Sweep 19 Sep 2026 · 02:36Z Build v2.1.278 500 read Stable v2.1.267 Latest v2.1.278 Next v2.1.278 Feeds RSS JSON llms.txt Unofficial
Claude Code v2.1.269 ·

'claude plugin eval' gains --allow-real-servers and concurrency options, plus harness-failure tracking

'claude plugin eval' adds --allow-real-servers and concurrency options, plus separate harness-failure tracking

TierUse it nowhow much it should matter to you
Useful4my rating, 1 to 5
Signal2worth watching, 1 to 5
AreaPlugin Evalwhat it touches
KindNew Featuresin v2.1.269,
Use it now Notable

'claude plugin eval' adds --allow-real-servers and concurrency options, plus separate harness-failure tracking

What

The claude plugin eval command now accepts an allowRealServers option and a concurrency option, both passed through to the eval runner. It also now tracks harness failures (errors in the eval tooling itself) separately from case failures, and fails the run distinctly, recording a harness_failure event, when the harness itself errors rather than when individual test cases fail.

Why

Separating harness failures from case failures makes it clearer whether an eval run failed because of the code being tested or because of a problem in the eval tooling itself. The new options give more control over whether real (non-mocked) servers can be used and how many cases run concurrently.

Read from
Names in the bundle--allow-real-servers--concurrency
What the documentation says
How sure we are
Two sources agreeTwo things we can check say the same as this entry.
Anthropic's release notes agreeAdded claude plugin eval: run a plugin's eval suite against Claude Code and get scored, reproducible results (JSON + HTML report); see…
The name it cites is new in this buildNew in this build: --allow-real-servers

See this entry in the whole of v2.1.269 →