Curriculum · 26 lessons across 3 tiers

A method library, not a content library.

Each lesson teaches one diagnostic move, gives you the prompt language to use it, walks through a real annotated transcript, and ends with a 30-minute exercise on your own project. No theory. Built from the live work across QC, MHG, and Parley.

Tier 2 · for the practitioner

Operating

The disciplines: contracts, postmortems, hooks, memory. The 13-folder vault. Routing six agents across multiple ventures.

  1. O01

    When your agent says "done" — turning claims into evidence

    ● live

    The diagnostic that catches every kind of "finished but not really." One prompt, three patterns, one habit.

    15 min read · 30 min apply↳ bundle: sprint-contract-system↳ prereq: Foundations 01-04
  2. O02

    Postmortem discipline — when something breaks anyway

    ● live

    The substitution test for structural causes. Action items that ship. The close-out protocol.

    15 min read · 45 min apply↳ bundle: postmortem-discipline↳ prereq: Operating 01
  3. O03

    Memory architecture — what to remember, what to throw away

    ● live

    MEMORY.md as an index. Four memory types. The single rule that prevents bloat.

    12 min read · 20 min apply↳ prereq: Operating 01
  4. O04

    Hooks — mechanical enforcement vs. promised future discipline

    ● live

    SessionStart, PreToolUse, PostToolUse. Why hooks beat "agents must remember to."

    18 min read · 60 min apply↳ prereq: Operating 01
  5. O05

    Mid-sprint scope changes — the amendment protocol

    ● live

    How to add work to a contract without losing rigor. When a re-sign is required.

    10 min read · 15 min apply↳ prereq: Operating 01
  6. O06

    Cross-agent handoffs — when one agent's done is another agent's begin

    ● live

    Communication protocols, delegation templates, authority boundaries.

    14 min read · 30 min apply↳ prereq: Operating 02
  7. O07

    Vault as operating system — the 13-folder convention

    ● live

    Numbered folders. Single source of truth per concern. Why a markdown vault beats a SaaS stack.

    20 min read · 60 min apply↳ bundle: vault-structure
  8. O08

    Wiki synthesis — turning chat history into queryable knowledge

    ● live

    Karpathy-style ingest. Page format, index pattern, lint cadence.

    15 min read · 45 min apply↳ prereq: Operating 07
  9. O09

    Decision logs — ADRs that ship

    ● live

    Frontmatter, options table, revisit conditions. Future-you reads this.

    10 min read · 20 min apply
  10. O10

    The routing model — one chief of staff, N specialists

    ● live

    Why six is right and fourteen is too many. Authority levels, trigger words, escalation.

    14 min read · 30 min apply
Tier 3 · for the operator-grade

Expert

Retrofit a project that's already a mess. Real ROI, token spend, scope creep, multi-venture portfolio operations.

  1. E01

    Retrofit — applying structure to a project that's already a mess

    ● live

    Where to start when there's no CLAUDE.md, no contracts, no postmortems, and the deadline was yesterday.

    25 min read · several hours apply
  2. E02

    Real ROI from agent hierarchies

    ● live

    When 6 agents are right, when 1 is enough, when more agents make you slower. With numbers.

    20 min read · 60 min audit
  3. E03

    Tracking token spend and identifying waste

    ● live

    Cache health ratios. Tokens per shipped artifact. Idle days vs. uncommitted-output days.

    20 min read · 30 min apply
  4. E04

    Accountability — contracts + postmortems + gates as one system

    ● live

    How the three disciplines compound. Where each catches the others' failures.

    18 min read · 45 min apply
  5. E05

    Scope creep prevention

    ● live

    The amendment protocol at scale. Refusing 'while we're in there' work. Without becoming an obstacle.

    12 min read · 30 min apply
  6. E06

    Multi-venture portfolio operations

    ● live

    Cross-venture routing, shared agents, isolation rules. Running 3+ ventures from one operator.

    25 min read · 60 min apply
  7. E07

    Cloud training discipline — postmortem-driven SOPs

    ● live

    Pod lifecycle decoupling. Exit-path audits. Watchdog cadences. Don't lose a 14-hour run.

    20 min read · 90 min apply
  8. E08

    Hidden cost of agent context drift (and how to detect it)

    ● live

    The signs that your session is gradually losing accuracy. Restart hygiene that compounds.

    15 min read · 30 min apply
  9. E09

    Building your first custom MCP server

    ● live

    When to build vs use existing. The protocol in plain language. The failure modes that cost teams two weeks each.

    20 min read · 2 hours apply↳ prereq: Operating 04 (hooks)
  10. E10

    Multi-agent orchestration patterns

    ● live

    Beyond chief-of-staff routing: parallel-spawn, gather-then-merge, race-then-cancel. When each fires and when each breaks.

    18 min read · 60 min apply↳ prereq: Operating 10 (agent routing)
  11. E11

    Production debugging playbook

    ● live

    When an agent misbehaves in prod: the diagnostic ladder. Five rungs from "claim says done but isn't" through context drift, tool failures, schema mismatches, upstream model regressions.

    20 min read · 60 min apply↳ prereq: Expert 04 (accountability)