Every guide, filed by section and by level.

577 guides in 12 sections, in English and Polish. Light up the guides that start at your level, filter by a word and open the one you need.

$59.99 once for 12 months of access. Nothing renews on its own. 30-day refund on a first purchase.

Sections in the library
12
Guides, in English and Polish
577
Free to read: Start here and Autonomy Ladder
19
Tools with a guide tree of their own
3

Every guide shows when it was last updated.

The whole library, drawn to scale.

One tick is one guide. A taller tick starts higher on the autonomy ladder. Pick a level to see where its guides sit.

Pick a level to light up its guides. The short grey ticks are guides that carry no level.

A guide’s level is the rung at which it starts being useful, read from the guide’s own front matter. Counted at build. Every guide sits in exactly one section, so the bars add up to the library. Guides are filed from Level 1 up: Level 0 is spicy autocomplete, where “not a character hits the disk without your approval” (Dan Shapiro, “The Five Levels” (opens in a new tab), 2026-01-23).

Open a section.

Sections are ordered by how often people use them. The Start here and Autonomy Ladder sections are free to read. In every other section you read 5 articles a month free, 10 with a free account, and all of them with the Toolkit.

Start here

Free to read 8 guides

A reading path for each role, and the quick wins for your first day.

Show all 8 guides in Start here
Open the Start here hub

Autonomy Ladder

Free to read 11 guides

Where your workflow sits today, and the guide for the next rung.

Show all 11 guides in Autonomy Ladder
Open the Autonomy Ladder hub

Cursor

70 guides

Rules, agent modes, the Agents Window, Bugbot and cloud agents, in nine task folders.

Show all 70 guides in Cursor

Build 23

Open the Cursor hub

Claude Code

79 guides

Memory, hooks, subagents, goals and routines, in the same nine task folders.

Show all 79 guides in Claude Code

Overview 1

Build 22

Open the Claude Code hub

Codex

56 guides

AGENTS.md, config.toml, worktrees and codex exec, in the same nine task folders.

Show all 56 guides in Codex

Overview 1

Open the Codex hub

Workflows & method

110 guides

The method that holds in all three tools: artifacts, context, the harness, verification and shipping.

Show all 110 guides in Workflows & method

Test & verify 22

Open the Workflows & method hub

Ecosystem & comparisons

116 guides

MCP servers, skills, plugins, agent tools and frameworks, plus the comparisons between tools.

Show all 116 guides in Ecosystem & comparisons

Choose a tool 20

MCP servers 31

Agent skills 20

Frameworks 15

Open the Ecosystem & comparisons hub

Cookbook

41 guides

Prompts for your stack, each paired with the check that proves the result.

Show all 41 guides in Cookbook
Browse the recipes by domain

Lead a team

24 guides

Rolling agents out to a team: the shared harness, the review flow and the people.

Show all 24 guides in Lead a team
Open the Lead a team hub

Engineering organization

40 guides

The operating model, security and compliance, measurement, and spend.

Show all 40 guides in Engineering organization
Open the Engineering organization hub

Strategy & business

11 guides

The business case, the economics, board reporting and how teams change shape.

Show all 11 guides in Strategy & business
Open the Strategy & business hub

Reference & help

11 guides

Command and config reference, the glossary, troubleshooting and what changed.

Show all 11 guides in Reference & help
Open the Reference & help hub

The same nine tasks in every tool.

Cursor, Claude Code and Codex are each filed under the same nine task folders, from quick start to reference. The numbers are guides per folder.

Guides per task folder in each tool tree
Task folder CursorClaude CodeCodex What is in it
Quick Start 11 12 10 Install, authenticate, configure, run a first task, set up MCP
Plan 4 5 4 Architecture, new projects, codebase analysis
Build 23 22 13 Features, refactoring, APIs, databases, documentation
Test & Debug 4 3 3 Debugging, test generation, test-driven development
Review & Ship 6 6 6 Code review, CI/CD, deployment
Operate 6 7 5 Cost, monitoring, performance, security audits
Automate 7 12 9 Headless runs, SDKs, subagents, scheduled automations
Team & Enterprise 3 7 3 Shared configuration, governance, privacy and security
Reference 5 4 2 Changelog, upgrades, shortcuts
Tool overview 1 1 1 The hub page for the tool
Guides in the tree 707956

Counted at build. Compare the three tools station by station on the comparison page.

Questions about the library.

Something else? Pick a reason on the Contact page and write to the right address.

Can’t I just ask my agent instead of reading guides?

You can, and the answer will often sound right. Models invent flags: ask for Codex approval settings and you may get --approval-mode, which is not a Codex flag. The real one is --ask-for-approval (Codex CLI 0.159.2, checked 2026-10-02). Every guide shows when it was last updated, so you can see what still holds.

Can I read a guide before I buy?

Yes. The Start here and Autonomy Ladder sections are always free: the reading path for your role, the quick wins for your first day, and the Ladder section's 11 guides: each level named, how to test for it and how to climb to the next. Every other section gives you 5 full articles a month free, 10 with a free account, and all of them with the Toolkit.

How do I know a guide is current?

Every guide shows when it was last updated, and many name the tool version they were checked against, such as the hooks guide (Claude Code v2.1.283).

I only use one of the three tools. Is most of this wasted?

Each tool has its own tree, filed under the same nine task folders from quick start to reference. The sections on workflows, the cookbook and organizations describe the same method for all three.

Is the Polish library the same?

Yes. The English and Polish libraries list the same pages. Product and file names such as CLAUDE.md and AGENTS.md stay in English.

What do the levels on this page mean?

They come from Dan Shapiro’s five levels, from spicy autocomplete to the dark factory (“The Five Levels” (opens in a new tab), 2026-01-23). A guide’s level is the rung at which it starts being useful.

Engineers at these companies work with AI Developer Toolkit

  • Grupa Morizon-Gratka
  • Ringier Axel Springer
  • TasteRay

Creator of wondel.ai Skills — 2.3k+ stars on GitHub (opens in a new tab)

Does this page answer your questions?

One tap, no sign-in.

not at all fully

Read the guide you came for.

Open any of the 577 guides with the Toolkit, in English or Polish.

$59.99 once for 12 months of access. Nothing renews on its own. 30-day refund on a first purchase.