Source Intelligence
Follow Discord
Sweep 28 Aug 2026 · 16:06Z Build v2.1.251 479 read Stable v2.1.236 Latest v2.1.251 Next v2.1.251 Feeds RSS JSON llms.txt

DisclaimerUnofficial, and not affiliated with Anthropic. Nearly all of this is read straight out of what ships: npm bundles, captured prompts, published docs. Anthropic's own notes go in verbatim, marked as theirs. The rest is my reading, and every entry carries the strings behind it. If one looks wrong, vote it down and say why.

Reference / Environment variables

CLAUDE_CODE_EVAL_CONFINED

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

What it is

In confined evaluation runs, publishing re-checks a file's identity before reading it.

Not Anthropic's. This is the line from the earliest changelog entry here that named it, v2.1.251.

Presence across releases

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.

Changelog entries naming it

  1. v2.1.251Publish re-verifies a file's identity after opening it

    In confined evaluation runs, publishing re-checks a file's identity before reading it.

    named in this entry

  2. v2.1.251How the evaluation subprocess environment is assembled

    The confined-evaluation flag is injected into eval child processes, confirming it's harness plumbing not a setting.

    named in this entry

  3. v2.1.251A confined evaluation mode, set by Claude Code on itself

    A confined evaluation mode exists that Claude Code only sets on its own eval subprocesses.

    named in this entry

  4. v2.1.251Evaluation runs get narrowed permissions

    In confined evaluation runs, allow rules from settings files are ignored; only CLI ones count.

    named in this entry

  5. v2.1.251What the confined mode changes across cloud, permissions and plugin loading

    Confined mode also blocks cloud sessions and changes how MCP servers and hooks load.

    named in this entry

Documentation pages

None of Anthropic's documentation pages this site has a copy of carries this name.

Names beside it

Every environment variable in the inventory starting claude_code_eval, up to twelve of them.

CLAUDE_CODE_EVAL_An env var turns on the tool that proposes new skills; otherwise it stays off in this build. never mined CLAUDE_CODE_EVAL_ALLOW_ARTIFACT_PUBLISHEval suites can only publish artifacts or override feature flags if you explicitly allow it. never mined CLAUDE_CODE_EVAL_ALLOW_FLAG_OVERRIDESEval suites can only publish artifacts or override feature flags if you explicitly allow it. never mined CLAUDE_CODE_EVAL_ARTIFACT_STUB_DIRPoint artifact publishing at a local directory and it writes files there instead of calling the service. never mined CLAUDE_CODE_EVAL_INTERVIEW_SESSIONAn env var turns on the tool that proposes new skills; otherwise it stays off in this build. 2.1.233

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 environment variable does. All environment variables.