CLAUDE LABJP
2.1.269 — A broad release with 98 CLI changes. The one worth your attention is claude plugin eval, which finally lets you measure whether a plugin earns its placeEVAL — Every case runs three times with the plugin loaded and three times without, so the number you get back is the difference the plugin makes, not just a pass or a failGRADER — Three kinds of grader are available: a regex over the reply, a check for whether a particular tool was called, and a rubric judged by a second modelDIFF — The Bash tool result now includes a diff of the files a command changed. Turn it on with bashEditDiffEnabledSTYLE — /output-style [name] lists and switches output styles, including over Remote Control and in cloud or headless sessionsOTEL — OTEL_METRICS_INCLUDE_REPOSITORY tags metrics and events with vcs. repository attributes, and commit events carry vcs.ref.head2.1.269 — A broad release with 98 CLI changes. The one worth your attention is claude plugin eval, which finally lets you measure whether a plugin earns its placeEVAL — Every case runs three times with the plugin loaded and three times without, so the number you get back is the difference the plugin makes, not just a pass or a failGRADER — Three kinds of grader are available: a regex over the reply, a check for whether a particular tool was called, and a rubric judged by a second modelDIFF — The Bash tool result now includes a diff of the files a command changed. Turn it on with bashEditDiffEnabledSTYLE — /output-style [name] lists and switches output styles, including over Remote Control and in cloud or headless sessionsOTEL — OTEL_METRICS_INCLUDE_REPOSITORY tags metrics and events with vcs. repository attributes, and commit events carry vcs.ref.head
ARTICLES

All Articles

All (863) Claude AI (137) Claude Code (370) Cowork (60) API & SDK (296)
Cowork/2026-09-09Beginner

Using Aqua Voice for Cowork and Everyday Messages — What Changed When I Started Speaking Instead of Typing

I use the dictation app Aqua Voice for briefing Cowork and for messages and email on my iPhone. Notes on how the texture of my writing changed before its speed did, how Mac and iPhone use differs, and what still gets in the way.

Cowork/2026-09-08Advanced

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.

Cowork/2026-09-05Advanced

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.

Cowork/2026-08-29Advanced

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.

Cowork/2026-08-24Intermediate

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.

Cowork/2026-08-23Advanced

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.

Cowork/2026-07-17Advanced

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.

Cowork/2026-07-12Advanced

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.

Cowork/2026-07-11Intermediate

Make Your Nightly MCP Connectors' Health Visible — A Lightweight Ledger for Solo Operators

You don't need Enterprise connector observability to see your MCP connectors' error rate and latency. Append one line per tool call, roll it up weekly, and let regressions ring a bell. A working health ledger for anyone running scheduled tasks solo.

Cowork/2026-07-05Advanced

The Two Weeks My Web Monitor Said Everything Was Fine — Field Notes on Catching Silent Misses

A competitor monitor built on Cowork and Claude in Chrome can keep reporting no changes while quietly missing them. Here is how I separated fetch success from extraction success and instrumented the silent failures, with the code I actually run.

Cowork/2026-07-05Intermediate

When Claude Declines a Request on Safety Grounds, What Should an Unattended Pipeline Return?

A third kind of ending that is neither an error nor a normal completion — a safety decline. Here is how to fold it into a pipeline you run unattended, with a classifier and a review-queue design drawn from indie development.

Cowork/2026-07-02Advanced

How Many Tasks Fire in the Same Minute — Flattening Cowork Scheduled-Task Collisions from Cron

When Cowork scheduled tasks bunch up at the same time and fight over shared resources, you can expand every cron expression into fire times, count collisions and true concurrency, and shave the peak with a greedy offset that never moves your premium slots. With working code and measured before/after numbers.