Source Intelligence
Follow Discord

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.

← All of v2.1.75 Home All releases ←olderv2.1.74 v2.1.76newer→
Claude Code v2.1.75

Plugin Configurable Options

What

Plugins can now declare user-configurable options in their manifest via a userConfig schema, with typed fields, defaults, and secure storage for sensitive values.

Details
  • Plugin manifests can include a userConfig block with named options of type string, number, boolean, directory, or file
  • Each option supports title, description, required, default, sensitive, min/max, and multiple fields
  • Option keys must be valid identifiers — they become CLAUDE_PLUGIN_OPTION_<KEY> environment variables in hooks
  • Sensitive values are stored in secure storage (macOS keychain or .credentials.json), non-sensitive values in settings.json
  • Available as ${user_config.KEY} in MCP/LSP server config, hook commands, and (non-sensitive only) skill/agent content
Evidence

Plugin options schema and env var injection (search for "CLAUDE_PLUGIN_OPTION_", "User-configurable values this plugin needs")

Strings lifted out of the shipped bundle, so the claim above can be checked against them.

Related

Other releases about the same thing. Found by shared names or similar wording; neither means one caused the other.

See this entry in the whole of v2.1.75 →