New /project command names the claude.ai Project for a session's…

Unclear It is not clear who passes the eligibility check the command also requires.

What

A new slash command, /project, sets which claude.ai Project a session's usage is reported under. Its description is "Set the claude.ai Project for this session's usage reports", and it takes [Project ID or claude.ai address] [--save] | clear [--save].

Choosing a Project: you give a Project ID or a claude.ai/project address. --save stores it as attributionProject in your local settings, and clear removes it.
Requirements: you must be logged in with claude.ai and connected directly to Anthropic, not in a cloud session, and CLAUDE_CODE_ATTRIBUTION_HEADER must not be set to 0. Managed settings can block the command, and the CLAUDE_CODE_ATTRIBUTION_PROJECT environment variable takes priority over it.
Availability: the command only appears when an eligibility check passes and the remote flag tengu_gentle_cupcake is true. Nothing has been read about that flag. Its built-in fallback is false. The command also works in non-interactive sessions.
Status lines: the session reports "This session names claude.ai Project ${r.name} for usage reports (${r.origin})" or "This session names no claude.ai Project for usage reports."
Where the setting came from: the origin is now worked out in one shared place. The source 'harness' is shown as CLAUDE_CODE_ATTRIBUTION_PROJECT, and 'admin_default' as "your organization's default". The existing 'user' and 'project' settings labels are unchanged. A setting given with --settings is now shown as "attributionProject in --settings".
Accepted IDs: the attributionProject setting now accepts IDs starting with "chan_" as well as "claude_proj_", and also the UUID of a claude_proj_ Project.
Error text: a related error now says the session "is in a claude.ai Project" instead of "started inside a claude.ai Project".

Why

When the command is available, you can choose which Project your usage counts towards from inside a session, and keep that choice with --save. Usage can also now be reported under a new kind of Project, whose ID starts with "chan_".

Read from

Names in the bundle/project

Feature flag

tengu_gentle_cupcake Not enough to say

Nothing here resolved what this flag was doing on this version, so nothing here should be read as on or off.

This account: no value returned · anonymous baseline: no value returned · compiled default in v2.1.318: off

These values were read against a different version of Claude Code, so treat them as the nearest reading available instead of one taken on this release.

Read once, for one account on one subscription tier, against v2.1.318. It isn't a statement about your account. What a flag value here can and cannot tell you

Since it was published

The entry above is what we published on the day. These lines were added later, as Anthropic's own pages caught up, and they sit beside the original rather than replacing it.

Confirmed since 5 Nov 2026 Anthropic's documentation has since written up /project, on Organization. **GET** `/v1/organizations/analytics/apps/chat/projects` api/organization see the edit

How sure we are

Something disagreesSomething we can check disagrees with this entry, or the writer said they could not settle it.

The writer flagged doubtIt is not clear who passes the eligibility check the command also requires.

Anthropic's documentation agreesAnthropic's documentation has since written up /project, on Organization.

The name it cites is new in this buildNew in this build: tengu_gentle_cupcake

See this entry in the whole of v2.1.318 →

The build it came inv2.1.318

3 Nov 2026 · 425 entries, this one is #5.

Use it now23
You'll notice215
Nothing to try yet27
Under the hood160

Either side of it

v2.1.317Older

Open the release →

Names in this entry

slash/project
A /project command lets a session name a claude.ai Project for usage reports, save it with --save, or remove it with clear
flagtengu_gentle_cupcake
A /project command sets which claude.ai Project a session's usage reports go to; it is off unless switched on remotely
settingattributionProject
The claude.ai Project used for usage reports now comes from an environment variable, a setting or a managed default, and bad IDs are flagged
cli--settings
Path to a settings JSON file or an inline JSON string. Values you set here override the same keys in your settings.json files for this session. Keys you omit keep their file-based values. The file must be a regular file no larger than 2 MiB. See settings precedence
envCLAUDE_CODE_ATTRIBUTION_HEADER
Set to 0 to omit the attribution block, which carries the client version and a prompt fingerprint, from the start of the system prompt. Caching on a direct connection to the Anthropic API is unaffected either way. In some direct-connection setups, Claude Code keeps the block on auto mode classifier requests even when you set 0. In System prompt attribution block, check which connections and credentials this covers. Before v2.1.181 the block included a per-request token on custom base URLs and Microsoft Foundry connections, so on those versions set it to 0 when your LLM gateway caches on the request body or forwards requests to a third-party provider, or when you connect to Microsoft Foundry directly
envCLAUDE_CODE_ATTRIBUTION_PROJECT
Claude Code now recognises CLAUDE_CODE_ATTRIBUTION_PROJECT and drops a value that is not a valid claude.ai Project ID from saved jobs

Is this right?