Agent-first customer support platform with human-in-the-loop for Skill Recordings products.
This is the overview and index. Start here. Detailed implementation instructions live in phase and reference docs.
| # Installing MCP Agent Mail on macOS (Python 3.14 + launchd) | |
| A chronicle of the fuckery involved in getting [mcp_agent_mail](https://github.com/Dicklesworthstone/mcp_agent_mail) running as a launchd service on macOS with Python 3.14. | |
| ## The Goal | |
| Run Agent Mail as a persistent service for multi-agent beads coordination. Prevents collision when multiple AI agents (Claude, Cursor, OpenCode, etc.) work the same repo. | |
| ## The Fuckery |
Joel Hooks - co-founder of egghead.io, education at Vercel, builds badass courses via Skill Recordings (Total TypeScript, Pro Tailwind). Deep background in bootstrapping, systems thinking, and developer education. Lives in the Next.js/React ecosystem daily - RSC, server components, suspense, streaming, caching. Skip the tutorials.
<tool_preferences>
always use beads bd for planning and task management
Reach for tools in this order:
This meal plan's structure optimizes your body's natural rhythms and hormonal patterns throughout the day. The early breakfast stabilizes cortisol and starts your metabolism, while the pre/post workout nutrition maximizes training adaptations and muscle protein synthesis. Strategic carb timing around workouts enhances performance and recovery, while the protein distribution supports continuous muscle maintenance. The earlier dinner and light evening snack align with natural insulin sensitivity patterns and support quality sleep. This consistent approach helps optimize testosterone production, manage cortisol, regulate blood sugar, and enhance overall metabolic flexibility, leading to better body composition and sustained energy levels.
| import dotenv from "dotenv"; | |
| import Anthropic from "@anthropic-ai/sdk"; | |
| import { setTimeout } from "timers/promises"; | |
| import * as fs from "fs/promises"; | |
| import { getSession } from "./neo4j"; | |
| // Configuration and Initialization | |
| dotenv.config(); | |
| const anthropic = new Anthropic({ |
| import {publicProcedure, router} from '@skillrecordings/skill-lesson' | |
| import {isEmpty} from 'lodash' | |
| import {getToken} from 'next-auth/jwt' | |
| import {getSubscriberFromCookie} from '@skillrecordings/skill-lesson/utils/ck-subscriber-from-cookie' | |
| export const offerRouter = router({ | |
| getNextOffer: publicProcedure.query(async ({ctx}) => { | |
| const token = await getToken({req: ctx.req}) | |
| const subscriber = await getSubscriberFromCookie(ctx.req) |
| // Name: ck stats for site | |
| // Snippet: ;ck | |
| import "@johnlindquist/kit" | |
| const sites = [ | |
| { | |
| name: "Some Account", | |
| ck_secret: await env("SOME_ACCOUNT_CK_SECRET"), | |
| } |