatter's tools field. This restricts the agent's capabilities to only what is necessary, maintaining safety and isolated context within the Claude environment.

Does Claude Code sub-agent creation require a specific model in the frontmatter?

Yes, sub-agent creation requires specifying a model in the YAML frontmatter. Enforcing model selection alongside name, description, and tools ensures the sub-agent configuration is complete and follows established best practices.

Why are my Claude Code sub-agents not maintaining isolated context?

Sub-agents lose isolated context if the YAML frontmatter lacks proper structure or tool scoping. Enforcing frontmatter conventions for name, description, tools, and model ensures isolation is maintained across the workflow.