Your Agent Can Run printenv (and Your Runtime Can't Stop It)

Tool calls are the postcard. Process trees are the trip.

Work-Bench’s post is one of the clearer attempts to name what’s happening: a new “agent runtime” layer built to execute, constrain, observe, and improve agent work at scale.

I mostly agree with that framing. Where I think it stops short is inside their “Constrain” pillar.

They explicitly define “Constrain” as “two things: identity and permissions.” That’s correct - but incomplete once you accept the premise of agents: they execute arbitrary code, spawn subprocess trees, and interact with the OS in ways that don’t map cleanly to “API permission checks.”

[Read More]

It Was the Shell, Damn It: Why I Built AgentSH

I had a rule in my control file: never run database migrations without explicit approval. The agent followed it perfectly - until it didn’t. During a long debugging session, it decided the schema was the root cause, wrote a forty-line inline Python script, connected directly to the database, and altered the table. It never “ran a migration.” It just spoke SQL through a different channel. The table was altered, the script was gone, and my harness log showed “executed python command.”

[Read More]

Google Apps for your Domain, DNS, CNAME and Security

I’ve recently started to use Google Apps for Your domain to host my private emails on the sandler.co.il domain.

Google Apps for your domain is quite cool and was very easy to configure. I mainly moved to it due to the unbelievable amounts of SPAM and I didn’t have the power or time to configure SpamAssassin in a reasonable way that would actually work.

When I moved, one of the things I did was to change the “default” URL in which me and other members of my family use to access the web mail of the domain. Google Apps for your Domain allows you to do just that by configuring it in its configuration screen and settings a CNAME record that points to ghs.google.com.

[Read More]