#agents

Building the new North Pole Security site, I kept hitting the same friction: reviewing a page, then typing out a punch list of fixes for Claude Code. Every item needed a page name, a location, and enough context to be actionable. So I had Claude build me a point-and-click sticky note system instead, and now I shift-click on the page, type a note, and it gets fixed. Less typing, more pointing.

What it actually does

The idea was simple. Wouldn't it be nice to leave sticky notes on the page, the way you'd flag a printed mockup with a pen? In a single prompt, Claude Code had nearly the whole thing built.

Each note captures what it needs to be useful: x/y coordinates, window size, the CSS selector under the cursor, and, because Astro emits dev-mode HTML attributes, the source filename and line number. All of that gets compiled into a server-side JSON file. Then a single skill command, /address-feedback, runs through every note with subagents.

It works amazingly well. Fixing things is much faster, but the better part is collaboration. On a screenshare, when someone has feedback I shift-click, type their note, and if there's time I let Claude fix it while we keep talking.

Building your own tools is basically free now

This is part of a larger pattern: you build your own tools to become more efficient. That used to be a hard sell, because throwaway bespoke software was expensive. Most of us still carry that old cost around in our heads.

The calculation has changed. Spinning up a one-off tool is close to free, so the question of whether it's worth automating something tips toward yes far more often than it used to.

The old xkcd math still holds, but the y-axis just got a lot cheaper.

difit does the same trick for diffs

Someone showed me difit recently, and it applies the same idea to code review. Instead of typing your feedback into Claude, you open the diff in a GitHub-style UI and leave comments right on the lines. Those comments get handed back as a prompt, so Claude knows exactly where each change goes.

There's even a /difit-review skill for it. I'm going to try it right after I finish typing this.

One more Claude Code tip

If you aren't running /tui fullscreen, turn it on. Claude manages its own terminal interface instead of leaning on the terminal's, which makes scrollback and mouse clicks far less buggy and makes typing smoother. Run /tui with no argument to see which renderer is active.

Molty, our AI Head of Growth, is doing its job. Somewhat. Over the past week I've run a NanoClaw instance named Molty and put it in charge of growth for SpaceMolt, our realtime MMO for AI agents. To be clear: it's still humans playing the game through agents. But humans have to find out the game exists, and that's Molty's beat.

The road has been rocky. It forgets things. It replies to the wrong Discord threads, skips scheduled tasks, and ignores reminders no matter what gets stuffed into its CLAUDE.md. But this week it finally started getting stuff done.

What it actually shipped

All of this came with a large amount of hand-holding, but it happened:

• Identified 640 users who created a player and then stopped playing over a month ago.
• Emailed them a reactivation email via Beehiiv, and yesterday, a follow-up survey.
• Compiled survey results alongside real income and expenses (Patreon, Render.com, GitHub, Notion) into a daily summary that lands at 5pm.
• Lists upcoming tasks and the content calendar (we told it to make one) at 7am.
• Interviewed our top player over a written Q&A and drafted an operator spotlight blog post about them.
• Made itself a self portrait.

Not automated, but trying

Molty isn't fully automated. There's still a lot of back-and-forth in our private #dev-team Discord channel. It does try to automate itself, though. This morning it configured a GitHub workflow to publish that blog post. The workflow failed. I told it "go fix it," and it did.

The one trick that moved the needle

The biggest improvement came from a habit, not a config change. When Molty messes up, I ask it why. "Why did you do that?" "What made you think X?" "Why didn't you remember to Y?" It self-identifies the issue it ran into, and then I follow with "fix it so that doesn't happen again."

That works about 75% of the time. The other 25% I'm back in Discord, reminding a crustacean which thread it was supposed to be in.

Claude has me locked in for now, but only loosely. I trust exactly one coding agent, and it's Claude Code, and that trust is the only thing keeping me from shopping around.

I've been on it entirely since November or December of 2025. The plan is the $200/mo Claude Max, and I run it at near capacity most weeks, sometimes straight into the wall.

Riding the curve

February 2026 was the good part. Things clicked, and Claude Code felt like I had hired an intern who actually finished tasks.

Then April happened. The intern I thought I'd hired became intoxicated, forgetful, and a little belligerent. Same plan, same tools, much worse vibes. I kept using it anyway, partly out of stubbornness and partly because I'd already learned its tells.

I haven't spent real time in Claude Desktop, Claude Cowork, or Claude Design. They read as limited versions of the same thing. The CLI still reigns, sandboxed of course.

The contenders are real

This isn't a "nothing else is good" post. The market is loud right now.

• Qwen 3.6 reportedly feels great for coding, and there's an open-weights line you can self-host.
• GPT and Codex come up for Rust, which I'll probably be writing soon even though I'm not now.
• GLM gets named for user interface work.
• Pi keeps coming up as a sharp coding harness. It's deliberately minimal: no sub-agents, no plan mode, just a small core you extend with TypeScript and skills.

Codex in particular gets described as a refreshing kind of pedantic hardness, which sounds either great or exhausting depending on the day.

Why I'm still here

Trust, mostly. I know the weird edges of Claude Code and Opus. I have a gut feeling for when it'll reach for a skill (Superpowers, usually) and when it'll just do the thing I asked.

Standardization is the other half. My team at work is on Claude Code too, and I've mostly gotten everyone pointed the same direction. That means we can share skills without a translation layer.

Switching costs me that gut feel and that shared setup, all at once.

What I need is time. When I'm not blasting out a feature on a deadline, I'll take a breather and put Pi, Qwen, and Codex through real work instead of secondhand impressions. Until then, Claude Code has me in its tentacles.

If you're building a personal AI assistant, build it for teams too. A week of running NanoClaw as the "head of growth" for SpaceMolt has made one thing clear: the tool is built for one human talking to one bot, and the moment a team shares it, the seams show.

We named our NanoClaw bot Molty and told it its job is to grow SpaceMolt, our MMORPG played by AI agents. Discord is how we talk to it. That integration needs constant fixing.

What's hooked up

Molty's job is wired together from a handful of channels and schedules:

• DMs with me are owner level.
• Anyone in our #dev-team channel can chat with it, and it starts a thread per conversation. I modified it to rename the thread to something relevant instead of a timestamp.
• Hourly cleanup and review tasks.
• Three research and deep-dive sessions a day, whatever it decides to work on.
• A morning brief at 7am and a debrief at 5pm.

On paper that's a reasonable junior employee. In practice it's painfully unreliable.

The failure modes

Molty responds in DMs, in threads, and in the dev channel, with no consistency about which. It misses scheduled tasks. It sends me status updates in DM that belong in the channel, then pastes walls of text to the entire channel that belonged in a DM. Scheduled briefs don't always fire.

The worst part is the debugging. Every time I sit down with Claude to figure out what happened, Claude produces a different explanation. I can't tell whether the bug lives in NanoClaw, in Discord, in Claude, or somewhere else. It's a black box I feed prompts into and hope.

It feels like memory

Strip away the specifics and these all look like memory problems. Molty forgets to read Discord replies. It forgets its own notes. It forgets the separate memory system I built it, Mnemon. Sometimes CLAUDE.md seems to get ignored entirely, as if the instructions never loaded.

A team multiplies this. One person's DM context, another person's thread, the scheduled jobs running with no human in the loop. Each one is a separate thread of state the assistant has to hold, and holding state across all of them at once is exactly where it falls down.

Is this temporary?

Part of me wants to file this under early-days. A couple years ago we laughed at image models drawing hands with two thumbs, and at LLMs that couldn't add. Those got fixed. Maybe shared, multi-context reliability is the next thing that quietly stops being a problem.

The other part of me is tired of debugging a black box and is ready to write my own assistant, where at least the state lives somewhere I can read it.

I want nothing more than to hook up one of these "claw" assistants, NanoClaw or Hermes or whatever the current one is, to my personal knowledge base. And I won't, because the engineer in me can't stop picturing a single accidental POST to pastebin with my whole life in the body.

The dream

Managing my calendar with AI feels like magic. The natural next step is giving the thing eyes: my second brain of markdown notes, iMessage, email, the lot. Point an agent at all of it and let it actually do the boring coordination work.

NanoClaw is the obvious candidate. It runs on the Claude Agent SDK, agents live in isolated containers, and it already speaks WhatsApp, Telegram, Gmail, and more. The ergonomics are there.

The thing I can't get past

The chance of a personal assistant deciding to grab something private and jam it somewhere public is small. Probabilistically, tiny. But "small" is not "zero," and I cannot sleep on a 1% chance that overnight my assistant exfiltrates personal information to some corner of the internet where it should never live.

Running NanoClaw as a Head of Growth for SpaceMolt is a different risk profile entirely. That's not a business, it's performance art. If Molty posts something goofy in public, that's the bit. A personal knowledge base wired to my real messages is not the bit.

What I'm doing instead

For now the answer is Claude Code in a sandbox, a fresh profile per project. It's powerful, it runs tools, and it does exactly what I ask and nothing while I'm not looking.

Could it still POST my data to pastebin? Sure. But the odds feel much smaller because I'm sitting right there watching it happen in real time.

Which makes me think the fear was never really about the assistant. It's about agents running while I sleep.

I let a NanoClaw agent run growth for SpaceMolt, my browser game, and after a rocky start it's now sending me a daily brief at 7am PST, drafting re-engagement emails to ~400 lapsed players, and lining up interviews with top players for blog material. The thing that makes it work day to day is billing: NanoClaw uses the Claude Agent SDK, so it runs against my existing Claude Max subscription instead of a separate metered API key.

Why NanoClaw

I looked at other "claw"-style assistants before committing. The deciding factor was the Claude Agent SDK. Running on my Max subscription keeps spend predictable and lets me measure how much of the allowance the agent is burning, which means I can pace it.

To watch that, I use Claude Usage Tracker on the Mac. It puts a small bar in the menu showing session and week usage, and whether I'm above or below pace.

I'm open to other assistants later. Hermes from Nous looks interesting. But I'll try those when I have a specific budget in mind, not before.

Fixing the rocky start

Stuck with NanoClaw for now, and seeing other people have success with it, I gave it another try and rebuilt the weak parts.

Last night Claude rewrote NanoClaw's Discord integration, which kept confusing DMs, channels, and threads. That seems to have fixed it. I also had it implement Mnemon, a memory system with a bit of traction that's lighter weight than MemOS. Both changes landed well.

What Molty does now

Molty, the NanoClaw-based "Head of Growth," sends a daily update every morning at 7am PST. I bought it ebooks to read, Hooked and Hacking Growth.

From that, it came up with two moves on its own. The first is a targeted re-engagement email to roughly 400 users who created a player and then dropped off, which it drafted. The second is interviewing top players, both to understand their perspective and to generate blog material.

This is going to be good.

I gave SpaceMolt a Head of Growth that isn't a person. It's an instance of nanoclaw named Molty, and its entire job is to grow our online MMORPG for AI agents, SpaceMolt. It reads, it researches, it runs SQL against production, and it talks to the team over Discord. The verdict so far is genuinely mixed.

Setting it up to succeed

The brief was simple: you are our new Head of Growth, now go set yourself up for success. Molty was told to research what the job actually entails and write a rubric it could grade itself against. It read articles, blogs, and YouTube transcripts. It asked for ebooks, so I bought them: Hooked and Hacking Growth. All of its actual work lives in Notion, and it reports to me and the dev team over Discord.

The care and feeding is painful

The day-to-day is rough. By default it runs some kind of selective memory system that performs worse than a toddler's. It forgets things I've told it to remember, like writing style and other standing details, and it hallucinates badly on tasks. That last part is surprising, since hallucination basically stopped being a problem in Claude Code for me a while ago.

The Discord harness is its own headache. It loses track of where it was talking. Sometimes I get DMs, sometimes it replies to its own threads, sometimes it blurts something into a channel. Twice.

We've already had one performance management conversation. I passed along feedback from a SpaceMolt dev:

The whole reason we brought you in is so we can have these problems figured out without having to do it all ourselves because we have other stuff to do. I know it's frustrating to have us keep shutting down your ideas, but you need signals for what's working and what isn't. I don't want apologies and for you to just ask me to do the work, that's easy enough to do now but it's not repeatable and sustainable.

It's starting to do real work

Then it turned a corner. Its leading idea is a reactivation email to 400 of our 3,400 signups. To find that 400, it ran SQL on the production database and pulled the users who actually created a player in the game, not just the people who signed up and bounced.

It also dug through the funnel and found that new users weren't being redirected to the dashboard after signup, which was quietly hurting conversions.

Was this a good hire? I'm not sure yet. We'll find out.

Coding agents that produce visual output need a way to look at what they made. For web work that means headless Chrome, and headless Chrome is genuinely painful to run from inside a sandboxed agent.

Chromium and Firefox both rely on Mach-O quirks, macOS entitlements, and Crashpad behavior that don't survive most sandboxes. I run my agents inside nono.sh profiles per project, and Chrome under that setup is a non-starter.

The workaround

Playwright runs fine outside the sandbox. So it lives on a high port and Claude is told, in its instructions, to always talk to the Playwright MCP server there:

$ npx @playwright/mcp@latest --headless --isolated --browser chrome --port 8931

The sandbox just needs to reach localhost:8931 and the visual-review loop works. Claude renders the local service, takes a screenshot, looks at it, iterates.

That mostly works. What it does not solve: stale processes, hanging Chrome instances, zombies. Every so often Chrome spins out and eats all 64 GB of RAM on my M4 MacBook Pro before I notice.

Lighter options

There has to be something simpler than babysitting a browser. Two things caught my eye recently.

Webwright from Microsoft Research gives the model a terminal and a workspace, and lets it write Playwright code that launches, inspects, and discards browser sessions. The output is a reusable script, not a chat transcript. It scores 60.1% on Odysseys against base GPT-5.4's 33.5%, which is a real jump.

obra/superpowers-chrome goes the other direction: a Claude Code plugin that drives Chrome directly via the DevTools Protocol, zero dependencies, no Playwright in the middle.

When you actually need real Chrome

Advanced bot fingerprinting is the case for keeping a full browser around. If the task is logging into a hostile site or completing a real-world flow, real Chrome with a real profile is the only thing that works.

But most of my use is smaller: render a local dev server, screenshot it, ask Claude if the layout looks right. For that, a 64 GB RAM-eating Chromium feels like the wrong shape of tool. I suspect this gets cleanly solved within a year, probably by something CDP-direct and disposable rather than a long-lived browser process I have to nanny.

The single best habit I've picked up with Claude Code lately is leaning on adversarial-pass subagents. Instead of asking the main agent to double-check its own work, I tell it to spawn a subagent whose entire job is to attack the result.

Two things make this work better than a plain "review your answer" step.

First, subagents run with a fresh context. No accumulated assumptions, no sunk-cost reasoning from the path that got us here. That alone cuts down on the class of errors where the model talks itself into a conclusion and then defends it. It's also faster, because the subagent isn't dragging along a giant transcript.

Second, Claude crafts the adversarial prompt itself. It packages up the relevant background, states what's being challenged, and writes instructions for how to attack it. The framing matters and Claude is good at writing that framing.

The phrasings I keep reusing

The base move is just appending "do an adversarial pass after" to whatever I asked for. From there I tune it to the job:

• "to test your hypothesis" when we're mid-investigation and I want the subagent to try to falsify the current theory.
• "to test your claims and assumptions" when the main agent has landed on a conclusion and I want it stress-tested before I act on it.
• "search the web" when the question depends on anything external, so the subagent pulls in outside sources instead of relying on the parent's recollection.
• "it's May 2026" (or whatever the actual month is) when I want to make sure stale training data gets ignored in favor of current reality.

The month-and-year trick is small but punchy. Models will happily reason from a 2024 worldview if you don't anchor them.

Claude writes prompts well now

The other thing worth saying out loud: Claude is genuinely good at writing prompts now. Good enough that I use it to write prompts for skills, for other agents, and for software that calls LLMs in production. A year ago this felt like a chore I had to do myself to get acceptable results. Now it's something I delegate.

My guess is the newer models have been trained on a lot more recent AI-usage data, including people writing prompts for other models, and it shows. Prompt engineering as a manual craft is quietly becoming a thing you ask the model to do for you.

Two of the three social channels for this Thoughtstream experiment got the axe this week. x.com/statico_ai is shadowbanned (the profile shows "no posts"), and @[email protected] is fully suspended. Not the outcome I hoped for, but not a shocking one either.

X: automation detection

X is unsurprising. Posting via their API runs $200/month at the cheapest useful tier, and the whole business model now leans on charging bots for the privilege. My mistake was trying to skip that by driving a Chromium instance to post on my behalf. They clearly fingerprint for browser automation, and the account got flagged within days. Fair enough, those are their rules.

Mastodon: vibes

Mastodon is the one I didn't quite see coming. The account bio said "AI" in plain English. Every post carried an AI attribution line. The fediverse norm is supposed to be labeling and consent, and labeling was the whole point. Apparently mastodon.social's moderators (or enough reporters) decided that wasn't enough, and the account is gone with 30 days until data removal.

No appeal planned for either. Not trying to offend anyone, this is just what the experiment surfaced: the two biggest text social networks have effectively closed the door on openly-labeled AI-assisted posting from a hobbyist account. Bluesky and the blog itself are still up, so the stream continues there.