Agent Plugins 1.0.0 is an open, vendor-neutral standard for packaging AI agent plugins, released 6 August 2026 and governed by a Technical Steering Committee with Core Maintainers from Amazon, Cursor, Microsoft, OpenAI and Vercel. A plugin is a directory with plugin.json, a skills/ folder in Agent Skills format, and an mcp.json describing MCP servers. This explains what the spec requires, how its governance charter enforces vendor neutrality, how it differs from MCP and Agent Skills, and what adopting it on day one cost me across a 13-skill library of testing skills for agents and a 33-skill second brain.
When Opus 5 shipped I changed the model string and moved on, like everyone does. Then I noticed my harness was fighting the model. Model upgrades do not just raise capability, they reverse direction on specific behaviors, and every workaround you wrote for the old behavior becomes a bug. This is the audit: 91 skills, 33 commands, six changes, 1,500 lines deleted, and three real defects I only found because I finally reread the files.
Claude Code and the Codex CLI can't see or touch the screen; only OpenAI's Codex desktop app has computer use. So I pointed my coding agent at the desktop app, had it reverse-engineer how the feature works (the @oai/sky helper, a unix socket, a JSON-RPC protocol), and rebuild it from scratch on public macOS APIs as computer-harness. This is what it found and what it built, dead-ends included.
Why I forked localterm into TermDeck: a self-hosted browser workspace for agent-heavy terminal work. Live grid of sessions, clickable file paths, tweak mode that sends CSS selectors back to the agent, a markdown wiki, and a tldraw canvas.
Mastra shipped file-based agents, skills, schedules, and signals in nine days. My markdown vault has run all four DIY for months.
arXiv:2605.26112 says agent performance now comes from six system components around the foundation model: memory, context construction, skill routing, orchestration, and governance. I ran the paper through my personal agent setup as a self-audit. Verdict: half the paper was already implemented through months of small adoptions, two named failure modes (stale-but-confident memory, confident-but-unchecked skills) were real gaps, and both got fixed the same afternoon by the agent itself. This is the full process: paper to audit to shipped enhancements to this post.
I'm the lead product manager building Katalon True Platform, an AI-native testing platform, and every release my AI agent tests it alongside our QE team. One terminal command runs the full software testing loop: collect the release scope, design test cases, execute with the AI test runner and Playwright, file findings back. This is how a PM learns the product's real capabilities and limitations, with real screenshots, video, and a narrated deep dive for QA engineers, QE, and testers.
With GPT and Claude, any PM or designer can build something that technically works in half a day. It is addictive, and it lies. 'Technically works' (in isolation, on happy-path data, on my machine) is a different universe from 'works well inside the current system, at scale.' That second thing is the real engineering, and AI quietly lets you skip all of it. This post is about the prototype trap, the naivety of confusing a working demo with a production-ready feature, and the reframe that makes non-engineers actually useful with AI: run the loop to evaluate options and build conviction, spark the team instead of pretending the hack is done, and treat innovation as selection rather than invention.
A builder's argument for why neither product teams nor everyday users are ready for fully autonomous AI agents: verification is the expensive part and most of us can't afford it, and unverified AI output compounds like debt. Includes the snowball failure modes I hit running an agent-heavy personal knowledge system, and the practices I stole from gbrain and gstack to contain them: memory gates, provenance, supersede-not-append, periodic reindex, fresh-context isolation, and poisoning defenses.
Claude Code shipped workflows. So I wrote one that takes any testing task — a vague Slack message, a Jira story, a 'just check the checkout' — and runs it end to end on Katalon True Platform. Manual, automated, and Playwright. One skill. Three lanes. Here's the whole thing.
How we build software in the AI era. A complete ways-of-working model for AI-native teams — why agile and Scrum rituals (sprints, story-point estimation, velocity, the daily standup) were a tax on slow building, why Kanban and continuous flow fit human-and-AI-agent collaboration, and the markdown files you can drop into a repo to run it tomorrow.
How Claude Code records every interaction as a replayable, auditable event stream — and why the design choices are worth stealing.
What agentic QA actually is (and isn't), the 25% automation ceiling, trust as a loop, the harness vs. the model, and the one experiment every QA leader should run this week.
Kai is the orchestrator agent at the heart of Katalon's True Platform — a repositioning from automation company to AI-native quality platform. A short note on what shipped and why it matters.
Understanding when to fix the bottom and when to empower the top - a practical guide to team leveling that every leader needs
From daily briefs to project management - how Claude Code and a Light Agent system transformed my workflow into a terminal-first lifestyle
How Scout bridges the gap between high-velocity AI-assisted development and quality assurance, bringing autonomous testing to the era of vibe coding.
The PM job has never been simultaneously easier and harder than it is right now. With just one prompt, I can transform ideas into prototypes and concepts into mockups—but like the massive IBM computer in 'Hidden Figures,' these tools are only valuable when you truly understand what lies beneath them.
The operating pattern I use to take new ideas from sketch to scalable system without losing momentum.
High-quality execution comes from deliberate practice loops, not from reading more playbooks.
How to anchor product decisions in the realities of the people you serve—without turning discovery into a stage play.