Bundle · $37.99
Agent Skills + Workbench: the Claude Code PDF bundle
Both books: what good agent output looks like, and how to check it
Make agent work easier to check. The Skills Pack shows the request and the real output for 17 skills. The Workbench gives you a two-week routine for planning Claude Code work, reading the evidence and deciding what to change.
Who it’s for
- Developers who want concrete examples of agent output they can review.
- Tech leads and managers who need a practical way to judge whether Claude Code is paying off.
- Builders who learn best from worked examples, diagrams and explicit checks.
What you get
- Agent Skills Pack: 17 worked examples (70 pages) Engineering, agent harnesses, diagrams and docs, and learning content. Each chapter shows the request, the output and anything that was not run.
- The Agent Workbench, Claude Code edition (29 pages) The plan, check and handoff routine, approval hooks and their limits, transcript readouts, a playbook, a manager memo and a way to measure results on your own code.
- One price for both $37.99, against $44.98 for the two books bought separately.
Terms
- Format
- Two downloadable PDFs, November 2026 editions, delivered by Gumroad right after checkout.
- Scope
- The PDF only. The code kits, installers, skill folders and templates the books describe are separate and not included.
Honest notes
- Independent publication by Tim Urista. Not affiliated with or endorsed by Anthropic. Claude and Claude Code are trademarks of Anthropic.
- Example projects and team numbers are synthetic and labeled as such. They are not customer results.
- No security, savings or productivity guarantees.
Inside the books
Actual rendered pages from the PDFs, with notes.
-
Agent Skills Pack, pages 10 and 51: the request and what came back, side by side. -
The Agent Workbench, pages 18 and 21: from a team readout to a decision memo. -
Agent Skills Pack, page 52: a real output of the exploded-view skill.