frontier-plan-opencode-executor

Community

Safely execute frontier plans inside OpenCode.

Authoralexdcd
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Frontier AI plans often overspec or diverge from the real repository. This skill ensures that large implementation plans are reality-checked and broken into safe, verifiable steps before editing code, reducing destructive changes and dead-end work.

Core Features & Use Cases

  • Reality-checks against the repository before edits to confirm file paths, libraries, and APIs exist.
  • Stepwise execution with incremental verification and diff inspection to prevent drift.
  • Safety rules that block dangerous operations unless explicitly approved.

Quick Start

Provide a multi-step frontier plan and instruct the agent to execute it step by step with real-repo reality checks.

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: frontier-plan-opencode-executor
Download link: https://github.com/alexdcd/Mafia-Claude-Skills/archive/main.zip#frontier-plan-opencode-executor

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 510,000+ vetted skills library on demand.