Skip to content
Get AgentKit
Guides

AgentKit v3 guides

Step-by-step AgentKit v3 guides, in order: install AgentKit, set up your kit and ship your first feature with AI coding agents.

  1. Step 1What is new in AgentKit v3? Not a "more features" release, a foundation swapOn 29/10/2026, the v3.0.0 tag landed on GitHub with 101 assets: kits for 8 runtimes, the ak CLI for macOS/Linux/Windows (amd64 and arm64) with SBOMs, the ak-gui desktop app, checksums.txt and release-provenance.json. The release note is long enough to be a eulogy, roughly 300 bullet points of…9 min read
  2. Step 2Updating to v3, rollback, auto-update and troubleshooting: how to avoid a meltdownI have one rule when building tools for devs: anything that can break things needs a way back. This article follows the order I recommend: capture the current state, update, verify, and only then think about turning on auto-update. If something goes wrong, scroll down to the rollback section.7 min read
  3. Step 3License and the new update policy: what you bought stays yours, said clearly once and for allThe question I have been asked most since announcing v3: "Does v3 make me pay again? Will the kit I bought get locked?"8 min read
  4. Step 4Installing kits for multiple runtimes, per project or global: the real certification table, no rose-tinted glasses"Does AgentKit run on Cursor?" The honest answer: it installs, but it is not certified yet. This article gives you the table I use internally to decide how "mature" each runtime is, then shows how to install for each case.5 min read
  5. Step 5Managing skills and SkillX: build your own kit without fearing an update wiping it outThis is the longest article in the series, because it holds the part of v3 I am most excited about: your skills are your assets. You write them, edit them, carry them to another machine, share them with your team, and the next kit update does not overwrite them.7 min read
  6. Step 6AgentKit Vault: store your API keys properly, stop letting agents read `.env`Come on, confess: how many .env files with real API keys are sitting on your machine right now? I once counted mine, and the number made me a little... embarrassed 😅6 min read
  7. Step 7Hooks and privacy: what the agent is blocked from reading, and why blocking is not enoughHooks are bits of code that run before or after each agent action: before reading a file, before running a shell command, when a session opens, when context is compacted... AgentKit uses hooks for two things: nudging the agent to work with discipline and blocking the agent from touching sensitive…4 min read
  8. Step 8Decision Layer: System One, Jev, Clef, and giving AI "decisions with a type"Before we start, I have to correct something: "Decision Layer" is not yet the name of a feature in AgentKit. You will not find this phrase in ak, in the docs, or on the site. It is just how I refer to an experimental direction: using small models that specialize in structured judgments to help the…4 min read
  9. Step 9Installing AgentKit on cloud and CI: Claude Routine, GitHub Actions and a few trapsLet me be clear up front: AgentKit's official docs do not yet have a dedicated cloud/CI page. This article is how my team and I do it, assembled from flags and behaviors that really exist in ak 3.0.0. Wherever something is my own recipe, I say so.5 min read
  10. Step 10The AgentKit ecosystem: what Vault, Render, CloudHarness, SkillX and TOSE are, and when to use themAgentKit is the core. Around it sit a few smaller products, each solving exactly one problem I ran into working with agents every day. This article is the map: what each one is, how far along it is, how it connects to ak, and when you actually need it.6 min read
  11. Step 11Becoming a Contributor and earning with AgentKit: what the program is, what you get, what is still unclearAgentKit grows because of people who use it every day and then come back to report bugs, send PRs, write skills, and recommend it to friends. I want those people to be recognized with something real: money and benefits, not just a thank-you line in the release note.4 min read
  12. Step 12Picking a workflow by model: when to brainstorm, when to advise, when to skip the plan step entirelyLately on Discord I have been sharing my new workflow with Opus 5.5: no more plan → clear → cook. And of course you all piled on with questions 😂 "So where does /ak-brainstorm fit?", "Do I use /ak-advise instead of brainstorm, or together?", "Do I need a worktree for every session?".7 min read
  13. Step 13`/ak-orchestrate` and `/ak-atoz`: hand a whole team of agents the overnight shift, wake up and just review PRsEver since I started using Opus 5.5 in Claude Code (the desktop app), the way I work has changed completely. I no longer sit chatting with one agent, waiting for it to do things one by one. Now I open one main session as the "conductor", and it splits the work into several sub-sessions running in…10 min read
  14. Step 14Cloud Harness MCP: let ChatGPT open a repo, edit code, run tests, open a PR (and where to be careful)My starting idea was pretty lazy: ChatGPT is great at chatting about code, but it has no hands and feet. Codex has hands and feet, but the quota is limited. So why not give ChatGPT its own set of hands and feet through MCP? The model thinks inside ChatGPT, while reading files, editing code,…4 min read
  15. Step 15`/ak-test`: fewer box-ticking tests, tests in the right places, run by blast radiusAI is now trained to produce more stable output, so it writes tests in huge quantities. Great, until you have a few thousand tests and the CI bill is jumping around, yet the app still breaks when it breaks. In that pile there are "obvious tests" (tautological tests, like true == true): tests that…5 min read
  16. Step 16AK Render: stop making AI write hundreds of lines of HTML just to present a reportTell an AI "make me a report" and it sweats away writing HTML, CSS, JavaScript, responsive layout, dark mode, charts... a hundred KB or so. Next time you ask for a similar report, it writes almost everything from scratch again. Using an expensive model to do a job a compiler does better does not…5 min read
  17. Step 17Turning the cloud into a workplace: VPS, Orca, OMP and the `ai-handle` label so agents pick up issues by themselvesLately I rarely have to type prompts. Not because I got lazier, but because work no longer starts with me opening a terminal. A customer reports a bug, the system creates an issue with context, an agent on the VPS picks it up, runs tests, opens a PR, and reports back on Discord. I just review the…6 min read
  18. Step 18Software factory: don't just build software, think about building the factoryEvery time a new buzzword shows up, I get the feeling of "huh, so the thing I have been doing all along has a name?". Prompt engineering, context engineering, harness engineering, and this week software factory. It sounds as grand as an ad for getting rich on autopilot, but this time there is…7 min read
  19. Step 19How I make anime with Opus 5.5: five stages, and why QA subagents matter more than the modelI had Opus 5.5 make anime from a bare one-line prompt, then pushed it through five stages to produce the series FRONTIER (episode 01 is up on YouTube, episode 02 was still rendering when I wrote the original post). This article pulls out the reusable parts. It is not a promise that "anyone can…6 min read
  20. Step 20Personal kit and `/ak-dogfood`: tweak your own skills without an update wiping them outAnyone who has used a kit for a while hits this: the ak-plan skill works fine, but your team has one convention it keeps forgetting. You open SKILL.md, edit it, and it runs great. Next week you run ak update and your edit vanishes 😂9 min read
  21. Step 21AK Vault: let agents use secrets without ever seeing themTo be fair up front: a vault is not a miracle cure. It solves exactly one problem, which is the agent can use the key without holding the key. It cannot save you if you paste a key into the chat yourself, and it cannot save you from a program that received a key and sent it somewhere. Those limits…24 min read