I verify what my Cowork memory claims instead of trusting its timestamp
Persistent memory keeps asserting whatever was true the day you wrote it. After an unattended job quietly read an empty folder for months, I stopped judging memory by its modification date and started attaching a verification step to every claim that can rot.
The 30-Day Session Cleanup Is Fixed, and It Made Me Rethink Where I Keep Records
Claude Desktop and Cowork sessions were quietly disappearing after 30 days until v2.1.248 fixed it. Here is how to check your own setup, what the new setting actually caps, and a small journal script that keeps one line per run outside the session.
The lock I left in a shared folder shut out every run after the first
A cloud-synced connected folder allows create, append, and rename, but refuses delete. Putting a single-instance lock there quietly disabled every unattended run after the first. Measurements for three lock styles, plus an implementation that picks a safe location.
I counted the keys in my connected folder: filenames found 5 of the 18
A record of counting what lives inside a connected folder, once by filename and once by file contents. Filenames returned 24 hits of which only 5 were real, while a content scan returned 18 of which 13 left no trace in their names. Includes a scanner that never prints a secret, its real output, and the rules I adopted afterwards.
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.
Localizing an App Store Screenshot PSD into 15 Languages Overnight with Cowork
A work log of localizing the store screenshots for the Android wallpaper app 'Beautiful Wallpapers' into many languages with Cowork: extracting text with psd-tools, pouring translations into layer names, and the real walls I hit with Thai and Korean glyphs.
Claude in Chrome Not Working? A Practical Troubleshooting Guide
Buttons that do nothing, pages that never load, tasks that report success but change nothing. Symptom-by-symptom fixes, plus the 42-run log where adding waits and verification steps moved completion from 62% to 95%.
Why Cowork Scheduled Tasks Stop Mid-Run and How to Recover
Diagnose Cowork scheduled task failures using measured exit codes and real error output — why safe.directory delays failure instead of fixing it, how to pick a writable root before cloning, and how to structure logs with reason codes.
Codify Your Writing Voice as a Cowork Skill: A Personal Brand Style Guide Pattern
How to capture your own writing voice — vocabulary, rhythm, structural quirks — as a Cowork Skill, using a three-step loop of observation, SKILL.md authoring, and falsification testing, plus a small helper script that turns the numbers into a list of places to re-read.
Canva × Claude in Practice — Saving Generated Candidates, Picking a design_type, Committing Edits
The parts of the Canva AI connector that actually trip people up in Claude: why generated designs are not saved yet, how to pick a design_type, why editing is a transaction, and what to check before exporting.
It Worked on My Machine, but Nobody Could Trigger It — Four Assumptions I Stripped Out of a Cowork Plugin
I bundled four working automation skills into a plugin and shared it. Only one of them ever fired. Here is how I measured skill trigger rate, and the four assumptions — vocabulary, paths, connections, and naming — I had to strip out before it was portable.
The Night a Connector Grew Write Tools, Your Unattended Job Could Quietly Send Something
The moment a connector update quietly adds write tools, a job you run unattended can suddenly send email or delete files. Here is how to build a gate that snapshots a connector's tool surface, diffs it, and stops unapproved writes before they run — drawn from indie development.