skills.rest
justinlevinedotme
justinlevinedotmeCOMMUNITY
Explore all skills by this author →
GitHub

opencode-agents

Define and configure OpenCode agents with permissions, tools, and mode rules.

7|2|Updated Jan 18, 2026
Search Tags:#automation#permissions#agent#tools#opencode#mode
One-click install
npx skills add https://github.com/justinlevinedotme/jalco-opencode --skill opencode-agents-justinlevinedotme
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: opencode-agents
Source: https://github.com/justinlevinedotme/jalco-opencode/tree/main/opencode/.config/opencode/skills/opencode-agents
Command: npx skills add https://github.com/justinlevinedotme/jalco-opencode --skill opencode-agents-justinlevinedotme

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

OpenCode agent configurations can become inconsistent and unsafe without a clear model for permissions, tools availability, and mode selection. This Skill provides a structured approach to define, validate, and apply agent settings to ensure predictable behavior and security. It also documents patterns for common scenarios such as creating a new agent, restricting access, or choosing between primary and subagent modes.

Core Features & Use Cases

  • Declarative frontmatter schemas for agent definitions (description, mode, model, temperature, maxSteps, permission, tools).
  • Guidelines for agent modes (primary, subagent, all) and safe tool routing.
  • System prompt structure and runtime behavior that enforce permissions and tool access.

Quick Start

Create a subagent named security-reviewer with read-only permissions and restricted bash access.

Frequently Asked Questions about opencode-agents

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

FAQPage Schema
How do I configure OpenCode agents with specific permissions?▼

You configure OpenCode agents by defining a declarative frontmatter schema that includes the agent description, mode, model, temperature, maxSteps, permission rules, and tools to ensure safe automation and predictable behavior.

What is the difference between primary and subagent modes in OpenCode?▼

Primary and subagent modes determine an OpenCode agent's runtime behavior and routing. Selecting between primary, subagent, or all modes dictates how the agent operates, directly affecting tool access and system prompt structure.

How do I restrict tool access for an OpenCode subagent?▼

You restrict tool access for an OpenCode subagent by applying allow and deny permission patterns within the frontmatter schema. This configuration limits the agent to approved tools, enforcing safe routing and predictable behavior.

Can I create a read-only OpenCode agent with restricted bash access?▼

Yes, you can create a read-only OpenCode agent with restricted bash access by combining subagent mode selection, specific permission rules, and tool restrictions within the declarative frontmatter schema.

Why do my OpenCode agent configurations behave inconsistently?▼

OpenCode agent configurations become inconsistent without a clear model for permissions, tool availability, and mode selection. Validating the agent frontmatter schema and applying strict allow and deny rules ensures predictable runtime behavior.

Related Skills

Explore More Software Engineering Skills→
robinebersrobinebers
46

worktree-setup

Generates setup scripts and configurations for AI agent worktrees.

Community
Advanced
mpsuessermpsuesser

opencode-plugin-development

Develop OpenCode plugins that hook events and intercept tool execution.

Community
Advanced
tankpkgtankpkg
1

@tank/opencode-agent-creator

Create specialized OpenCode agents with roles, expertise, and behavioral directives.

Official
Advanced
rauly-1408rauly-1408

dag-permission-validator

Validate child agent permissions against parent security boundaries.

Community
Advanced