How I decide between Cowork and Claude Code: by where approvals land
Cowork and Claude Code run the same Claude, so I stopped comparing features and started sorting work by one question: can a human approval interrupt this step, or not? Here is the line I draw and the code I keep on the unattended side.
The scheduled task that only ran on days my desk was awake
Cowork scheduled tasks run remotely by default, but the moment one needs a local file or app, it runs only on your machine. Here is how the last field in the setup dialog decides that, and the three questions I now answer before creating a task.
Until I planted a failing sample, my unattended checks had never once failed
A check running on an unattended schedule lost its exit code to a single pipe added for readable logs. I measured where the status disappears and built a small harness that checks the checker.
Two hooks that record every model switch and stop the ones you never agreed to
Build a PostModelSwitch hook that logs every model change and a PreModelSwitch hook that blocks unapproved switches during unattended runs. Complete scripts, measured timings, and the reason the two jobs must stay separate.
Drop the quotes on a heredoc and the prices in your log quietly change
An unquoted heredoc runs the variables and backticks inside its body. Here are the four ways my log got rewritten, how the three quoting forms compare, a safe placeholder-and-sed pattern, and a small script for auditing what you already have.
Half of My Scheduled Runs Vanished Without a Single Error
A batch job set to run twice a day was only firing once. No errors, no failure alerts. Here is how to expand your own schedule, count expected runs, and reconcile them against execution records to catch silent misses.
Don't let your verification script's full output flow back through a hook
The check was working the whole time. The conversation was what ran out of room. Measured side by side: 58 bytes from one scan of 833 files, 42KB from another. Which paths actually reach the model, and how to enforce a budget on them.
Trusting the allow rules in your repo, or moving them to the environment
On disposable machines, the permissions.allow rules committed to your repo are dropped while the workspace waits to be trusted. Here is what gets dropped and what survives on 2.1.246, where each kind of rule belongs, and a preflight that catches the gap before a run starts.
A One-Letter Typo in settings.json Is Ignored Without a Single Warning
I diffed claude doctor output between a settings.json with misspelled keys and a correct one. There was no difference at all. Here is what actually gets validated, what slips through, and a small check that catches typos before they cost you a day.
One Space in a Folder Name Turned 80 Checks Into Zero
An inspection loop reported 80 files checked and 0 readable. The files were fine. Here is how word splitting turns path fragments into real directories, measured side by side, plus the count assertion I now put in front of every delete-heavy batch.
Not Every Unreachable Connector Means the Same Thing in an Unattended Run
When an unattended task cannot reach a connector, the cause splits into three states: still connecting, unauthenticated, or genuinely absent. Each demands the opposite response. Here is the resolver that tells them apart.
Handing a long job to another session — and the completion marker for when the notification never arrives
How to use notify_when_idle to hear when another Claude Code session finishes, and a small completion marker that keeps you from waiting forever when the notification is dropped.