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

experimental

setting never mined JSON

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

MCP task results and cancellations now use standard requests instead of an experimental helper.

Not Anthropic's. This is the line from the earliest changelog entry here that named it, v2.1.221.

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 v2.1.129 first named in a changelog, 5 May 2026

In the changelogs

8

Releases whose published page names experimental.

  1. v2.1.285
    Browser MCP server setup now runs a bundled Playwright script

    Claude Code can build a browser MCP server that runs a bundled Playwright script with node and sets CLAUDE_TEST_PROJECT_DIR

    found in this entry's text

  2. v2.1.283
    Plugin validation checks more manifest paths

    claude plugin validate now checks paths for more plugin parts and flags a .json path that is really a folder

    found in this entry's text

  3. v2.1.248
    Agents can set their own prompt cache lifetime in frontmatter

    An agent file can set its own prompt cache lifetime under experimental cacheTtl.

    named in this entry, found in this entry's text

  4. v2.1.235
    claude plugin eval --eval-dir shipped, with ownership checks on where cases and results are written

    plugin eval's --eval-dir flag ships with checks that it isn't writing results to a symlinked or foreign-owned directory

    found in this entry's text

  5. v2.1.235
    plugin eval gains --eval-dir and a manifest eval directory, still early access

    plugin eval gets a configurable case directory via --eval-dir or a manifest key, still gated as early access

    found in this entry's text

  6. v2.1.235
    plugin eval can target a non-default eval directory

    claude plugin eval gets an --eval-dir <dir> flag to target a non-default eval directory

    found in this entry's text

  7. v2.1.221
    MCP tasks use raw requests instead of the experimental client helpers

    MCP task results and cancellations now use standard requests instead of an experimental helper.

    found in this entry's text

  8. v2.1.129
    Better Plugin Authoring Diagnostics

    found in this entry's text

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 settings key does. All settings keys.

Feedback