Your agents worked all afternoon. What did each one ask to do, and who answered it?
ACTower's decision log keeps every request with its own ID, per pane, and who answered it: ACTower's rules, Autopilot, you in ACTower, or you in the terminal.
It stays on your machine.
It's been nearly 6 months since I posted a 'watch me work' deep dive on my skills.
Since then, they've become the most-starred skills repo in the world.
So, here's 70 minutes of me building a 21,000-line PR, especially focusing on:
- DDD with /grill-with-docs
- Improving your codebase with /retro
- How to do human review effectively
Enjoy!
@Libes66@Damianships@peteralexbizjak 🙂Apples and Oranges.
Do you always need SEO? I built many Flutter web app “Dashboards” for clients. Paired with mobile apps, no SEO, just a single page web app, lots of code and package sharing. Ready for desktop.
Restarting a long Claude Code session by hand: ask for a handoff, start fresh, paste it back.
ACTower does all three: past your token limit, after ten quiet minutes, it asks for the handoff, restarts Claude Code and gives it back.
Off by default. Each auto restart is logged.
@Damianships@peteralexbizjak There are still plenty of use cases where you should go with Flutter. I have an app with web Dashboard and mobile app. Flutter let me share lots of domain and UI code. I can add desktop support easily if needed.
ACTower 1.3.7 is out.
The Responder, redesigned around what needs you: your questions on top, Autopilot's folded below, busy panes one click away.
Also: a calmer Auto Restart, and Autopilot answers more on its own.
Takeaways:
Loading a skill ≠ the model following it
Verify the process, not just the output
Ask for evidence: failing test output, order of changes, etc.
One experience, not a benchmark. Curious how the @antigravity team thinks about enforcing skills in the harness.
Today I was working with Gemini 3.8 Flash in @antigravity, with a TDD skill loaded.
The model read the skill, then quietly skipped it.
@googleaidevs a short thread on what happened 🧵
Model or harness? My read: mostly the model.
The skill loaded fine. The model knew the rule and still broke it.
But the harness isn’t fully off the hook: a skill is just text in context. Nothing enforces “no code before a red test.”
@0xVatsaShah I am using herdr with multiple agents, Claude, Codex, Agy… They spawn each other for MoA workflows. So CLI is still the sweet spot for me.
Some agents in tmux, some in #herdr. Now you have two places to check who is waiting on you.
ACTower works with both: their questions land in one queue, safe ones get approved automatically, the rest wait for you.
Keep the setup you like. Where do your agents run?