Cypherpunk Samurai CypherpunkSamurai

OpenCode Plugins Guide

A comprehensive guide to writing plugins for OpenCode that extend agent behavior with hooks, custom tools, and event handling.

Quick Start

Create a TypeScript file in .opencode/plugin/ (project) or ~/.config/opencode/plugin/ (global)
Export a named plugin function
Restart OpenCode

Warning

I see many people proposing solutions for other platforms (such as Windows or macOS). I cannot verify the authenticity of those methods, and you should not copy, paste, and run code from random people on the internet without first understanding what it does. Ideally, review every line carefully and, even then, run it with caution in a sandboxed environment.

Introduction

I personally experienced slowdowns and issues while using the ja-netfilter agent.

I decided to investigate how JetBrains checks license validity, because despite explicitly configuring JetBrains to work offline, it still attempts to validate licenses.

Here are my findings:

Using Gmail SMTP with Cloudflare Email Routing: Step-by-Step Guide

Learn how to send emails through Gmail SMTP with Cloudflare Email Routing in this comprehensive guide.

Step 1: Enable 2-Factor Authentication

To proceed with this method, ensure that you have enabled two-factor authentication for your Google account. If you haven't done so already, you can follow the link to set it up → Enable 2FA in your Google account.

	"""
	Dynamic NanoGPT Adder: 130 params + 0 buffers

	transformer.wte.A [10, 1] = 10
	transformer.wte.B [1, 4] = 4
	transformer.h.0.attn.c_attn.weight [12, 4] = 48
	transformer.h.0.attn.c_proj.weight [4, 4] = 16
	transformer.h.0.mlp.c_fc.weight [4, 4] = 16
	transformer.h.0.mlp.c_fc.bias [4] = 4
	transformer.h.0.mlp.c_proj.u [4, 1] = 4

	"""190-param nanoGPT that adds any two 10-digit numbers. All weights hand-coded."""
	import math
	from dataclasses import dataclass
	import torch, torch.nn as nn
	from torch.nn import functional as F

	# === NanoGPT (from github.com/karpathy/nanoGPT/blob/master/model.py) ===
	# Modifications: sinusoidal PE buffer, configurable mlp_hidden, c_fc bias always on

	class CausalSelfAttention(nn.Module):

	Always follow the instructions in plan.md. When I say "go", find the next unmarked test in plan.md, implement the test, then implement only enough code to make that test pass.

	# ROLE AND EXPERTISE

	You are a senior software engineer who follows Kent Beck's Test-Driven Development (TDD) and Tidy First principles. Your purpose is to guide development following these methodologies precisely.

	# CORE DEVELOPMENT PRINCIPLES

	- Always follow the TDD cycle: Red → Green → Refactor
	- Write the simplest failing test first

	You are Manus, an AI agent created by the Manus team.

	You excel at the following tasks:
	1. Information gathering, fact-checking, and documentation
	2. Data processing, analysis, and visualization
	3. Writing multi-chapter articles and in-depth research reports
	4. Creating websites, applications, and tools
	5. Using programming to solve various problems beyond development
	6. Various tasks that can be accomplished using computers and the internet

	# train_grpo.py
	#
	# See https://github.com/willccbb/verifiers for ongoing developments
	#
	"""
	citation:

	@misc{brown2025grpodemo,
	title={Granular Format Rewards for Eliciting Mathematical Reasoning Capabilities in Small Language Models},
	author={Brown, William},

	import argparse
	import random
	import sys

	from transformers import AutoModelForCausalLM, AutoTokenizer, DynamicCache
	import torch

	parser = argparse.ArgumentParser()
	parser.add_argument("question", type=str)
	parser.add_argument(