sjzsdu

sjzsdu / OpencodePlugins

Public

🤖 OpenCode 插件 - 三省六部多智能体协作系统：将中国古代治理智慧融入 AI 编程助手，自动完成复杂编程任务的规划、审核与执行

40
3
100% credibility
Found Mar 15, 2026 at 40 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
TypeScript
AI Summary

Plugins for the OpenCode AI coding assistant that create teams of AI agents to collaboratively handle software development tasks through structured planning, implementation, testing, and review.

How It Works

1
🔍 Discover AI Teams

You hear about special AI teams that help build software by working together like a crew.

2
📥 Add to Your Assistant

You easily bring these teams into your friendly AI coding helper with a simple setup.

3
Pick Your Team Style
⚡
Quick Squad (Commander)

For everyday coding wins with fast planning, building, checking, and polishing.

🏛️
Grand Council (Emperor)

For thorough reviews, plans, builds, tests, and checks like a royal court.

4
💬 Share Your Task

You chat with the team leader, describing what you want built, and they take charge.

5
🔄 Watch Them Collaborate

The team divides the work, builds pieces, tests fixes, and reviews everything step by step.

6
📊 Check Progress Anytime

You peek at updates or pause if needed, feeling in control as it all comes together.

🎉 Perfect Results Delivered

You get a complete, tested feature with a full report, ready to shine in your project.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 40 to 40 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is OpencodePlugins?

OpencodePlugins turns OpenCode into a multi-agent AI coding assistant by adding two TypeScript plugins: Commander for quick engineering tasks and Emperor for governance-heavy workflows. Commander delegates work to a lead planner, coder, tester, and optional reviewer that auto-classify complexity, run fix loops on test failures, and dispatch subtasks in parallel. Emperor mimics ancient Chinese ministries with 11 agents for triage, recon, planning, review, and execution across architecture, security, testing, and infra—triggered via tools like `cmd_task` or `emperor_create_edict`.

Why is it gaining traction?

It stands out as an opencode github copilot alternative with built-in agent collaboration, unlike single-model tools that hallucinate fixes without verification. Developers notice adaptive pipelines that handle trivial edits directly or scale to complex changes with mandatory reviews and sensitive pattern checks, plus persistent task stores for status tracking. The opencode github integration via plugins makes it a drop-in for opencode github enterprise setups, bypassing issues like "opencode github copilot the requested model is not supported."

Who should use this?

Backend devs building features like JWT auth with RBAC, tests, and CI updates; teams needing security audits on refactors; or solo devs tired of manual planning in opencode github agent flows. Ideal for TypeScript/Node projects where opencodeplugins automate multi-step tasks without opencode github copilot api key hassles.

Verdict

Worth a test run for opencode github mcp users wanting structured AI dev teams—solid docs and tests show promise despite 40 stars and 1.0% credibility signaling early maturity. Pair with opencode github action for production if it fits your workflow.

(198 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.