For engineers and teams working with Claude Code, Codex or Cursor

Agentic engineering, not vibe coding. Stop reading every line your agent writes.

AI Developer Toolkit is the open manual for agentic engineering with Claude Code, Codex and Cursor. Read all open guides free, audit your repository locally with @wondelai/harness-audit, or pick up the eight offline books and team services.

npx @wondelai/harness-audit

100% open web docs · MIT CLI runs locally in <2s · Zero code uploaded.

Open guides (EN & PL, zero paywall)
140+
Factory Stations audited by CLI
6
Curated offline books (EPUB & PDF)
8
GitHub stars on wondelai/skills (2026-11-21)
2.7k+

Mindset and architecture core — linking to official docs for volatile CLI flags.

One task, start to finish, on a Level 4 setup.

Your attention goes to the spec before the build and the evidence after it. The diff goes to checks you set up once.

  • Written by you
  • Read by you
  • Agent and checks
  1. TicketIntent

    PAY-412

    Prorate plan changes made mid-cycle.

    You write

  2. SpecIntent

    spec.md

    Acceptance criteria, edge cases, files the agent must not touch.

    38 lines

    You write and read

  3. PlanIntent

    plan.md

    Seven steps. The agent proposes them, you approve before it builds.

    Agent writes

  4. BuildLoop

    +612 −148

    14 files changed in an isolated worktree, until the tests pass.

    Agent writes

  5. VerifyVerification

    • 212 tests passed
    • Stop hook passed
    • Review passed

    760 changed lines read

    Checks read

  6. Pull requestRelease

    #1184

    Opened with the test report attached. You read it against the spec.

    24 lines

    You read

Harness: permissions, sandbox, MCP servers and hooks, verified by @wondelai/harness-audit
Lines you read62
Lines the checks read760
Drawing
One task on a Level 4 setup
Runs in
Claude Code, Codex, Cursor
Note
An illustration of the workflow, not a measurement

Engineering teams at these companies use it

  • Grupa Morizon-Gratka
  • Ringier Axel Springer
  • TasteRay

Creator of wondel.ai Skills — 2.7k+ stars on GitHub (opens in a new tab)

Your agent got faster. Your review queue didn’t.

Once the agent writes most of the code, you become its full-time reviewer. Every task ends in a diff you either read line by line or approve on trust. Approving on trust is vibe coding. Agentic engineering replaces that trust with checks that can say no.

“You are still responsible for your software, just as before.”

Andrej Karpathy, published transcript of his Sequoia Ascent talk (opens in a new tab), 2026-04-30
“Your life is diffs.”
Dan Shapiro on Level 3, the developer who reviews everything the agent writes. “The Five Levels”, 2026-01-23

Tue 09:12

You approve a 600-line diff you only skimmed, because reading it properly would take longer than writing it.

Tue 11:30

Your CLAUDE.md started as a paste from someone’s thread. Nobody on the team knows which lines still do anything.

Tue 14:05

Three engineers run three different coding agents on the same repo, with no shared hooks, test gates or review bar.

From our reader survey

“I switch between Claude Code, Cursor, VS Code, GitHub, and other agents, and often have to explain the same project or problem again.”

A reader, July 2026

What two years of telemetry from 22,000 developers shows

Faros AI, “AI Engineering Report 2026”, April 2026 (opens in a new tab)

+66%

epics completed per developer

+242%

incidents per pull request

+441%

median time a pull request spends in review

Output went up, and so did incidents and review time. The way out is checks that read the code for you, set up once and run on every task. That is what this canon teaches.

Know your level. Then climb one rung.

Dan Shapiro’s five levels describe how much of the work you hand to an agent, from spicy autocomplete to the dark factory. Every open guide is filed by level, so the next step is always named.

Want a real measurement instead of a guess?

Run npx @wondelai/harness-audit locally in under 2 seconds. It inspects your repository across 6 Factory Stations, calculates your Level 0–5 cap, and links directly to the free chapter for each gap.

Explore @wondelai/harness-audit
  1. 5

    The dark software factory

    “a black box that turns specs into software”

    WritesAI

    ReadsNobody

  2. 4

    The engineering team

    “write a spec” … “leave for 12 hours, and check to see if the tests pass”

    WritesAI

    ReadsTests, mostly

    Level 3 to 4 guides
  3. 3

    The developer

    “Your life is diffs.” … “almost everyone tops out here”

    WritesAI, most of it

    ReadsYou, full-time

    The valley, levels 2 and 3
  4. 2

    The junior developer

    “where 90% of ‘AI-native’ developers are living right now”

    WritesYou and the AI, paired

    ReadsYou, every line

  5. 1

    The coding intern

    “you offload specific, discrete tasks to your AI intern”

    WritesYou, mostly

    ReadsYou, all of it

  6. 0

    Spicy autocomplete

    “not a character hits the disk without your approval”

    WritesYou

    ReadsYou

Level names and quotations: Dan Shapiro, “The Five Levels” (opens in a new tab), danshapiro.com, 2026-01-23. The share figures are his. Every guide on this site is free to read: start with the ladder guide.

Start with the job in front of you.

Pick the situation you are in today. Every docs track and the CLI are open and free.

  1. WhenYour agent config grew organically and you don’t know what’s missing.

    You get Run npx @wondelai/harness-audit locally (<2s, MIT, zero code uploaded). Get a 0–100 score across 6 Factory Stations, Level 0–5 gating, and --prompt to emit HARNESS-FIX-PROMPT.md.

    Harness Audit CLI

  2. WhenThe agent’s diffs are bigger than your attention span.

    You get The Level 3 to 4 patterns: test oracle protection, Stop hooks, sandboxes and architectural fitness functions so every task ends with evidence instead of a wall of code.

    Verification guides

  3. WhenThe task is too big to hand over in one prompt.

    You get The brief chain: intent.md, spec.md, plan.md. The agent works from a spec you wrote and approved (spec-driven development), in Claude Code, Codex or Cursor.

    Spec-first examples

  4. WhenYou want a structured solo path from Level 2 to Level 4.

    You get The open Developer Track: write one tight AGENTS.md, isolate loops with worktrees and permissions, and move code review from line-by-line reading to evidence verification.

    Developer Track

  5. WhenYour team works at five different levels on the same codebase.

    You get The open Tech Lead Track plus harness-audit --interview --role lead: baseline the repo, standardize hooks and CI gates, and run code review as a queue with WIP limits.

    Tech Lead Track

  6. WhenYou want an external diagnostic or hands-on rollout with your team.

    You get Fixed-price work directly on your repository, delivered by Michał Jaskólski: a written Repo Diagnostic from $499, a Team Working Day, or a measured org pilot.

    Services for teams

Open canon. Local CLI. Offline books.

Everything you need to learn and audit your repo is free. Pay only for the 8-book offline bundle or hands-on team services.

The eight books, at a comparable ebook’s price$383

The Offline Ebook Bundle, paid once$59.99

Books: each title is priced at $47.99, explained in the books section below. The web documentation and @wondelai/harness-audit CLI are free.

  • The open guide library

    140+ architecture and mindset guides for Claude Code, Codex and Cursor, filed by level, in English and Polish. Covers context engineering, verification and org rollout — linking to official docs for volatile CLI flags.

    Free100% open web

  • @wondelai/harness-audit CLI

    Open-source MIT diagnostic for harness engineering. Deterministic <2s local scan across 6 Factory Stations, optional --deep LLM review, --interview, --prompt and safe init scaffold.

    • AGENTS.md
    • CLAUDE.md
    • .cursor/rules
    • hooks
    • CI gates
    • HARNESS-FIX-PROMPT.md

    MITopen source

  • Eight offline books

    The four-title library (96 chapters, 541 pages) plus four role paths for developers, tech leads, CTOs and executives. DRM-free EPUB & PDF in EN & PL, or single editions on Amazon. See the shelf

    $59.99all 8 books

  • Also free without an account: the open MCP server so your agent can search the canon, the Agentic Engineering Glossary, the /harness-audit skill in wondelai/skills, and the field-notes newsletter.

Eight books, compiled from the open canon.

The four library titles run to 541 pages, and the four role paths reuse those pages in the order your role needs. Get all eight DRM-free offline for $59.99, or individual editions on Amazon.

Cover of The AI Engineering Handbook

Library1 of 4

The AI Engineering Handbook

Cursor, Claude Code & Codex — The Craft of Shipping with AI

Read it once and the loop stops depending on which tool is open: you write the spec, let a failing test set the stop condition, and read the evidence at the gate instead of every diff.

Chapters
60
Pages
338
Formats
EPUB, PDF
Editions
EN, PL

Typical price of a comparable ebook

$47.99

Included in Ebook Bundle Included in Ebook Bundle

Also on amazon.com: Kindle on amazon.com, opens in a new tab

Cover of AI Engineering with Cursor

Library2 of 4

AI Engineering with Cursor

A Practical Guide to AI-Native Development in the Cursor IDE

Pick the smallest Cursor surface that can finish each job, from Tab to Cloud Agents, and trust the result because a test, CI and Bugbot checked it, not because the diff looked right.

Chapters
12
Pages
69
Formats
EPUB, PDF
Editions
EN, PL

Typical price of a comparable ebook

$47.99

Included in Ebook Bundle Included in Ebook Bundle

Also on amazon.com: Kindle on amazon.com, opens in a new tab Paperback on amazon.com, opens in a new tab

Cover of AI Engineering with Claude Code

Library3 of 4

AI Engineering with Claude Code

A Practical Guide to Agentic Development in the Terminal

What it takes to leave a terminal agent running without you: a CLAUDE.md that names the gates, a permission mode for each kind of session, and hooks that enforce what a prompt only asks for.

Chapters
12
Pages
67
Formats
EPUB, PDF
Editions
EN, PL

Typical price of a comparable ebook

$47.99

Included in Ebook Bundle Included in Ebook Bundle

Also on amazon.com: Kindle on amazon.com, opens in a new tab Paperback on amazon.com, opens in a new tab

Cover of Agentic Engineering for Developers

Role path1 of 4

Agentic Engineering for Developers

A reading path up the autonomy ladder: from your first merged agent change to reviewing evidence instead of diffs

Write the instructions file, set permissions, give the agent a feedback loop it runs itself, then approve changes on their evidence instead of reading every line.

Steps
16
Further reading
2
Pages
119
Editions
EN, PL

Typical price of a comparable ebook

$47.99

Built from the library’s pages, in the order a developer needs them.

Included in Ebook Bundle Included in Ebook Bundle

Also on amazon.com: Kindle on amazon.com, opens in a new tab

Cover of Agentic Engineering for Tech Leads

Role path2 of 4

Agentic Engineering for Tech Leads

Move the whole team up one rung: harness, verification design and review capacity

Place the team on the ladder, set a baseline, standardize the harness, design verification and run code review as a queue with limits.

Steps
16
Further reading
4
Pages
140
Editions
EN, PL

Typical price of a comparable ebook

$47.99

Built from the library’s pages, in the order a tech lead needs them.

Included in Ebook Bundle Included in Ebook Bundle

Also on amazon.com: Kindle on amazon.com, opens in a new tab

Cover of Agentic Engineering for CTOs

Role path3 of 4

Agentic Engineering for CTOs

The operating model for agent-built software, from a measured pilot to the board

Run a pilot with a control group, name who owns the harness, grant autonomy by risk class, secure the agents and report spend to the board.

Steps
16
Further reading
3
Pages
129
Editions
EN, PL

Typical price of a comparable ebook

$47.99

Built from the library’s pages, in the order a CTO needs them.

Included in Ebook Bundle Included in Ebook Bundle

Also on amazon.com: Kindle on amazon.com, opens in a new tab

Cover of Agentic Engineering for Executives

Role path4 of 4

Agentic Engineering for Executives

The brief and the decisions you own: cost, business case, org design, roadmap and board reporting

What coding agents change for cost, speed and risk, the dated evidence both ways, and the decisions leadership owns, from the cost of an accepted change to the board update.

Steps
8
Further reading
4
Pages
86
Editions
EN, PL

Typical price of a comparable ebook

$47.99

Built from the library’s pages, in the order an executive needs them.

Included in Ebook Bundle Included in Ebook Bundle

Also on amazon.com: Kindle on amazon.com, opens in a new tab

1 / 8

Typical price: the median list price of ten ebooks on AI-assisted and agentic coding from Leanpub, Manning, O'Reilly, Packt and Pragmatic Bookshelf, checked 2026-10-10 (range $24.95 to $59.99). Page counts are the English A4 PDF editions.

Your first week, planned.

  1. Day 1

    Audit your real repository.

    Run npx @wondelai/harness-audit --prompt inside your main repo (<2s, 100% local). See your score across 6 Factory Stations and generate HARNESS-FIX-PROMPT.md for the top missing guardrails.

  2. Days 2 to 5

    Hand over one real ticket.

    Follow the free chapters linked from your audit to wire a Stop hook and test gate, then write intent.md and spec.md for one real task. Review the test report and evidence bundle.

  3. Week 2+

    Standardize across the team.

    Put harness-audit --ci in GitHub Actions so hygiene never regresses, share the open role tracks, or book a fixed-price Repo Diagnostic or Team Working Day to accelerate the rollout.

Run @wondelai/harness-audit Explore team services

MIT open source · Zero account required · Works on Claude Code, Codex and Cursor repos.

Who checks this, and how.

Every guide written and maintained by Michał Jaskólski.

  • 26 years building web apps
  • 2 IPOs
  • AI Lecturer at SWPS University
  • Using Cursor since 2023, Claude Code and Codex since early beta
  • CTO at TasteRay (built with AI)
npx @wondelai/harness-audit --prompt
> npx @wondelai/harness-audit --prompt
Score: 64/100  ·  Level 3 (Review Manager)
Cap: Verification (missing oracle guard & Stop hook)
Wrote HARNESS-FIX-PROMPT.md (4 prioritized fixes)
  • Mindset & architecture here; volatile flags in official docs.

    Every chapter focuses on durable engineering principles and links directly to official Claude Code, Codex and Cursor documentation for fast-changing CLI flags and shortcuts.

  • Every page carries a last-updated date.

    Each guide shows when it was last audited and updated, so you always know how fresh what you are reading is.

  • The diagnostic is open source and deterministic.

    @wondelai/harness-audit is MIT-licensed with zero runtime dependencies. Every check is readable TypeScript you can run offline or gate in CI.

  • Numbers come from third parties, with a date.

    Every statistic on this page names its publisher and when it was published. No invented productivity multipliers.

  • Mistakes are reported and fixed in public.

    Every guide links to its GitHub issue tracker, and wondelai/skills is maintained openly alongside the documentation.

Free on the web. Pay for offline books or team work.

All web documentation and `@wondelai/harness-audit` are free. Buy the DRM-free 8-book bundle for offline reading, or hire Michał directly for fixed-price team delivery. Prices in USD. The total for your country, with any VAT or sales tax, is shown at checkout before you pay.

Offline Ebook Bundle

Offline books

All 8 books in DRM-free EPUB & PDF (EN & PL) for focused offline reading.

$59.99once

12 months of updated editions. Downloaded files stay yours permanently.

Buy Ebook Bundle Download your books

Paid once. 30-day refund on a first purchase.

  • All eight curated books, EPUB and PDF, English and Polish: 32 DRM-free files ($383 at the median price of comparable ebooks)
  • The four-book library (Handbook, Cursor, Claude Code, Codex) plus four role paths (Developer, Tech Lead, CTO, Executive)
  • Download offline and keep your files permanently: personalized license page, no DRM
  • Every updated edition published over 12 months, paid once, nothing renews automatically

Team Ebook Bundle

All 8 offline books for up to 10 engineers, on one company invoice.

$299.99once

12 months of edition updates for the whole team.

Buy Team Bundle

Paid once. 30-day refund on a first purchase.

  • All 8 books (EPUB + PDF, EN + PL) for each person on the team
  • Up to 10 people: you and up to 9 more, added by email address on your account page
  • One company invoice with VAT, issued by Polar
  • Costs less than separate bundles from the sixth person

Services for teams

Fixed-price work on your repository, delivered personally by Michał Jaskólski.

From $499

excl. VAT, invoiced by Wondel.ai

See services for teams

A free intro call first

  • Repo Diagnostic: written findings + 30-day harness roadmap
  • Half-day workshop or full Team Working Day inside your repo
  • Audit & Setup or measured Pilot with written acceptance criteria
  • Zero paywall on web

    Read every guide and run `@wondelai/harness-audit` free without creating an account.

  • 30-day refund

    On a first Ebook Bundle purchase, for any reason. Email support and it is refunded.

  • DRM-free files you keep

    Every EPUB and PDF you download stays yours permanently after the 12-month update window.

  • VAT invoice

    Polar issues an invoice immediately for bundles; Wondel.ai invoices consulting engagements.

Who it is for.

A good fit if

  • You use Claude Code, Codex or Cursor at work every week.
  • You want to hand over bigger tasks and verify the outcome with deterministic gates.
  • You lead an engineering team and want shared standards across Level 2–4 workflows.

Probably not a fit if

  • You want a promise that you’ll ship 10x faster. The studies we cite show output and incidents rising together, so we make no such promise.
  • You haven’t tried a coding agent yet. Start with the open ladder guide.
  • Your team wants a magic plugin without changing specs, tests or review habits.

FIELD NOTES · LOW VOLUME

One practical note when a real harness pattern changes.

Get new architecture essays, major @wondelai/harness-audit releases, and an immediate starter checklist in your inbox. Zero fluff, unsubscribe in one click.

No spam. Your email is never shared or sold.

Questions people ask before starting.

Something else? Write to support@developertoolkit.ai and the author answers.

Is the entire web documentation really free now?

Yes — 100% open with no article meter and no paywall. You can read every guide and run @wondelai/harness-audit (MIT) free. Revenue comes from readers who want the 8 DRM-free offline books (bundle or Amazon) and teams who bring Michał in for fixed-price diagnostics, workshops and rollouts.

What does @wondelai/harness-audit inspect, and does it upload code?

The default scan runs 100% locally in under 2 seconds with zero API keys and zero network calls. It checks 6 Factory Stations (Intent, Harness, Loop, Graph, Verification, Release) and caps your Autonomy Level when critical gates are missing. Optional --deep, --interview, and --prompt modes run only when you ask.

How is this different from the official docs?

Official docs describe one tool’s features and fast-changing flags — and we link directly to them for those details. This canon teaches the cross-tool mindset, architecture, verification gates and organizational rollout across Claude Code, Codex and Cursor.

How is agentic engineering different from vibe coding?

Karpathy published a transcript of his Sequoia Ascent talk (opens in a new tab) (30 April 2026), and one line of it sums up the difference: “Vibe coding raises the floor. Agentic engineering is about extrapolating the ceiling.” In vibe coding nobody reads the diff and no check stands in for the reader. This canon teaches agentic engineering: you review the spec and the test report, and checks you set up review the diff.

Is this AI-assisted coding or AI pair programming?

It starts there and goes further. AI pair programming is the way of working where you read every line the AI writes; AI-assisted coding is the umbrella over all of it, vibe coding included. The guides begin at pairing and move one loop at a time up the autonomy ladder, until checks you set up read the diff for you.

I only use one of the three tools.

That works. Each tool has its own 10-chapter architectural core (and its own offline book), and the underlying workflow stays identical if you add another tool later.

Is the Ebook Bundle a subscription?

No. You pay $59.99 once for all 8 books (EPUB + PDF, EN + PL) and 12 months of updated editions. Nothing renews automatically, and every file you download stays yours permanently.

Do you offer refunds on the Ebook Bundle?

Yes, 30 days from your first purchase of the Offline or Team Ebook Bundle, for any reason. Email support@developertoolkit.ai and it is refunded, as set out in the Terms.

Do I get an invoice for my company?

Yes. Polar, the merchant of record, issues an invoice with the VAT or sales tax for your country right after checkout. Team consulting services are invoiced directly by Wondel.ai.

Will agents replace me?

Your work moves to the spec, the architecture and the stop conditions. In the published transcript of his Sequoia Ascent talk, Karpathy says you are “in charge of taste, engineering, design, and whether the system makes sense.” This canon is about doing those well.

Does this page answer your questions?

One tap, no sign-in.

not at all fully

Audit your harness. Then climb one rung.

“level 2, and every level after it, feels like you are done. But you are not done”

Dan Shapiro, “The Five Levels” (opens in a new tab), 2026-01-23

MIT open-source CLI · 100% open web docs · Fixed-price B2B diagnostics & workshops.