CLAUDE_CODE_ENTRYPOINT
A Claude Code environment variable, read out of the shipped bundle. It has been in the build since v2.1.138, including the newest one read.
Waiting for MCP servers before a headless run is tidied up and logs more detail.
Not Anthropic's. This is the line from the earliest changelog entry here that named it, v2.1.221.
In the changelogs
41Releases whose published page names CLAUDE_CODE_ENTRYPOINT.
-
v2.1.305
A desktop host can set the name Claude Code's requests are sent under
CLAUDE_CODE_ENTRYPOINT_ON_REQUESTSsets the name requests go out under, but only whenCLAUDE_CODE_ENTRYPOINTisclaude-desktop-3pfound in this entry's text
-
v2.1.304
Plugin MCP servers can be loaded later by default in some cases
Plugin MCP servers that don't set alwaysLoad can now be deferred until needed in some cases, not only those with alwaysLoad set to false
found in this entry's text
-
v2.1.301
The reported entry point in request headers can now come from another source
Claude Code now checks another source for its reported entry point before falling back to CLAUDE_CODE_ENTRYPOINT
found in this entry's text, named in this entry
-
v2.1.301
Claude Code's request label checks another source for how it was started
The label Claude Code sends with its requests now checks another source first for how it was started, before
CLAUDE_CODE_ENTRYPOINTfound in this entry's text, named in this entry
-
v2.1.292
Skill permission reset now applies only to remote cowork sessions
The permission reset when a skill runs no longer has a server switch and now depends only on the session being a remote cowork one
found in this entry's text, named in this entry
-
v2.1.287
Cowork setup and /explain-usage no longer limited to the remote Cowork entry point
The Cowork guided setup and /explain-usage were available only when Claude Code started as remote Cowork; they now follow a different check
found in this entry's text, named in this entry
-
v2.1.286
Skipping flag settings saves no longer depends on a remote switch
The rule that lets Claude Code skip saving and announcing unchanged flag settings now depends on how it was launched and on policy, not a remote switch
found in this entry's text
-
v2.1.284
A tool in remotely triggered sessions may no longer be loaded up front
In sessions started by a remote trigger, one tool is no longer always forced into the set of tools loaded at the start
found in this entry's text, named in this entry
-
v2.1.284
Remote sessions from the desktop app no longer need an extra flag
Remote sessions started from the Claude desktop app now depend on the same single flag as every other starting point
found in this entry's text, named in this entry
-
v2.1.284
Hidden built-in guide plugin for mods, with an animated panel
A built-in plugin,
cc-plugin-mods-guide, shows an animated panel over a question about hot reloading and is off unless switched on remotelyfound in this entry's text
-
v2.1.283
Claude Desktop can cap the auto-compact window on 1M-context models
In Claude Desktop, auto-compact on 1M-context models can now be capped at a 600k or 500k window by a server-side setting
found in this entry's text
-
v2.1.283
Remote Control no longer lets hooks and plugins through its inbound guard
Remote Control's inbound guard now always excludes hooks and plugins, and remote tools depend on two environment variables
found in this entry's text
-
v2.1.281
Responsive mode is no longer offered in Slack or Teams
Responsive mode is no longer offered when Claude Code runs inside Slack or Teams
found in this entry's text, named in this entry
-
v2.1.280
New remote-control entrypoint detection helper
Remote-control session detection now recognizes a remote_trigger entrypoint
found in this entry's text
-
v2.1.278
Auto-mode classifier now distrusts unix-socket proxies unless SSH remote
Sessions using ANTHROPIC_UNIX_SOCKET now lose server-side auto mode classification unless connecting over SSH remote
named in this entry, found in this entry's text
-
v2.1.277
New terminal-title-suppression gate for SDK-CLI entrypoint
Terminal title can now be suppressed for the SDK-CLI entrypoint, behind a new flag
found in this entry's text, named in this entry
-
v2.1.274
New CLAUDE_CODE_HOST_SESSION_ID passthrough env var
Claude Code now recognizes a CLAUDE_CODE_HOST_SESSION_ID environment variable
found in this entry's text
-
v2.1.272
AppifactRepl gated behind remote_cowork entrypoint + tengu_buzzing_lightning flag
AppifactRepl only turns on for the remote_cowork entry point, gated behind the tengu_buzzing_lightning flag
found in this entry's text
-
v2.1.268
New env var CLAUDE_CODE_QUESTION_OPTIONAL_DESCRIPTIONS, gated to specific entrypoints
New CLAUDE_CODE_QUESTION_OPTIONAL_DESCRIPTIONS env var makes AskUserQuestion option descriptions optional, but only for certain entrypoints
found in this entry's text
-
v2.1.267
Builtin plugin registration now runs unconditionally, plus again for non-local-agent entrypoints
Built-in plugins now register unconditionally at startup, in addition to existing conditional registration
found in this entry's text
-
v2.1.265
Command-line entrypoint telemetry routed through new normalizer
Command-line entrypoint telemetry now goes through a normalizer instead of reading the raw environment variable
found in this entry's text, named in this entry
-
v2.1.265
Slack entrypoint detection extended with a second check
Detecting Claude Code running inside Slack now checks a second source in addition to the environment variable
found in this entry's text
-
v2.1.257
New preserved environment variable CLAUDE_CODE_CCR_SURFACE
CLAUDE_CODE_CCR_SURFACE is now preserved and passed through like the existing entrypoint variables.
found in this entry's text
-
v2.1.248
Custom CA no longer misreported for local agent runs
Inherited certificate settings are no longer reported as your own custom CA in local agent runs.
found in this entry's text
-
v2.1.247
Remote memory snapshots move from a transport callback to a conversation attachment
Remote memory snapshots now arrive as a conversation attachment rather than a transport callback.
found in this entry's text
-
v2.1.247
The local-agent entrypoint registers only three built-in skills
Running as a local agent loads only three built-in skills instead of the full set.
named in this entry, found in this entry's text
-
v2.1.246
Assorted smaller behaviour changes
Per-session cost tracking survives restarts, the whiteboard menu was reworded, and the pride dialog entry is gone.
found in this entry's text
-
v2.1.242
Cloud headless can ask its host to refresh the OAuth token
A host program can take over refreshing your login token, off unless an env var is set.
named in this entry, found in this entry's text
-
v2.1.239
Scheduled runs are told to format their notification as a phone banner plus email body
Scheduled runs format notifications so the first sentence becomes a phone banner and the rest an email body.
found in this entry's text
-
v2.1.237
Verified-human marker for Slack-relayed turns, plus a stubbed third relay surface
Slack turns from a server-verified human get a marker so Claude treats them as you without extra confirmation.
named in this entry, found in this entry's text
-
v2.1.233
Entrypoint and SDK version are sanitized before being reported
Your entrypoint and SDK version are checked against known values before being reported.
named in this entry, found in this entry's text
-
v2.1.232
User-scope memory files skip symlinks and hard links
Your user-level CLAUDE.md and rules skip symlinked or hard-linked files unless external includes are allowed.
found in this entry's text
-
v2.1.227
New entrypoint value: remote_cowork_trigger
CLAUDE_CODE_ENTRYPOINT accepts remote_cowork_trigger, counting as both trigger-launched and remote.
named in this entry, found in this entry's text
-
v2.1.225
Child processes no longer inherit an IDE entrypoint identity
Commands you spawn no longer inherit an IDE entrypoint or remote session id from your editor session.
named in this entry, found in this entry's text
-
v2.1.223
Feedback is disabled for SDK entrypoints
Feedback and bug-report commands are hidden when Claude Code runs through the SDK.
named in this entry, found in this entry's text
-
v2.1.221
Headless MCP pre-wait takes an options object and reports more telemetry
Waiting for MCP servers before a headless run is tidied up and logs more detail.
found in this entry's text
-
v2.1.207
Morning Brief for Non-Cowork Sessions [In Development]
found in this entry's text
-
v2.1.199
Guided Cowork Setup (/setup-cowork)
found in this entry's text
-
v2.1.15
API Billing Attribution Headers
found in this entry's text
-
v1.0.28
Technical Improvements
found in this entry's text
-
v1.0.3
Process Information
found in this entry's text
First cited
5The earliest release whose published evidence quoted CLAUDE_CODE_ENTRYPOINT was v2.1.248, 27 Aug 2026. That is the oldest release this project wrote about it, so it is a floor on the name's age and not the release that introduced it. It is not a presence reading: which builds carried the name is the table below.
Presence across releases
1Build by build
149One 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.
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.