bioshazard

Protected Core Architecture for an Effect React SPA

Goal

Build the React SPA so that AI coding agents can change implementation code often without changing product rules by accident.

Separate stable product rules from replaceable implementation code.

Treat changes to the stable part as exceptional.

bioshazard

Here is a shorter version that assumes the reader knows basic software engineering, but not DDD, Effect, XState, or TLA+.

Building Safer Agentic Software with Executable Domain Rules

Purpose

This design uses the application’s own rules to constrain both the running software and any AI agent that changes it.

The core idea is:

bioshazard

Code Quality Skill — React SPA Agent Review

Purpose

This skill instructs an agent how to evaluate a React SPA codebase with the judgment of a seasoned engineer. It defines what to look for, how to look for it, what representation to use, and where automation has hard limits.

---

Representation First

bioshazard

Thinking Notation Framework

Capture reasoning durably, navigate it at any altitude, communicate it without synthesis overhead.

---

Core Distinction: Thinking vs. Work

Maintain two separate systems.

bioshazard

ollama rm active-big:latest
ollama create active-big -f <(echo FROM qwen3:30b-a3b)

bioshazard

// index.ts

import { $ } from "bun";

const token = process.env.BEARER_TOKEN;

if (!token) {
  throw new Error("Missing BEARER_TOKEN environment variable");
}

bioshazard

git config --global alias.nb '!f() { git fetch origin && git checkout -b "$1" origin/${2:-master} --no-track; }; f'
git config --global --type bool push.autoSetupRemote true

bioshazard

#!/bin/bash

# MCPO CLI - Efficient MCP OpenAPI Proxy Client
# Usage: ./mcpo.sh <command> [args...]

set -e

# Configuration
MCPO_HOST="${MCPO_HOST:-http://localhost:8000}"
MCPO_TOKEN="${MCPO_TOKEN:-supersecret}"

bioshazard

import os
import re
from typing import Callable, Any
from youtube_transcript_api import YouTubeTranscriptApi
from youtube_transcript_api.formatters import TextFormatter

class EventEmitter:
    def __init__(self, event_emitter: Callable[[dict], Any] = None):
        self.event_emitter = event_emitter

bioshazard

INPUT=$1

# TY https://github.com/paulpaul999/vr-video-notes/blob/main/vr-to-flat/README.md
ffmpeg -i $INPUT -filter_complex "
[0:v]crop=iw/2:ih:0:0[left];
[0:v]crop=iw/2:ih:iw/2:0[right];
[left]v360=input=hequirect:output=flat:d_fov=125:w=1920:h=1080:pitch=0[flattened_left];
[right]v360=input=hequirect:output=flat:d_fov=125:w=1920:h=1080:pitch=0[flattened_right]
" \
-map "[flattened_left]" -c:v libx265 -crf 18 -pix_fmt yuv420p flattened_left.mp4 \