Agent plugins finally got a test runner. claude code shipped plugin eval, which runs your plugin…
agent plugins finally got a test runner. claude code shipped plugin eval, which runs your plugin against a suite of cases, scores it, and compares against a no-plugin baseline, with eval init drafting the cases and graders for you.
plugins stopped being unverifiable glue.
Context
The Claude Code v2.1.269 release, published 11 September 2026, says it added claude plugin eval, which runs a plugin's eval suite against Claude Code and returns scored, reproducible results as JSON and an HTML report. A third-party tutorial says claude plugin eval init reads the plugin and proposes cases and graders, and that running the eval does three runs with the plugin and three without and reports the two scores and the delta, and that eval sessions consume plan allowance or API billing.
The release note supports the eval command only. The no-plugin baseline and the init drafting come from the third-party tutorial and not a first-party doc, which was not found in the docs pages read. The release is dated 11 September, before the note. Three runs per case is a small sample by the tutorial's own description. Plugins stopped being unverifiable glue is the author's thesis.
Watch next
- First-party docs for plugin eval.
Sources
- Claude Code v2.1.269 release (GitHub)github.com
- Claude Code plugin evals (omidsaffari.com)omidsaffari.com
Provenance
The note above is reproduced unedited from the original post, first published on Threads on 20 September 2026 at 08:02 IST. Sources are the papers and datasets the note draws on.
View the original post ↗Embed this note
More notes
The air is now being asked to keep its own ledger
the air is now being asked to keep its own ledger: ecmwf’s aifs compo becomes the first ai model to forecast atmospheric composition globally every three hours, cleanair simulates 365 days of pm2.5 over china in ten seconds, and a unified framework maps six pollutants at one kilometer across the whole country. the air now files its own composition report.
read the note →The current is now being asked to draw its own map
the current is now being asked to draw its own map: china’s langya 2.0 predicts six ocean phenomena including internal waves and mesoscale eddies, a deep net called wenhai resolves eddies globally with air sea flux formulas built in, and scripps infers surface currents from the way temperature patterns deform in satellite images. the ocean now files its own circulation report.
read the note →The soil is now being asked to report its own carbon
the soil is now being asked to report its own carbon: a nix color sensor paired with generative data augmentation predicts soil organic carbon without a lab, random forest drives 74 percent of soil health mapping studies, and sentinel 2 tracks five year carbon change across france and italy from 922 samples. the dirt now files its own carbon account.
read the note →