skills.rest
sandgardenhq
sandgardenhqOFFICIAL
Explore all skills by this author →
GitHub

create-opencode-agents

Create specialized OpenCode agents with custom prompts, models, tools, and permissions.

130|8|Updated Jan 23, 2026
Search Tags:#security#agent#configuration#code-review#opencode#custom
One-click install
npx skills add https://github.com/sandgardenhq/sgai --skill create-opencode-agents
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: create-opencode-agents
Source: https://github.com/sandgardenhq/sgai/tree/main/cmd/sgai/skel/.sgai/skills/meta/create-opencode-agents
Command: npx skills add https://github.com/sandgardenhq/sgai --skill create-opencode-agents

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Projects often require specialized AI agents for tasks such as security auditing, code review, planning, or documentation, but the built‑in agents are generic and lack granular tool restrictions, leading to safety concerns and inefficient workflows.

Core Features & Use Cases

  • Purpose Definition: Clearly state the agent’s role and when it should be invoked.
  • Custom Configuration: Choose model, temperature, tools, and permissions tailored to the task.
  • Safety Controls: Restrict or deny dangerous tools (e.g., write, bash) for audit‑focused agents.
  • Use Cases: Security audit agents, code‑review assistants, planning sub‑agents, and documentation generators that need task‑specific prompts and limited tool access.

Quick Start

Ask the skill to create an OpenCode agent for security auditing with the appropriate configuration.

Frequently Asked Questions about create-opencode-agents

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

FAQPage Schema
How do I create custom OpenCode agents for security audits?▼

You can configure custom OpenCode agents for security audits by defining their purpose, selecting a model, and restricting dangerous tools like write and bash. This enforces safety controls and task-specific behavior for focused security auditing.

What are custom OpenCode agents used for?▼

Custom OpenCode agents are used for security auditing, code review, planning, and documentation workflows. They provide custom prompts, models, tools, and permissions when built-in generic agents lack granular tool restrictions.

Can I restrict tool permissions for code review agents in OpenCode?▼

Yes, you can restrict or deny dangerous tools such as write and bash when configuring OpenCode agents. This ensures audit-focused agents and code review assistants operate with limited tool access for improved safety.

When should I use a custom OpenCode agent instead of built-in agents?▼

Use a custom OpenCode agent when built-in agents are insufficient for security audits, code reviews, planning, or documentation workflows and you need granular tool restrictions to enforce safety and task-specific behavior.

How do I configure model and temperature settings for OpenCode planning agents?▼

Configure OpenCode planning agents by selecting a model, setting the temperature, and choosing tailored tools and permissions. This custom configuration enforces task-specific behavior for planning sub-agents.

Related Skills

Explore More Software Engineering Skills→
benjaminwesternbenjaminwestern
3

opencode-dev

Configure AI agents, custom tools, and MCP servers in OpenCode.

Community
Intermediate
dr-codedr-code

release-check

Run pre-release verification checks and write a versioned release assessment report.

Community
Advanced
Weihong-LiuWeihong-Liu
6

security-review

Audit code for OWASP Top 10 vulnerabilities, hardcoded secrets, and unsafe patterns.

Community
Advanced
jpoutrinjpoutrin
14

agent-tools

Configure Claude Code agent tool permissions with path and command restrictions.

Community
Basic