recall: One Search Bar Across Every Agent Transcript I've Ever Had
How I built a local SQLite FTS5 index over every Claude Code and Cursor conversation, and a prompt you can hand your own agent to build the same thing.
How I built a local SQLite FTS5 index over every Claude Code and Cursor conversation, and a prompt you can hand your own agent to build the same thing.
A Claude/Cursor skill that turns agent-built diffs, features, and plans into short Sideshow sessions designed so you can actually hold the work in your head.
A portable generator for agent workflows that classify work, force evidence, interview for missing process, and leave better engineering output behind.
Salesforce Field History only tracks what you enable. We already had daily full-object backups in Own — this local toolkit turns them into queryable day-by-day field history.
How /daily and /foreman split Jira sync from agent dispatch, and why a single gitignored map.md file is the only thing that survives between sessions.
A seven-step work loop, four modes, and a PROD → SCRATCH → AGENT_DEV org model that keep ephemeral Cursor agents shipping Salesforce changes without inventing process each run.
A curses network monitor with dual process ladders and braille history — built for walking a phone hotspot around the house looking for a corner that isn't terrible.
A always-on backyard listener that identifies bird calls, keeps a running journal of who visited, and turns your sightings into a personal field guide — no cloud, no subscription.
Reverse-engineering Salesforce's Lightning Classic switcher: the /ltng/switcher URL, referrer encoding, and a bookmarklet that skips the profile menu.
Three Claude Code skills that encode patient data lookup patterns once so I never have to re-explain OpenPhone GSIs or Heidi session schemas again.
A month of shipping for a solo concierge OB practice: medical records forms, fax intelligence, control center outreach, and a phantom-records audit.
How a custom Claude Code skill turns messy conversation-length analysis into branded, print-ready executive summaries — with a design system, component library, and one command to the printer.
A walkthrough of a subtle patient name matching bug in an AI-powered fax processing pipeline — and why a shared first name is never enough to make a match.
Porting a Playwright automation to agent-browser taught me a tight debugging loop: annotate, screenshot, hand to Claude, fix, re-run.
How we turned Heidi Health session data — trapped in a third-party app — into a searchable, embeddable, auditable clinical record system using DynamoDB, Bedrock, and React.
How we untangled a monorepo of local-path submodules, orphan directories, and detached git repos — and pushed everything to GitHub with a single bash script.
A breakdown of the digital services running a private medical practice in 2026.
A technical deep-dive into the custom-built infrastructure for the OBGYN Practice Automation Suite.