Every bundle is a self-contained, MIT-licensed artifact extracted from live work across QC, MHG, and Parley. Tap any card to read the full bundle on this site, or grab the source on GitHub.
Pre-work contracts co-signed by builder and evaluator. Eliminates close-enough shipping. 48 contracts shipped.
Blameless postmortems with structural action items. The discipline that makes the same mistake stop happening twice.
The annotated skeleton every Claude Code operator needs before their second week. Three worked examples, one framing essay, and the advice everyone skips: what NOT to put in.
The chief-of-staff + N-specialists scaffold. Routing table, authority levels, and an escalation protocol — the piece everyone skips until it bites them.
13-folder Obsidian template that scales across multiple ventures. The operating system around your AI agents.
Five production-tested Claude Code hooks — session loading, config protection, eval auditing, decision logging, anchor-check cadence. The mechanical enforcement layer your CLAUDE.md rules have been promising.
The bundles above are extracted artifacts. The lessons are the disciplines that produced them. Three tiers, twenty-six lessons, each with a diagnostic prompt, an annotated transcript, a prompt kit, and a homework checklist. All live; all free.
Your first CLAUDE.md, agent.md, skill, brief, document, report, web page.
Sprint contracts, postmortems, memory, hooks, vault-as-OS, agent routing.
Retrofit, real ROI, token discipline, scope creep, multi-venture, training, drift.