Founder of AgentKit
Founder of AgentKit, writing about AI coding agents, automation, and practical developer workflows.
· 24 min read · AgentKit Guides
To 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…
Read article →· 9 min read · AgentKit Guides
Anyone 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 😂
Read article →· 6 min read · AgentKit Guides
I 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…
Read article →· 7 min read · AgentKit Guides
Every 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…
Read article →· 6 min read · AgentKit Guides
Lately 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…
Read article →· 5 min read · AgentKit Guides
Tell 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…
Read article →· 5 min read · AgentKit Guides
AI 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…
Read article →· 4 min read · AgentKit Guides
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,…
Read article →· 10 min read · AgentKit Guides
Ever 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…
Read article →· 7 min read · AgentKit Guides
Lately 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?".
Read article →· 4 min read · AgentKit Guides
AgentKit 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.
Read article →· 6 min read · AgentKit Guides
AgentKit 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.
Read article →· 5 min read · AgentKit Guides
Let 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.
Read article →· 4 min read · AgentKit Guides
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…
Read article →· 4 min read · AgentKit Guides
Hooks 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…
Read article →· 6 min read · AgentKit Guides
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 😅
Read article →· 7 min read · AgentKit Guides
This 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.
Read article →· 5 min read · AgentKit Guides
"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.
Read article →· 8 min read · AgentKit Guides
The question I have been asked most since announcing v3: "Does v3 make me pay again? Will the kit I bought get locked?"
Read article →· 7 min read · AgentKit Guides
I 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.
Read article →· 9 min read · AgentKit Guides
On 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…
Read article →· 13 min read · Vibe Coding
Protect your AI-built projects with a vibe coding backup routine. Learn the 5-layer framework to secure your code, database, and configurations. Start today.
Read article →· 21 min read · MCP & Integrations
Ensure production-ready software with this 40-point AI-assisted deployment checklist. Verify code, configuration, and security before your next release.
Read article →· 15 min read · Claude Code Guides
Learn how to configure Claude Code PostToolUse hooks for automated formatting and linting. Follow our guide to improve workflow efficiency today.
Read article →· 13 min read · Claude Code Guides
Learn how to configure Kimi K2 with Claude Code using Anthropic-compatible endpoints. Follow our step-by-step guide for setup, verification, and testing.
Read article →· 10 min read · Claude Code Guides
Learn how Claude Code effort level impacts reasoning and performance. Discover the best settings for your tasks to balance efficiency and accuracy.
Read article →· 11 min read · Claude Code Guides
Learn how to use the Claude Code-Simplifier agent for safe, efficient code refactoring. Follow our step-by-step guide to install, scope, and validate changes.
Read article →· 12 min read · Claude Code Guides
Understand Claude Code MCP scopes: local, project, and user. Learn to manage server registration, precedence, and troubleshooting for better configurations.
Read article →· 15 min read · Vibe Coding
Is vibe coding dead? Learn why rapid AI prototyping needs to evolve into structured AI-assisted engineering for production. Build safer software today.
Read article →· 9 min read · Claude Code Guides
Learn how to use the Claude Code --append-system-prompt flag to add custom runtime instructions. Boost productivity with best practices and examples.
Read article →· 15 min read · Vibe Coding
Learn when to use vibe code for internal tools, identify risks, and use our scorecard to deploy prototypes safely without compromising system integrity.
Read article →· 14 min read · Claude Code Guides
Learn how to use Claude Code to identify XSS vulnerabilities. Explore capabilities, limitations, and a safe evidence-based workflow for code review.
Read article →· 13 min read · Vibe Coding
Master the vibe coding refactor: a secure workflow to manage AI-generated code, reduce technical debt, and ensure maintainability. Optimize your process today.
Read article →· 17 min read · Claude Code Guides
Master Claude Code for Angular development. Learn to set up your repository, configure CLAUDE.md, and execute safe coding workflows with this guide.
Read article →· 15 min read · Vibe Coding
Learn to secure AI-generated code with essential vibe coding security guardrails. Master lifecycle controls, agent permissions, and verify output today.
Read article →· 14 min read · Claude Code Guides
Compare Claude Code vs v0 to find the right AI tool for your project. Learn when to use browser-first generators versus repository-centered coding agents.
Read article →· 13 min read · Claude Code Guides
Master the Claude Code working directory. Learn how to set project context, manage Git roots, configure CLAUDE.md files, and handle multiple directories.
Read article →· 15 min read · Vibe Coding
Learn to implement vibe coding governance for secure AI development. Use our framework to manage risk, ensure accountability, and scale AI-assisted software.
Read article →· 16 min read · Claude Code Guides
Stop AI overbuilding by using TDD Claude Code. Learn to guide Claude with tests to ensure precise, efficient implementation. Start your TDD workflow now.
Read article →· 9 min read · Claude Code Guides
Explore the status of Claude Code Ultraplan. Learn how to implement effective repository planning workflows and verify features before code execution.
Read article →· 12 min read · Claude Code Guides
Learn how to use Claude Code auto mode to reduce approval fatigue. Follow our guide on safe implementation, best practices, and manual review requirements.
Read article →· 14 min read · Claude Code Guides
Learn how Claude Code Channels works for event-driven workflows. Master setup, secure integration, and best practices for connecting external messages today.
Read article →· 7 min read · Claude Code Guides
Investigating the Claude Code Buddy feature. Learn how to verify if the /buddy command is active in your terminal and separate rumors from verified facts.
Read article →· 15 min read · Claude Code Guides
Learn how to install the Claude Code desktop app for your projects. Follow our guide to set up your workspace, manage permissions, and start coding today.
Read article →· 15 min read · Claude Code Guides
Discover how to use Claude Cowork for delegating knowledge work safely. Learn to set up tasks, follow best practices, and evaluate productivity gains.
Read article →· 14 min read · Claude Code Guides
Master Claude Code agent teams for coordinated coding. Learn setup, best practices for task delegation, and how to avoid file conflicts. Start today.
Read article →· 15 min read · Production Workflows
Learn the Agent Skills specification. Standardize AI procedures with SKILL.md files, directory structures, and metadata. Create reusable, portable skills now.
Read article →· 11 min read · Claude Code Guides
Learn how to check Claude Code token usage using slash commands, monitor session costs, and manage context occupancy effectively to optimize your workflows.
Read article →· 15 min read · Claude Code Guides
Learn how to effectively use a Claude Code MCP manager. Compare native tools with third-party options and follow our safe setup and configuration guide.
Read article →· 13 min read · Claude Code Guides
Master Claude Code visual regression testing with this guide. Learn to automate screenshot comparisons, interpret results with AI, and ensure UI stability.
Read article →