Shipmates on Luther Monson

Your Agent's Shell Allowlist Is Bypassable

Tue, 29 Sep 2026 20:30:00 -0700

Every shipmates crew member runs shell commands. Before any of them runs, it goes through a permission gate. The gate uses the same rule syntax as Claude Code settings: Bash(git status), Bash(rm *), Write(**/.claude/settings.json). The rules are merged from several layers:

a fleet-wide deny list pushed from Fleet Command
per-persona policy files
project settings
the Brig, which compiles shipmates’ fifteen “Ship’s Articles” into deny and ask rules

Deny beats ask, ask beats allow.

Cross-Platform Process Containment: Job Objects vs Process Groups vs cgroups

Sat, 26 Sep 2026 16:20:00 -0700

Every turn a shipmates crew member takes is a subprocess. It’s claude or the codex app-server. That in turn spawns shells, go test, npm or whatever the task calls for. Two things have to be true about that tree. When a turn ends or gets killed, the whole tree goes, including the grandchildren. And if somebody sets a memory or CPU budget, the budget applies to the whole tree, not just the process I happened to start.

A 1 TB Test: Building a Memory Watchdog for go test

Tue, 22 Sep 2026 20:48:00 -0700

On August 16th a server.test.exe from shipmates climbed to roughly 1 TB of commit charge on my Windows workstation. Windows Terminal was hosting several agent sessions in tabs. It hard-faulted with E_OUTOFMEMORY, and every one of those sessions died at the same moment. It wasn’t the first time either. An earlier one hit about 236 GB through an infinite filepath.Dir loop.

The machine has 128 GB of RAM. Commit charge doesn’t care. It’s backed by the page file, and Windows will happily let a process reserve-and-commit until the commit limit is gone. Then everything else on the desktop starts failing allocations too.

os/exec's StdoutPipe Footgun: How cmd.Wait() Ate My Last Frame (Twice)

Thu, 17 Sep 2026 20:12:00 -0700

shipmates spends most of its life spawning claude (and codex) processes and reading newline-delimited JSON off their stdout. The last frame of a turn is the important one. It’s a result frame with the cost, the model and the final text. Stderr matters too, because that’s where Claude Code tells you Invalid API key · Please run /login. For a while I was throwing both away under load. The cause is documented right there in the os/exec godoc. I fixed it in one package and then found the exact same bug again a month later in another.

shipmates Short Ones: 8 Minutes Extracting Go, and Three Voice-Loop Bugs

Sat, 12 Sep 2026 14:35:00 -0700

A few shipmates bugs don’t need a whole post each. They were too good to leave in commit messages, though.

setup-go spends 8 minutes extracting Go on Windows CI

shipmates CI runs on my own ephemerd runners. On Windows those jobs run inside a Hyper-V utility VM. The windows-x64 leg kept timing out in actions/setup-go. Here’s the log from PR #48:

20:58:46  Setup go version spec 1.26.6
20:58:46  Attempting to download 1.26.6...     <- tool-cache MISS
20:58:48  Acquiring 1.26.6 from ...zip
20:58:53  Extracting Go...
21:06:46  ERROR: The action 'Run actions/setup-go@v5' has timed out after 8 minutes

Seven seconds from the start of the step to Extracting Go.... Then almost eight minutes extracting until the step timeout killed it.

Finding a Data Race in rancher/remotedialer, Then Pinning Only Two-Thirds of the Fix

Tue, 01 Sep 2026 21:05:00 -0700

shipmates ships connect to Fleet Command over outbound websocket tunnels. That way nothing on the ship side has to be exposed to the internet. I didn’t write that tunnel layer. I used rancher/remotedialer, the same library Rancher uses to reach downstream cluster agents. I spent years around that code at Rancher, so it was the obvious pick. What I didn’t expect was for my CI’s race job to find two data races in it in the first week.

shipmates: Persona-Based AI Coding Crews That Remember

Fri, 21 Aug 2026 21:18:00 -0700

Since June most of my evenings have gone into shipmates, a Go CLI and daemon for running crews of AI coding agents. I tagged v0.5.0 on August 17th. That was two months and about 240 commits after the first architecture doc. So it’s a good time to write down what it is and why it exists.

The problem

I run a lot of agent sessions. On a normal night this workstation has four or five projects going at once. Each has a few Claude Code sessions doing different jobs: one reviewing, one writing tests, one chasing a bug. Two things kept annoying me.

Atomic File Replacement on NTFS Is Not rename + fsync

Thu, 06 Aug 2026 21:27:00 -0700

shipmates writes a lot of small state files that other processes read. Voyage plans and state, tracker files. Each of them has to be replaced atomically, so a reader sees the old file or the new one and never half of each. Each also has to be replaced durably. When the function returns success, a power cut doesn’t take it back. Every Unix programmer knows the recipe for that. It doesn’t work on Windows, and the reasons are more interesting than “Windows is different”.