Follow Discord
Sweep 22 Oct 2026 · 04:32Z Build v2.1.308 527 read Stable v2.1.308 Latest v2.1.308 Next v2.1.308 Feeds RSS JSON llms.txt llms-full.txt Unofficial
Home / Reference / CLI flags

plugin eval

cli never mined JSON

A Claude Code CLI flag, read out of the shipped bundle. No mined inventory carries it: everything below comes from what this site has written about it.

Plugin eval now writes report.html and publishes it to claude.ai unless you pass --no-publish.

Not Anthropic's. This is the line from the earliest changelog entry here that named it, v2.1.224.

First seen — never in a mined build
Last seen — never in a mined build
Builds0 / 149on this box, as of v2.1.308
Written about v2.1.224 first named in a changelog, 7 Aug 2026

In the changelogs

22

Releases whose published page names plugin eval.

  1. v2.1.305
    claude plugin eval passes your session's API key to its test runs

    With an API key session, claude plugin eval now hands the key to its test runs itself, except on Windows, where you must set ANTHROPIC_API_KEY

    named in this entry

  2. v2.1.289
    claude plugin eval tests folder marketplace plugins from where sessions load them

    Evaluating an installed plugin from a folder marketplace now runs it from that folder, or stops with an error if the folder no longer lists it

    named in this entry

  3. v2.1.283
    claude plugin eval now needs git 2.31 or newer

    claude plugin eval now checks your git version and refuses to run with git older than 2.31

    named in this entry

  4. v2.1.269
    claude plugin eval GA text and its server-side kill switch

    claude plugin eval is now generally available, with a server-side switch that can turn it off per session

    named in this entry

  5. v2.1.269
    claude plugin eval now requires explicit trust confirmation before running

    claude plugin eval now checks that a plugin is trusted before it will run its eval suite

    named in this entry

  6. v2.1.269
    plugin eval CLI help text expanded with sandboxing/trust disclosure

    claude plugin eval help text now explains sandboxing limits and the new untrusted-plugin confirmation prompt

    named in this entry

  7. v2.1.251
    Eval runs clean up the whole process tree

    Plugin eval kills the whole process tree so spawned tools don't outlive the run.

    named in this entry

  8. v2.1.242
    plugin eval can mock a plugin's MCP servers, with docs to match

    Plugin evals can swap a plugin's MCP servers for fakes defined in a mocks folder.

    named in this entry

  9. v2.1.234
    plugin eval no longer swallows piped input

    Piping input into plugin eval now works because startup no longer captures that stdin first.

    named in this entry

  10. v2.1.234
    Plugin eval reference documents image grading and new exit codes

    Plugin eval docs now say image focus files are shown to the judge, and document new exit codes.

    named in this entry

  11. v2.1.234
    claude plugin eval handles termination signals and cleans up its output

    Plugin eval runs now handle kill signals with proper exit codes and title reports with plugin names.

    named in this entry

  12. v2.1.234
    Plugin eval reference rewritten around a tighter sandbox

    Plugin eval runs now happen in a tighter sandbox with their own git repo and home directory.

    named in this entry

  13. v2.1.233
    Plugin eval runs report exit codes, stderr and auth rejection

    Plugin eval runs now report exit codes and stderr tails when a case fails.

    named in this entry

  14. v2.1.233
    Plugin eval checks your credentials before running any case

    Plugin eval checks your credentials first and aborts instead of failing every case.

    named in this entry

  15. v2.1.233
    Plugin eval stops the suite when authentication fails

    A failed login stops the whole eval suite instead of wasting every case.

    named in this entry

  16. v2.1.233
    plugin eval --verbose now writes traces to the debug log

    Eval --verbose now writes traces to the debug log instead of streaming them live.

    named in this entry

  17. v2.1.233
    Eval report publishing prints a working link and a way to opt out

    Published eval reports now print a working link and mention --no-publish.

    named in this entry

  18. v2.1.233
    Plugin eval tells the model the env var that turns it on

    Setting CLAUDE_CODE_WALNUT_SPIRE=1 turns on the early-access plugin eval command.

    named in this entry

  19. v2.1.233
    The built-in guide agent can answer questions about plugin eval and /skill-doctor offline

    The built-in guide agent can now answer about plugin eval and /skill-doctor from bundled reference text.

    named in this entry

  20. v2.1.224
    claude plugin eval writes a report and publishes it by default

    Plugin eval now writes report.html and publishes it to claude.ai unless you pass --no-publish.

    named in this entry

  21. v2.1.224
    plugin eval: report publishing flags reworked

    Plugin eval publishes its HTML report by default; --publish-report now means require publishing.

    named in this entry

  22. v2.1.224
    Plugin eval can validate and report its own JSON output

    Plugin eval JSON output is validated before printing, and suppressed with a stderr warning if invalid.

    named in this entry

First cited

0

No release's published evidence quotes this name. The ledger indexes the Evidence lines of every changelog on this site, so this says nobody here has ever quoted it; it says nothing about how old the name is.

Presence across releases

0

The miner has never read a build containing this name. It is here because a changelog entry of ours names it, which is evidence that it existed and not evidence of which releases carried it. The inventory starts at v2.1.138 and everything older than that was never mined.

Read out of the published npm bundle release by release, and out of Anthropic's own documentation as this site captured it. Nothing on this page is a description anybody here wrote about what the CLI flag does. All CLI flags.

Feedback