Decide whether to migrate. Control your token bill. Read failures before you make them. The three books are sold separately on Gumroad. This page exists because reading any two of them sharpens the third.
Five measurable triggers, three-path framework (stay / switch / hybrid), cost-forecast worksheet, decision tree, 48-hour rollback checklist. Active within-edition refresh sweeps tracked in Appendix D.
View on Gumroad →800+ measured hours distilled into 10 chapters. CLAUDE.md restructuring (100→35 lines, cache hit 89%→95%), 9 hook-based token guards, context management timing, cache_control bug recovery, post-compaction spike forensics.
View on Gumroad →Ten production-level incidents reverse-engineered from public Issues, commits, and 800+ verified hours. Detection hooks for each pattern. The book is the body of evidence the changelog left out.
View on Gumroad →Each book was built around a specific decision. Migration Playbook answers "should I move?" with five measurable triggers and a three-path comparison. Token Book answers "where is the bill going?" with cache ratio targets and 9 enforcement hooks. Incident Postmortems answers "what already broke?" with ten reverse-engineered production failures.
A single 300-page book would have collapsed all three decisions into one chapter each, and the reader would have skipped two of them. Splitting forces honesty: each book has to earn its price on its own. The reader who finishes one is the reader who is ready for the next.
There is no enforced reading order. The most common path is Token Book → Postmortems → Migration Playbook for someone already in production, or Migration Playbook → Postmortems → Token Book for someone deciding before they start.
| Pain | Migration Playbook |
Token Book |
Incident Postmortems |
|---|---|---|---|
| Pro plan got reshuffled, should I switch? | ● | · | · |
| Five-hour quota burned in 9 minutes | · | ● | ● |
| cache_creation rising past 0.20 | · | ● | · |
| Subagent identity leak / boundary failure | · | · | ● |
| Silent regression across version bumps | · | · | ● |
| CLAUDE.md is 100+ lines and slowing me | · | ● | · |
| Comparing Claude Code to Cursor / Codex | ● | · | · |
| Post-compaction usage spike | · | ● | ● |
| Building a rollback checklist before migrating | ● | · | · |
| Hybrid delegation between Claude and a cheaper model | ● | · | · |
Three books mean three entry points. Pick the one that matches what is hurting right now. The other two stay on the shelf until the matching symptom appears.
The three books above cover the durable operational layers: decide, cost, forensics. Two newer books cover narrower surfaces that emerged sharply in May 2026 and warranted their own treatment rather than being absorbed as chapters:
Claim-Verify Handbook ($19, live since 2026-05-22) catalogs 130 cases where Claude Code or its sub-agents claimed success while the underlying action failed silently (15 main + 115 appendix D, 233 hours of source corpus, ~32-fold acceleration over the 30-day baseline). 14 operator-side defense procedures, 5 detection tools (all implemented and tested, 165+ test cases passing). Anchored by Anthropic's own v2.1.144 release notes and Issue #60226's structural parent.
Sub-Agent Observability Handbook (~$19, ships 2026-05-27) documents 4 distinct sub-patterns of sub-agent failure surfaced across 7 issues filed in a 72-hour window (#60987 / #61102 / #61107 / #61167 / #61315 / #61405 / #61547): dispatch fabrication, silent stall, missing observation/control, scope expansion. Each pattern has a worked operator-side defense hook in cc-safe-setup (PRs #282 / #283 / #286 / #298). The canonical reference page is free at the link.
Both are sibling surfaces to the Operations Suite trinity rather than replacements for it. A reader who finishes Migration Playbook, Token Book, and Postmortems and wants the action-time verify-vs-claim layer reads CVH next; a reader who runs sub-agents in production reads the Sub-Agent Handbook.