All Articles
Before You Trim a Scheduled Task's Runbook, Count How Many Times It Gets Re-read
I cut 13 KB from a scheduled task's preloaded docs, and recounted by re-reads it was worth about 1.3 tool calls. Here is the ledger that counts re-reads, and a shell helper that records bytes during a run.
Two Default-Model Changes Haven't Reached Claude Code's Stable Channel Yet
This morning, Claude Code's stable channel sat 6 releases and 10 days behind latest. A small standard-library Python script that counts the gap in real, published releases instead of version arithmetic, and lists what hasn't arrived yet with a headline for each.
The Night Claude Returned 529, My Fallback Failed Too — Strip cache_control at the Provider Boundary
My Claude API fallback threw a TypeError because content blocks still carried cache_control when they reached another vendor. Here is the stripping function, the pre-send guard, and the weekly forced-fallback routine that finally made the fallback a real safety net.
The Week Opus 5.5 Became the Default, I Counted the Places I'd Left as Aliases
Claude Code 2.1.280 made Opus 5.5 the default Opus and moved Pro's default from Sonnet to Opus. Before touching a single setting, I checked three things: what the alias resolves to, whether a saved /effort carries over, and what $0.20 cache reads do to a monthly estimate. Scripts included.
Will Your Cowork Scheduled Task Still Run Next Saturday?
A definition that runs once and stops, two fire times packed into one task, a weekday that quietly emptied after an edit. Cowork schedules can go missing without leaving a single log line. Here is a working audit that compares what you defined with what you meant.
Write Access Came Third: The Order I Hand Folders to Cowork
When I connect a folder to Cowork I open it in three steps: read-only, a place where new files may appear, then write access. Here is the line I drew with a client's asset folder, and the three things I settle before connecting.
Character counts won't predict PDF input tokens — bracket the cost per page before you send
How to estimate the input tokens of a PDF before sending it to the Claude API, by bracketing from page count rather than character count. Includes a measured 6.6x gap on a nine-page A4 document, the two separate increases that come with current models, and the count_tokens limitation that bites when you use file_id.
Taking Inventory of Worktrees That Were Supposed to Be Gone
Isolated worktrees my subagents created were never folded away. Here is what I measured in git 2.34.1 about when remove succeeds, the branches that outlive the trees, the 12 MB per-tree difference, and how I decide who owns cleanup.
The morning a deprecation notice appeared, I checked versions before editing config
Claude Desktop and Cowork stop accepting older managed-configuration spellings on October 7. Here is how I sorted mine into what to fix now, what to fix after upgrading, and what changes meaning on its own.
I Was Paying for Pro and Still Getting Billed by the Console
Your subscription and your API usage are two separate ledgers, and Claude Code will happily run on either one. Which credential wins is decided by a precedence list where your login sits dead last. Here is how to read status, and why unattended runs answer differently.
When a proofreading request comes back as a rewrite: keeping the original wording
Ask for proofreading and you often get a polished replacement instead. Fixing the output shape first, splitting edits into three layers, and showing one keep-and-change example pair will hold on to the author's sentence endings and word order.
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.