dpaluy

Source: https://www.youtube.com/watch?v=hYBi2OAakNo

Jason Cohen did online Office Hours with Dmytro Krasun founder of https://screenshotone.com and teach him how to get to the next stage.

dpaluy

# .config/wt.toml
# Rails + Postgres worktree setup with teardown

# --- Setup ---

# Step 1: secrets + env (master.key is gitignored, copy from primary worktree)
[[pre-start]]
master-key = "cp {{ primary_worktree_path }}/config/master.key {{ worktree_path }}/config/master.key"
env = """echo 'PORT={{ branch | hash_port }}
DB_NAME={{ repo }}_dev_{{ branch | sanitize_db }}' > .env"""

dpaluy

@AGENTS.md

Picking the right models for workflows and subagents

Rankings, higher = better. Cost reflects what I actually pay (OpenAI has really generous limits), not list price. Intelligence is how hard a problem you can hand the model unsupervised. Taste covers UI/UX, code quality, API design, and copy.

model	cost	intelligence	taste
gpt-5.5	9	8	5
sonnet-5	5	5	7

dpaluy

<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
<plist version="1.0">
<dict>
    <key>Label</key>
    <string>com.clawbot.llama-server</string>

    <key>ProgramArguments</key>
    <array>
        <string>/opt/homebrew/bin/llama-server</string>

dpaluy

Add those files to bin folder.

Usage:

• bin/worktree-setup [task_id] - Sets up new worktree with isolated test DB
• bin/worktree-teardown - Drops test DB and prints removal command

dpaluy

#!/bin/bash

# Read JSON input
input=$(cat)

# Extract session data
model=$(echo "$input" | jq -r '.model.display_name')
limit=$(echo "$input" | jq -r '.context_window.context_window_size // 200000')
current_dir=$(echo "$input" | jq -r '.workspace.current_dir // "."')
current_usage=$(echo "$input" | jq '.context_window.current_usage')

dpaluy

#!/usr/bin/env ruby
require 'open3'

environment = ARGV[0] || 'default'
creds_path = "config/credentials#{environment == 'default' ? '' : '/' + environment}.yml.enc"

puts "\n=== Merging credentials conflict for #{creds_path} ===\n"

# Extract both versions
`git checkout --ours #{creds_path}`

dpaluy

---

name: majestic:code-story description: Generate documentary-style narrative of repository development history argument-hint: "[--output PATH] [--detail minimal|standard|comprehensive] [--since DATE] [--commits N]" allowed-tools: Bash, Read, Grep, Glob, Task, Write, TodoWrite

You are a documentary filmmaker for code repositories. Your mission is to transform git history into an engaging narrative that tells the story of a project's evolution—its genesis, growth, pivotal moments, and the people who built it.

dpaluy

name	dhh-code-reviewer
description	Use proactively after writing or modifying Ruby/Rails and JavaScript code to review against DHH's exacting standards for code quality, elegance, and idiomatic style as exemplified in Rails and Hotwire codebases
tools	Glob, Grep, Read, WebFetch, TodoWrite, WebSearch, Bash, Write
model	opus
color	red

Purpose

dpaluy

Reflect on Conversation

Analyze our conversation history and suggest improvements to CLAUDE.md based on patterns, feedback, and lessons learned.

Process

1. Review Conversation History
   • Analyze all user feedback and corrections
   • Identify moments where instructions weren't followed

• Note any repeated issues or preferences