2026 Edition · Copy-Paste Ready · Instant PDF Access
terminal craft — the-prompt-library — 80x24

$ open the-prompt-library.md

The prompts that get usable code the first time

Forty tested prompts for working with a coding agent. Scoping a task, reading an unfamiliar repository, planning before writing, reviewing a diff. Each one gives you the exact wording, what it's for, and when to reach for something else.

Price: $10 · one-time payment · instant access

[ok] instant pdf access
[ok] secure digistore24 checkout
[ok] 60-day money-back guarantee
[ok] 2026 edition
cat problem.md
A terminal session that drifted across seven files

Sound familiar?

Three rounds of clarification for one small change?

The agent is not the problem. It writes fine code when it knows the goal, the constraints and what it must not touch. Most of the frustration comes from prompts that carry the goal and leave the other three implicit, so it guesses. It guesses reasonably, and it guesses wrong.

The result is a session that burns twenty minutes rewriting the same instruction with slightly different adjectives, and a diff you no longer trust because you have lost track of what it was allowed to change.

ls prompts/ | head -3

Sample pages

A look inside the library

Every prompt is laid out the same way: what it's for, the exact wording to paste, what it pairs with, and when to reach for something else instead.

prompt 01

Before any change

The Scope Lock

Before writing code: restate the task in one sentence, list the files you expect to touch, and name what you will NOT change. Wait for my go-ahead.

Use whenAny task over 10 linesPairs withThe Plan Gate
prompt 07

An unfamiliar codebase

The Cold-Repo Read

Map this repo before changing anything: entry points, where state lives, how data flows in, and the three files I'd need to understand first. Cite paths.

Use whenFirst session in a repoPairs withThe Scope Lock
prompt 23

Reviewing generated code

The Diff Interrogation

Review this diff as a hostile reviewer. For each change: what breaks if input is empty, null, or huge? Name the single riskiest line and why.

Use whenBefore every mergePairs withThe Test-First Turn

40 in total inside the guide

Every prompt is dated, tested on a real repository, and carries a plain note on when not to use it.

cat contents.md

What's inside

Here's exactly what you'll be able to do

  • How to scope a task so the agent stops guessing at what you meant
  • Reading an unfamiliar codebase before you change a line of it
  • How to make the agent plan first and write second
  • Reviewing a diff you didn't write without skimming past the bug
  • Recovering a session that has drifted, without starting over
contents
01 The Anatomy Of A Prompt That Lands
02 Scoping Prompts
03 Exploration Prompts
04 Planning Prompts
05 Review Prompts
06 Recovery Prompts
why --verbose

Why this library works

It replaces improvised instructions with wording that has been run on real repositories, and it tells you plainly when a prompt is the wrong tool.

Paste And Go

No templates to fill in and no theory to translate into wording. Every prompt is written out in full, ready to copy.

Grouped By The Job

Organised by what you are doing: scoping, exploring, planning, reviewing, recovering. Not by an abstract taxonomy of prompt types.

Dated And Honest

The 2026 Edition on the cover, a chapter on what shifts between model versions, and a plain note on when each prompt is the wrong choice.

grep -n 'is this for me'

This is for you if

  • You already run a coding agent on a real project most days
  • You keep re-typing the same instructions and getting different results
  • You have lost an afternoon to a diff that touched files you never mentioned
  • You want wording you can paste, not theory about prompt engineering

This is not for you if

  • You have never run a coding agent — start with the tool's own docs first
  • You want a course, videos or a community — this is a written reference
  • You expect prompts that make review unnecessary. Nothing does that.
PDF

What you get

The Prompt Library — 52-page guide (PDF)

Forty tested prompts for working with a coding agent, with the exact wording and when not to use them.

  • 52 pages6 chapters, 2026 Edition
  • 40 promptsExact wording, ready to paste
  • Instant accessEmailed the moment you buy
  • Any deviceRead on desktop, tablet or print

Pages shown are from the actual guide. Digital product (PDF) — no physical item and no software licence is included.

Stop rewriting the same prompt four times to get one usable answer.

The Prompt Library is where the system starts. Forty prompts you can paste today, grouped by the job you're doing, plus the structure that makes any prompt land: give the agent the goal, the constraints, the files and the definition of done, in that order, every time.

US$10one-time
Yes, I want prompts that land the first time — Only $10

Instant digital download. One-time payment of $10, billed securely by Digistore24. Educational material only. Results depend on your project, your model and how you apply it. Independent publication, not affiliated with or endorsed by any AI vendor.

man faq

Frequently asked questions

Is this a physical book or a digital product?

It's a digital guide (PDF). Right after purchase you get an email with a secure link to download it instantly. Nothing is shipped.

Is this official, or connected to Anthropic?

No. Terminal Craft is an independent publisher with no affiliation to, endorsement from or sponsorship by Anthropic or any other AI vendor. Claude and Claude Code are trademarks of Anthropic PBC. This guide is our own field notes on using those tools well.

Does this include software, a licence or a subscription?

No. You need your own tools and your own account. This is written material: prompts, patterns and workflows you paste into whatever you already use.

AI changes constantly. Will this be out of date next month?

Every guide is dated on the cover as the 2026 Edition, and each one includes a chapter on what tends to change between versions and how to adapt a prompt when it does. The patterns outlast the version numbers; the specific outputs will not, and we say so plainly rather than pretending otherwise.

Do I need to be an experienced developer?

You need to be comfortable running a coding agent on your own project. The prompts are written in plain English and explained, but they assume you already have a codebase you're working on.

What if it isn't for me?

You're protected by a 60-day money-back guarantee. If it doesn't help, email us within 60 days for a full refund. No questions asked.

Run a better prompt on your next task

Get instant access to all forty prompts and the structure behind them, and stop paying for the same clarification round three times.

Yes, I want prompts that land the first time — Only $10

Your payment will be processed securely by Digistore24.