Follow Discord
Sweep 12 Nov 2026 · 23:00Z Build v2.1.323 540 read Stable v2.1.311 Latest v2.1.323 Next v2.1.323 Feeds RSS JSON llms.txt llms-full.txt Unofficial
Home / Reference / Settings keys

name

setting gone JSON

A Claude Code settings key, read out of the shipped bundle. It was in the build from v2.1.284 and was gone by v2.1.309.

The SDK now rejects malformed skill names with a clear reason instead of creating a rule that never matches.

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

First seen v2.1.284 28 Sep 2026
Last seen v2.1.308 22 Oct 2026, gone by v2.1.309
Builds8 / 162on this box, as of v2.1.323
Written about v2.1.30 first named in a changelog, 3 Feb 2026
v2.1.284in the build not in the build never minedv2.1.323

In the changelogs

120

Releases whose published page names name.

  1. v2.1.318
    Tool errors explain when Claude called a tool before loading its details

    When Claude calls a deferred tool without its input format loaded, the error now shows the format or explains how to load it

    found in this entry's text

  2. v2.1.317
    Hook settings now spell out the fields for agent and mcp_tool hooks

    The description of valid hook settings now lists the fields for agent hooks and mcp_tool hooks

    found in this entry's text

  3. v2.1.311
    Claude's guidance for links inside artifacts is stricter

    Artifact instructions now limit link anchors to letters, digits and hyphens, warn against secrets in them and reserve comment-*

    found in this entry's text

  4. v2.1.311
    Claude is told to reload a tool's details before calling it again

    Claude is now told when earlier-loaded tools have lost their input details, and to load them again with a select:<name> query before using them

    found in this entry's text

  5. v2.1.309
    Git tracked-file check is protected from git settings in your environment

    When Claude Code asks git whether a file is tracked, it now sets git's environment itself, so tracing and path-matching settings can't change the answer

    found in this entry's text

  6. v2.1.309
    Claude now avoids accidental @mentions in pull requests and issues

    Claude is now told to write a bare @name in GitHub text only for a real person it means to notify, and to put other @ words in backticks

    found in this entry's text

  7. v2.1.309
    Claude is told to write GitHub @mentions only for people it means to notify

    The Bash tool instructions now tell Claude that GitHub notifies anyone @mentioned, so it should only @mention real logins it means to notify

    found in this entry's text

  8. v2.1.307
    A list of earlier subagents in a session, off unless switched on

    Claude Code can list the subagents that ran earlier in a session, off unless CLAUDE_CODE_SUBAGENT_HISTORY is set or it is switched on remotely

    found in this entry's text

  9. v2.1.305
    Tags that carry attributes are now picked up when reading tagged text

    When Claude Code pulls text out of a tag pair, it now also recognises opening tags with attributes, such as a tag followed by a space and extra details

    found in this entry's text

  10. v2.1.301
    Claude Code won't retry when a git remote name refers to a group of remotes

    If a git remote name is defined as a group of remotes, Claude Code now reports that and does not retry

    found in this entry's text

  11. v2.1.301
    Git config check for on-demand fetching can now target a named remote

    Claude Code's safety check on git configuration before on-demand fetches can now check a specific named remote

    found in this entry's text

  12. v2.1.300
    OpenTelemetry traces now carry standard AI attributes and support prompt redaction

    Interaction and tool spans in OpenTelemetry traces now include standard gen_ai attributes, and the recorded prompt can be redacted afterwards

    found in this entry's text

  13. v2.1.300
    Tool traces now carry standard GenAI attributes for OpenTelemetry

    Traces of tool use now include standard GenAI fields such as the tool name, and the MCP server name for MCP tools

    found in this entry's text

  14. v2.1.295
    Plugin names are read from plugin.json, and marketplace clones get a path

    Claude Code reads a plugin's name from its plugin.json file, and cloning a plugin marketplace now also passes a path

    found in this entry's text

  15. v2.1.295
    Adding a marketplace with an unusable name now fails straight away

    Claude Code now refuses to add a plugin marketplace whose name can't be used in plugin names, and says what to fix

    found in this entry's text

  16. v2.1.292
    Refused marketplace names now come with steps to rename them

    When a marketplace from a settings file is refused for an Anthropic-like name, the message now explains how to rename it

    found in this entry's text

  17. v2.1.292
    Skill, agent and command names are limited to 256 characters

    A skill, agent or command whose name is longer than 256 characters is now rejected with an error

    found in this entry's text

  18. v2.1.292
    Messages sent with SendMessage now record what kind of recipient they go to

    SendMessage calls shown to hooks and transcripts now include recipient_kind, and messages to cloud and Remote Control sessions use new routing

    found in this entry's text

  19. v2.1.292
    Skill and plugin command names are now checked when loaded

    The name field in a skill's or plugin command's header is now passed through a check instead of being taken as plain text

    found in this entry's text

  20. v2.1.292
    Skill and agent names over a length limit are rejected

    A name in a skill or agent file's frontmatter longer than a set limit is now rejected or ignored with a warning

    found in this entry's text

  21. v2.1.290
    claude attach and claude logs accept a session name

    claude attach and claude logs now take a session name as well as an id, and part of the name is enough

    found in this entry's text

  22. v2.1.290
    claude logs now finds background sessions by name

    claude logs now accepts a session's name, or part of it, as well as its ID, and lists the matches when the name is ambiguous

    found in this entry's text

  23. v2.1.290
    Teammate error message now asks for the full address

    When several teammates match a name, the error now says to use the full address (name@team) instead of the full agent ID

    found in this entry's text

  24. v2.1.290
    Claude is told it can stop a named background agent by its name

    The TaskStop instructions now say a background agent started with a name can be stopped by passing that name

    found in this entry's text

  25. v2.1.290
    Refusals from --from-link can include another spelling of the name

    When the hidden --from-link option refuses, its JSON output can now include a requested field holding another spelling of the name

    found in this entry's text

  26. v2.1.288
    Unset plugin options can now be left as placeholders instead of causing an error

    Filling in a plugin's ${user_config.*} placeholders can now leave an unset option as written instead of always failing; failing is still the default

    found in this entry's text

  27. v2.1.284
    --channels still matches built-in plugins after they are renamed

    --channels now also accepts a built-in plugin's new name after a rename, and plugin telemetry records the previous name

    found in this entry's text

  28. v2.1.284
    Built-in plugins in enabledPlugins are matched regardless of letter case

    An enabledPlugins entry for a built-in plugin now takes effect even if its name differs from the plugin's only in upper or lower case

    found in this entry's text

  29. v2.1.283
    Permission prompts no longer explain rules that match a skill's old name

    The permission hint for a renamed skill, saying an old-name rule covers it and suggesting the new name, has been removed

    found in this entry's text

  30. v2.1.283
    The claude-ai: skill prefix is gone and plugin skills gain shorter names

    Skill names starting claude-ai: are no longer mapped to anthropic-skills:, and plugin skills can now be reached by shorter aliases

    found in this entry's text

  31. v2.1.283
    Synced skills are now always shown with the anthropic-skills: prefix

    Skills synced from your account now show as anthropic-skills:<name> unless they already have that prefix or have their own name override

    found in this entry's text

  32. v2.1.283
    Artifact previews tell Claude which features can only be tested after publishing

    In artifact previews, calls to window.claude.use() now return null and Claude is told to test that code after publishing

    found in this entry's text

  33. v2.1.283
    Git remotes using plain http:// are now refused

    When Claude Code looks up a repository's git remote URL, it now accepts only https:// (or file:// where allowed) and refuses http://

    found in this entry's text

  34. v2.1.283
    HTML preview check notes when a page calls window.claude.use()

    The HTML preview's health check now records which names a page asks for through window.claude.use()

    found in this entry's text

  35. v2.1.282
    Account skills can arrive through a wrapper plugin named anthropic-skills

    Claude Code can now treat a plugin named anthropic-skills as a wrapper for your account's skills and map claude-ai: skill names to it

    found in this entry's text

  36. v2.1.282
    Skills and MCP servers named "claude-ai" or "anthropic-skills" are no longer loaded

    The names "claude-ai" and "anthropic-skills" are now reserved for skills synced from claude.ai, and local skills or MCP servers using them are refused

    found in this entry's text

  37. v2.1.282
    Git worktrees with something mounted over their .git/worktrees entry are refused

    Claude Code now refuses to upload from a git worktree whose entry under .git/worktrees sits on a different mount from the repository, and says how to fix it

    found in this entry's text

  38. v2.1.282
    Session edit permissions limited to skill folders

    Session 'allow' rules for editing files by path pattern are now dropped unless the path is a skill folder in a .claude directory

    found in this entry's text

  39. v2.1.281
    Launch-dir filter regex no longer treats single-letter 'x:' strings as non-paths

    Windows drive paths like C: are no longer mistaken for web-style addresses and dropped from launch directories

    found in this entry's text

  40. v2.1.281
    OTEL label validation with reserved names

    Custom telemetry labels are now checked: names use a limited character set, some names are reserved, and values must be short printable ASCII

    found in this entry's text

  41. v2.1.281
    Channels: plugin identity check compares the installed plugin's name as well as its marketplace

    --channels now checks that the installed plugin's name matches, not only its marketplace, and names the installed plugin when skipping

    found in this entry's text

  42. v2.1.280
    Tool wrapper object now preserves extra mcpInfo fields

    Tool descriptors built from MCP info no longer drop unlisted fields

    found in this entry's text

  43. v2.1.277
    Plugin install supports a preview download path with randomized temp filename

    Plugin preview downloads now use a randomized temp filename and are left in place instead of being installed

    found in this entry's text

  44. v2.1.277
    Coordinator sessions blocked from reading worker transcripts/task outputs via shell tricks

    Coordinator agents are now blocked from reading worker transcripts or task outputs via shell workarounds

    found in this entry's text

  45. v2.1.277
    Marketplace settings-source schema defers reserved-name rejection to load time in one code path

    Marketplace 'settings' source schema can defer reserved-name checks to load time instead of at compile time

    found in this entry's text

  46. v2.1.277
    Hooks-module re-entry warnings now name the module by label, not name, and swap origin computation

    Hooks re-entry log messages now show a module's label instead of its name

    found in this entry's text

  47. v2.1.275
    Plugin install can now target npm packages directly, behind a flag

    Plugin install can now pull straight from npm with a new --registry option, gated behind an account flag

    found in this entry's text

  48. v2.1.274
    SDK gains an agent.register call

    SDK adds an agent.register call for defining named agents programmatically

    found in this entry's text

  49. v2.1.274
    MCP tool descriptions carry provenance ('source') into the render payload

    MCP tool data sent to the UI now includes where each MCP client came from

    found in this entry's text

  50. v2.1.274
    MCP server identity now threaded through permission requests

    Permission prompts now carry which MCP server is asking, including its name and source

    found in this entry's text

  51. v2.1.273
    New Artifact Types: 'slides' and 'design' with file-based storage

    Artifacts gain two new file-based types, 'slides' and 'design', alongside the existing 'design-system' type

    found in this entry's text

  52. v2.1.273
    Metric attribution fields (agent/skill/plugin/mcp names) can be redacted before emission

    Attribution fields like agent, skill, plugin, and MCP names can now be redacted from emitted metrics

    found in this entry's text

  53. v2.1.273
    apply_flag_settings control response strips an internal key

    apply_flag_settings control response handler now explicitly strips one internal key before returning settings

    found in this entry's text

  54. v2.1.269
    Plugin calls now reject when the calling plugin isn't admitted yet

    Cross-plugin calls now fail with a clear error if the target plugin hasn't finished registering yet.

    found in this entry's text

  55. v2.1.269
    Plugin hooks-module scan enforces that next.to() targets be statically discoverable

    Plugins that call next.to() with a hooks module name Claude Code can't find in the code are now rejected

    found in this entry's text

  56. v2.1.269
    OpenTelemetry metrics can optionally include VCS/repository attributes

    OpenTelemetry metrics can now optionally tag data with the project's git repository and provider details.

    found in this entry's text

  57. v2.1.269
    Dir-sync git operations now disable custom git hooks in addition to filters

    Background git operations now also disable custom git hooks, not just content filters

    found in this entry's text

  58. v2.1.269
    Plugin slash-commands can be invoked via short :name suffix suggestions

    Typing a plugin command's short :name suffix now suggests the matching full command

    found in this entry's text

  59. v2.1.269
    Synced skills now get namespaced under an anthropic-skills: prefix to avoid name collisions

    Skills synced from your account now get an anthropic-skills: prefix so they don't collide with local commands

    found in this entry's text

  60. v2.1.269
    Skills now addressable via an anthropic-skills: URI scheme

    Synced skills are now referenced by an anthropic-skills: identifier instead of a GitHub URL

    found in this entry's text

  61. v2.1.269
    Agent resume gains worktreeBranch and name validation groundwork

    Resuming an agent now validates its worktree branch and name before proceeding

    found in this entry's text

  62. v2.1.268
    toolUses / toolResults validation schema renamed fields

    toolUses/toolResults validation now expects tool_use_id and tool fields instead of id and name

    found in this entry's text

  63. v2.1.267
    "snooze"-like entries (name/until) now scoped by sessionId

    Snooze-style entries (name/until) can now be scoped to a specific session

    found in this entry's text

  64. v2.1.265
    Plugin SDK gains a command namespace: register/run/list slash commands

    Plugins can now register, run, and list slash commands through a new $.command API

    found in this entry's text

  65. v2.1.265
    MCP channel flags require plugin:/server: tagging

    --channels and its development-channels flag now require explicit plugin: or server: tags

    found in this entry's text

  66. v2.1.261
    Claude-code-hint plugin references now validated as name@marketplace

    Malformed plugin-hint tags are now dropped instead of parsed.

    found in this entry's text

  67. v2.1.259
    Prompt context blocks now pass through a resolver/invalidator pipeline before assembly

    User context is assembled into named blocks and passed through a resolver that can rewrite it; by default it passes through untouched.

    found in this entry's text

  68. v2.1.257
    OAuth callback server errors now carry distinct user-facing names

    OAuth callback failures such as port-in-use or timeout now carry distinct short names.

    found in this entry's text

  69. v2.1.257
    Workflow tool rejects control/invisible characters in name and scriptPath

    The Workflow tool rejects a name or scriptPath containing control or invisible formatting characters.

    found in this entry's text

  70. v2.1.257
    Resource-link collection capped at 50 links / 64KiB

    Resource-link collection stops at 50 entries or 64KiB and strips internal annotation keys.

    found in this entry's text

  71. v2.1.247
    Preview screenshots are shrunk and re-encoded to fit the image budget

    Preview screenshots are re-encoded and shrunk so they fit inside the image budget.

    found in this entry's text

  72. v2.1.247
    Memory files can be checked for size and frontmatter after a write

    Memory files can be checked after a write for oversize, split files and bad descriptions.

    found in this entry's text

  73. v2.1.246
    Custom keybinding actions now use a command: prefix instead of x-

    Custom keybindings must now be named command:<name>; old x- names no longer validate.

    found in this entry's text

  74. v2.1.246
    claude plugin update accepts a bare plugin name

    You can run claude plugin update with just the plugin name, no marketplace needed.

    found in this entry's text

  75. v2.1.246
    Bundled skill and reference text moved out of the JavaScript into embedded files

    Built-in skills and their reference docs now load from embedded files rather than inline strings.

    found in this entry's text

  76. v2.1.246
    Plugin interfaces are checked before they are used

    A plugin publishing an interface for others now fails loudly if it isn't a proper object of functions.

    found in this entry's text

  77. v2.1.242
    Cloud sessions report which host settings they ignored

    A cloud session now reports which of your flags and settings keys it ignored.

    found in this entry's text

  78. v2.1.239
    Relayed coordinator messages are labelled and escaped

    Coordinator messages forwarded to worker agents are labelled and escaped so they can't fake markup.

    found in this entry's text

  79. v2.1.238
    Ambiguous agent names now say which ID to use

    Ambiguous agent names now tell you to use the full name@team ID or the task ID.

    found in this entry's text

  80. v2.1.235
    Template placeholder substitution no longer resolves inherited object properties

    Template {{name}} substitution no longer resolves inherited Object.prototype properties like constructor or toString

    found in this entry's text

  81. v2.1.234
    Saved artifact HTML is sanitized and refused if it will not round-trip

    Artifact saves get sanitized and refused if the content cannot be published cleanly, in a disabled skill.

    found in this entry's text

  82. v2.1.233
    No more frontmatter warnings for reference docs alongside agents

    Reference docs sitting next to your agents no longer trigger missing-frontmatter warnings.

    found in this entry's text

  83. v2.1.232
    @-mention another session or agent in your prompt

    Type @name in a prompt to complete and address a running agent, local, cloud or bridge session.

    found in this entry's text

  84. v2.1.228
    Transcript cleanup prunes a new sidecar file and refuses risky directory names

    Cleanup now deletes leftover per-directory sync files so they stop piling up next to transcripts.

    found in this entry's text

  85. v2.1.224
    Failed @name messages now tell you they failed

    Direct messages you send with @name now warn you when delivery fails.

    found in this entry's text

  86. v2.1.224
    Memory index built by scanning files rather than read from disk

    A memory index can be generated by scanning recent files rather than read from a stored index.

    found in this entry's text

  87. v2.1.223
    Artifact and frame URLs accept a prefixed slug

    Artifact and frame links that include a readable slug before the id now work instead of being rejected.

    found in this entry's text

  88. v2.1.221
    The Agent SDK validates skills entries before turning them into permission rules

    The SDK now rejects malformed skill names with a clear reason instead of creating a rule that never matches.

    found in this entry's text

  89. v2.1.215
  90. v2.1.213
    Host OTLP Telemetry for SDK Integrations

    found in this entry's text

  91. v2.1.212
    Worktree Symlink Security Check

    found in this entry's text

  92. v2.1.212
  93. v2.1.207
    Sibling Org Repo Docs in Auto-Mode Setup

    found in this entry's text

  94. v2.1.198
    TaskStop: Stop Agents by Name

    found in this entry's text

  95. v2.1.198
    Skill Upkeep Guidance Improvement

    found in this entry's text

  96. v2.1.196
    Organization Default Model

    found in this entry's text

  97. v2.1.193

    found in this entry's text

  98. v2.1.187
  99. v2.1.183
  100. v2.1.178
  101. v2.1.178

    found in this entry's text

  102. v2.1.176
    Footer Link Badges

    found in this entry's text

  103. v2.1.174
  104. v2.1.140
  105. v2.1.129
    Better Plugin Authoring Diagnostics

    found in this entry's text

  106. v2.1.119
    Skill Tool Description Update

    found in this entry's text

  107. v2.1.118
    /plugin tag Command

    found in this entry's text

  108. v2.1.118
    Custom Theme Creation and Management

    found in this entry's text

  109. v2.1.116
  110. v2.1.111

    found in this entry's text

  111. v2.1.111
    Skill Tool Description Improvements

    found in this entry's text

  112. v2.1.105
    Enter Existing Worktrees

    found in this entry's text

  113. v2.1.84
    Plugin Source Tracking

    found in this entry's text

  114. v2.1.77
    Plugin/Skill Manifest Validation

    found in this entry's text

  115. v2.1.75
    Hook Source Tracking

    found in this entry's text

  116. v2.1.71
    Team Memory (Shared Persistent Knowledge)

    found in this entry's text

  117. v2.1.69

    found in this entry's text

  118. v2.1.69
    Memory System Overhaul

    found in this entry's text

  119. v2.1.50
    VCS-Agnostic Worktree Isolation via Hooks

    found in this entry's text

  120. v2.1.30
    SDK Schema Documentation

    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

6
BuildsHow manyDatesReading
v2.1.284 – v2.1.2863 builds28 Sep 2026 → 30 Sep 2026 ◆in the build
v2.1.287 – v2.1.30113 builds1 Oct 2026 → 15 Oct 2026 ○not in the build
v2.1.302 – v2.1.3043 builds16 Oct 2026 → 19 Oct 2026 ◆in the build
v2.1.305 – v2.1.3062 builds20 Oct 2026 → 21 Oct 2026 ○not in the build
v2.1.307 – v2.1.3082 builds21 Oct 2026 → 22 Oct 2026 ◆in the build
v2.1.309 – v2.1.32313 builds22 Oct 2026 → 12 Nov 2026 ○not in the build

Build by build

36

One row per release since the first build this name was read out of. Absent means the build was read and the name was not in it, never mined means no bundle for that release was ever archived, and a declared type or a default is only ever what that release's own bundle stated.

BuildDateStateThe record behind it
v2.1.28428 Sep 2026·addedverdict: added
v2.1.28529 Sep 2026·presentverdict: present
v2.1.28630 Sep 2026·presentverdict: present
v2.1.2871 Oct 2026·removedverdict: removed
v2.1.2882 Oct 2026·absent—
v2.1.2893 Oct 2026·absent—
v2.1.2905 Oct 2026·absent—
v2.1.2916 Oct 2026·absent—
v2.1.2926 Oct 2026·absent—
v2.1.2937 Oct 2026·absent—
v2.1.2948 Oct 2026·absent—
v2.1.2958 Oct 2026·absent—
v2.1.2969 Oct 2026·absent—
v2.1.29914 Oct 2026·absent—
v2.1.30014 Oct 2026·absent—
v2.1.30115 Oct 2026·absent—
v2.1.30216 Oct 2026·addedverdict: added
v2.1.30318 Oct 2026·presentverdict: present
v2.1.30419 Oct 2026·presentverdict: present
v2.1.30520 Oct 2026·removedverdict: removed
v2.1.30621 Oct 2026·absent—
v2.1.30721 Oct 2026·addedverdict: added
v2.1.30822 Oct 2026·presentverdict: present
v2.1.30922 Oct 2026·removedverdict: removed
v2.1.31023 Oct 2026·absent—
v2.1.31126 Oct 2026·absent—
v2.1.31227 Oct 2026·absent—
v2.1.31430 Oct 2026·absent—
v2.1.31530 Oct 2026·absent—
v2.1.31631 Oct 2026·absent—
v2.1.3172 Nov 2026·absent—
v2.1.3183 Nov 2026·absent—
v2.1.3196 Nov 2026·absent—
v2.1.3219 Nov 2026·absent—
v2.1.32210 Nov 2026·absent—
v2.1.32312 Nov 2026·absent—

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