Omarchy Runs Your Coding Agent With the Safety Off
Omarchy's launcher gives every coding agent a skip-approval flag by default. The attack surface a security lead inherits, and what Omarchy gets right.
We can't find the internet
Attempting to reconnect
Something went wrong!
Attempting to reconnect
Writing · Tag
56 posts on agents, page 2 of 5. Or browse the full writing index →
Omarchy's launcher gives every coding agent a skip-approval flag by default. The attack surface a security lead inherits, and what Omarchy gets right.
I set two agent frameworks loose on real work in team-of-agents mode. They agreed their way into the wrong product. The research says exactly why.
Omarchy's own AGENTS.md, skills, and a design doc reviewed by two other vendors' agents, read from the quattro branch instead of the README.
Ecto schemaless changesets as the pre-execution trust boundary on LLM tool-call arguments, not another output-shape validator.
Agents stop before the work is done, not because the model is lazy but because nobody built the management system a human employee gets for free.
How Oban actually fetches jobs, notifies workers, and elects a leader, plus the VACUUM cost nobody mentions. Read from oban-bg/oban v2.23.1, not the README.
Compression toward machine-preferred notation isn't a future bet. It's already landing in context formats, agent protocols, and the files your harness reads.
The two documents an enterprise reviewer wants for your AI agent, the allow-list and the tool-call log, specified field by field and generated from code.
José Valim's case for Elixir as a coding-agent harness holds up on the runtime. The tax is the ecosystem around it: sandboxing, plugins, and SDKs.
Telling a junior to use less AI is advice with an expiry date. Move the quality bar off style and onto verification. Here's what that looks like.
Senko Rašić is right that “code was never the hard part” insults programmers. Peter Naur explained what it actually gets wrong, in 1985.
Return-to-office mandates are what companies reach for when they can't measure output. Agents just destroyed the last proxies that were limping along.