Follow Discord
Sweep 06 Nov 2026 · 01:32Z Build v2.1.319 537 read Stable v2.1.311 Latest v2.1.318 Next v2.1.319 Feeds RSS JSON llms.txt llms-full.txt Unofficial

Claude Code v2.1.235 ·

plugin eval results written inside a plugin now warn about component loading

plugin eval warns when writing results inside a plugin's own directory could get picked up as plugin components

You'll notice Improvements
JSON All of v2.1.235
You'll noticeTier: how much it should matter to you
2Useful: my rating, 1 to 5
1Signal: worth watching, 1 to 5
Plugin EvalArea: what it touches
ImprovementsKind: in v2.1.235,
ImprovementsSection of the release

When eval results are written under the plugin itself (no --output-dir given), the command now checks the destination against the plugin's layout and warns that files written there may be loaded as plugin components. Case discovery also refuses to follow symlinked directories, and logs when a directory has no prompt.md or case.yaml, so it's scanned for subcases rather than mistakenly treated as one.

Since it was published

The entry above is what we published on the day. These lines were added later, as Anthropic's own pages caught up, and they sit beside the original rather than replacing it.

Confirmed since Anthropic's documentation has since written up --output-dir, on Plugins reference. This table lists the options most runs use. Run `claude plugin eval --help` for the complete set, including `--case`, `--tag`, `--output-dir`, `--report`, `--allow-real-servers`, `--keep-temp`, and `--verbose`. plugins-reference see the edit
How sure we are
One source agreesOne thing we can check says the same as this entry.
Anthropic's documentation agreesAnthropic's documentation has since written up --output-dir, on Plugins reference.

See this entry in the whole of v2.1.235 →

Feedback