An entry is only as true as the day it was written.
Flags move on the server after a release ships. Anthropic's own notes land days later and their documentation later still. Sometimes an entry turns out to be wrong and gets corrected by hand. All of that is recorded against the entry it happened to, and this is the whole of it in the order it happened.
Nothing here replaces an entry. Every line links to the page its release published, still saying what that release said, because a correction is added and dated rather than swapped in.
| When | Entry | What happened |
|---|---|---|
v2.1.257approve |
Documentation arrivedAnthropic's documentation has since written up approve, on Get started.
the line in the docsWhen the app opens, sign in with your Claude account. On Windows, the app opens claude.ai in your default browser for this and continues in the app window once you approve the sign-in. If the sign-in redirect can't return to the app (for e… |
|
v2.1.243--version |
Documentation arrivedAnthropic's documentation has since written up --version, on Get started.
the line in the docsUbuntu 24.04's repositories carry a new enough bubblewrap and Ubuntu 22.04's don't; on any distribution, confirm with `bwrap --version` that the installed version is 0.8.0 or later before you start Claude Science. |
|
v2.1.237--version |
Documentation arrivedAnthropic's documentation has since written up --version, on Get started.
the line in the docsUbuntu 24.04's repositories carry a new enough bubblewrap and Ubuntu 22.04's don't; on any distribution, confirm with `bwrap --version` that the installed version is 0.8.0 or later before you start Claude Science. |
|
v2.1.257full |
Documentation arrivedA small documentation edit on Custom connectors touched a line naming full after this was published.
the line in the docsLocal-command connectors run inside the sandbox with the same network limits as Claude's code and a per-connector writable directory. Environment variables for local connectors are saved unencrypted in a configuration file readable by your… |
|
v2.1.257read |
Documentation arrivedA small documentation edit on Custom connectors touched a line naming read after this was published.
the line in the docsLocal-command connectors run inside the sandbox with the same network limits as Claude's code and a per-connector writable directory. Environment variables for local connectors are saved unencrypted in a configuration file readable by your… |
|
v2.1.229command |
Documentation arrivedA small documentation edit on Custom connectors touched a line naming command after this was published.
the line in the docsLocal-command connectors run inside the sandbox with the same network limits as Claude's code and a per-connector writable directory. Environment variables for local connectors are saved unencrypted in a configuration file readable by your… |
|
v2.1.257HTTPS_PROXY |
Documentation arrivedAnthropic's documentation has since written up HTTPS_PROXY, on Use Claude Science on a corporate network.
the line in the docsSign-in fails with this message when the proxy demands credentials the app is not sending, because the proxy address carries none or the proxy was detected from the macOS or Windows system settings, which never supply credentials. Include … |
|
v2.1.251stop |
Documentation arrivedAnthropic's documentation has since written up stop, on Use Claude Science on a corporate network.
the line in the docsThe `[network] ca_bundle` key in `config.toml` points at a PEM file whose certificates Claude Science adds to its default trust for sign-in, the Claude API, Anthropic-hosted connectors, update checks, and [cloud storage](/docs/claude-scien… |
|
v2.1.229copy |
Documentation arrivedAnthropic's documentation has since written up copy, on Use Claude Science on a corporate network.
the line in the docsClaude Science stores the credential encrypted in its local database, using a key kept in a file only the member's account can read (on macOS, a copy of that key is in the keychain for recovery), and also writes the credential, automatical… |
|
v2.1.242scale |
Documentation arrivedAnthropic's documentation has since written up scale, on Use Claude Science on a corporate network.
the line in the docs| TLS inspection on the app's own connections (Zscaler, Netskope, and similar) | Supported with a CA bundle setting | Supported; a corporate root in the computer's certificate store is trusted automatically | Supported with a CA bundle set… |
|
v2.1.257plain |
Documentation arrivedAnthropic's documentation has since written up plain, on Configuration file reference.
the line in the docs| `allow_insecure_mirror` | boolean | `false` | Allows `http://` mirror URLs in this file (the Settings page accepts `https://` only). Off by default because a plaintext mirror lets an on-path attacker substitute packages. | |
|
v2.1.242cloud |
Documentation arrivedAnthropic's documentation has since written up cloud, on Configuration file reference.
the line in the docs| `ca_bundle` | string (absolute path) | unset | PEM file added to the app's default TLS trust for sign-in, the Claude API, Anthropic-hosted connectors, update checks, and [cloud storage](/docs/claude-science/cloud-storage) access from Set… |
|
v2.1.242cloud |
Documentation arrivedAnthropic's documentation has since written up cloud, on Configuration file reference.
the line in the docs| `ca_bundle` | string (absolute path) | unset | PEM file added to the app's default TLS trust for sign-in, the Claude API, Anthropic-hosted connectors, update checks, and [cloud storage](/docs/claude-science/cloud-storage) access from Set… |
|
v2.1.242cloud |
Documentation arrivedAnthropic's documentation has since written up cloud, on Configuration file reference.
the line in the docs| `ca_bundle` | string (absolute path) | unset | PEM file added to the app's default TLS trust for sign-in, the Claude API, Anthropic-hosted connectors, update checks, and [cloud storage](/docs/claude-science/cloud-storage) access from Set… |
|
v2.1.265diff |
Documentation arrivedAnthropic's documentation has since written up diff, on Configuration file reference.
the line in the docsClaude Science reads optional settings from a TOML file named `config.toml` in its default data folder, which is `~/.claude-science/config.toml` on macOS and Linux and `%USERPROFILE%\.claude-science\config.toml` on Windows. Every key has a… |
|
v2.1.260hosted |
Documentation arrivedA small documentation edit on Compute providers touched a line naming hosted after this was published.
the line in the docsModel endpoints are available in Claude Science on macOS and Linux. In Settings > Compute, under Model endpoints, click Connect on NVIDIA BioNeMo NIM. Import the skills from the BioNeMo Agent Toolkit, add your NVIDIA NGC API credential, an… |
|
v2.1.259pin |
Documentation arrivedAnthropic's documentation has since written up pin, on Command line settings.
the line in the docs| `claude-science uninstall` | Windows only. Remove the app, its shortcuts, and its PATH entry while keeping your data; `--purge` also deletes the data directory. Quit Claude Science first. | |
|
v2.1.259pin |
Documentation arrivedAnthropic's documentation has since written up pin, on Command line settings.
the line in the docs| `claude-science uninstall` | Windows only. Remove the app, its shortcuts, and its PATH entry while keeping your data; `--purge` also deletes the data directory. Quit Claude Science first. | |
|
v2.1.259pin |
Documentation arrivedAnthropic's documentation has since written up pin, on Command line settings.
the line in the docs| `claude-science uninstall` | Windows only. Remove the app, its shortcuts, and its PATH entry while keeping your data; `--purge` also deletes the data directory. Quit Claude Science first. | |
|
v2.1.259pin |
Documentation arrivedAnthropic's documentation has since written up pin, on Command line settings.
the line in the docs| `claude-science uninstall` | Windows only. Remove the app, its shortcuts, and its PATH entry while keeping your data; `--purge` also deletes the data directory. Quit Claude Science first. | |
|
v2.1.251logs |
Documentation arrivedAnthropic's documentation has since written up logs, on Command line settings.
the line in the docsclaude-science serve starts Claude Science and opens the web app in your browser at a single-use login link. Everyday use is that one command. The others manage the running program: they mint login links, report status, follow logs, instal… |
|
v2.1.238status |
Documentation arrivedAnthropic's documentation has since written up status, on Command line settings.
the line in the docsclaude-science serve starts Claude Science and opens the web app in your browser at a single-use login link. Everyday use is that one command. The others manage the running program: they mint login links, report status, follow logs, instal… |
|
v2.1.238status |
Documentation arrivedAnthropic's documentation has since written up status, on Command line settings.
the line in the docsclaude-science serve starts Claude Science and opens the web app in your browser at a single-use login link. Everyday use is that one command. The others manage the running program: they mint login links, report status, follow logs, instal… |
|
v2.1.248/run |
Documentation arrivedAnthropic's documentation has since written up /run, on Claude Science changelog.
the line in the docs* Claude Science is now available for Windows: download it from [claude.com/product/claude-science](https://claude.com/product/claude-science), and see [Run on Windows](/docs/claude-science/run-on-windows) for requirements and setup |
|
v2.1.229/pr |
Documentation arrivedAnthropic's documentation has since written up /pr, on Claude Science changelog.
the line in the docs* Claude Science is now available for Windows: download it from [claude.com/product/claude-science](https://claude.com/product/claude-science), and see [Run on Windows](/docs/claude-science/run-on-windows) for requirements and setup |
|
v2.1.257label |
Documentation arrivedAnthropic's documentation has since written up label, on Claude Science changelog.
the line in the docs<Update label="0.1.47" description="September 10, 2026"> |
|
v2.1.251/effort |
Documentation arrivedA small documentation edit on Orchestrate subagents at scale with dynamic workflows touched a line naming /effort after this was published.
the line in the docs`/effort ultracode` lasts for the current session; to have every session start with it, set the [`ultracode`](/docs/en/settings-reference#ultracode) setting. Drop back with `/effort high` when you return to routine work. The `/effort` menu… |
|
v2.1.257full |
Documentation arrivedAnthropic's documentation has since written up full, on Use Claude Code in VS Code.
the line in the docsClick any conversation to resume it with the full message history. If the conversation is already open in another tab of the current window, clicking it switches to that tab. For more on resuming sessions, see [Manage sessions](/docs/en/se… |
|
v2.1.251@claude |
Documentation arrivedAnthropic's documentation has since written up @claude, on All settings.
the line in the docs* **Type**: array of objects, each with `marketplace` and `plugin` strings. An entry can instead be a `"plugin@marketplace"` string such as `"telegram@claude-plugins-official"`, which Claude Code treats as the equivalent object. The string… |
|
v2.1.251@claude |
Documentation arrivedAnthropic's documentation has since written up @claude, on All settings.
the line in the docs* **Type**: array of objects, each with `marketplace` and `plugin` strings. An entry can instead be a `"plugin@marketplace"` string such as `"telegram@claude-plugins-official"`, which Claude Code treats as the equivalent object. The string… |
|
v2.1.251/effort |
Documentation arrivedAnthropic's documentation has since written up /effort, on All settings.
the line in the docsCap the [effort level](/docs/en/model-config#adjust-effort-level) a session can use, leaving lower levels available. Any higher level runs at the cap instead, including one from `/effort`, the `/model` picker, `--effort`, [`CLAUDE_CODE_EFF… |
|
v2.1.242CLAUDE_CODE_EFFORT_LEVEL |
Documentation arrivedAnthropic's documentation has since written up CLAUDE_CODE_EFFORT_LEVEL, on All settings.
the line in the docsCap the [effort level](/docs/en/model-config#adjust-effort-level) a session can use, leaving lower levels available. Any higher level runs at the cap instead, including one from `/effort`, the `/model` picker, `--effort`, [`CLAUDE_CODE_EFF… |
|
v2.1.265/model |
Documentation arrivedAnthropic's documentation has since written up /model, on All settings.
the line in the docsCap the [effort level](/docs/en/model-config#adjust-effort-level) a session can use, leaving lower levels available. Any higher level runs at the cap instead, including one from `/effort`, the `/model` picker, `--effort`, [`CLAUDE_CODE_EFF… |
|
v2.1.265/model |
Documentation arrivedAnthropic's documentation has since written up /model, on All settings.
the line in the docsCap the [effort level](/docs/en/model-config#adjust-effort-level) a session can use, leaving lower levels available. Any higher level runs at the cap instead, including one from `/effort`, the `/model` picker, `--effort`, [`CLAUDE_CODE_EFF… |
|
v2.1.265/model |
Documentation arrivedAnthropic's documentation has since written up /model, on All settings.
the line in the docsCap the [effort level](/docs/en/model-config#adjust-effort-level) a session can use, leaving lower levels available. Any higher level runs at the cap instead, including one from `/effort`, the `/model` picker, `--effort`, [`CLAUDE_CODE_EFF… |
|
v2.1.260/model |
Documentation arrivedAnthropic's documentation has since written up /model, on All settings.
the line in the docsCap the [effort level](/docs/en/model-config#adjust-effort-level) a session can use, leaving lower levels available. Any higher level runs at the cap instead, including one from `/effort`, the `/model` picker, `--effort`, [`CLAUDE_CODE_EFF… |
|
v2.1.251/model |
Documentation arrivedAnthropic's documentation has since written up /model, on All settings.
the line in the docsCap the [effort level](/docs/en/model-config#adjust-effort-level) a session can use, leaving lower levels available. Any higher level runs at the cap instead, including one from `/effort`, the `/model` picker, `--effort`, [`CLAUDE_CODE_EFF… |
|
v2.1.251/model |
Documentation arrivedAnthropic's documentation has since written up /model, on All settings.
the line in the docsCap the [effort level](/docs/en/model-config#adjust-effort-level) a session can use, leaving lower levels available. Any higher level runs at the cap instead, including one from `/effort`, the `/model` picker, `--effort`, [`CLAUDE_CODE_EFF… |
|
v2.1.251/model |
Documentation arrivedAnthropic's documentation has since written up /model, on All settings.
the line in the docsCap the [effort level](/docs/en/model-config#adjust-effort-level) a session can use, leaving lower levels available. Any higher level runs at the cap instead, including one from `/effort`, the `/model` picker, `--effort`, [`CLAUDE_CODE_EFF… |
|
v2.1.248/model |
Documentation arrivedAnthropic's documentation has since written up /model, on All settings.
the line in the docsCap the [effort level](/docs/en/model-config#adjust-effort-level) a session can use, leaving lower levels available. Any higher level runs at the cap instead, including one from `/effort`, the `/model` picker, `--effort`, [`CLAUDE_CODE_EFF… |
|
v2.1.248/model |
Documentation arrivedAnthropic's documentation has since written up /model, on All settings.
the line in the docsCap the [effort level](/docs/en/model-config#adjust-effort-level) a session can use, leaving lower levels available. Any higher level runs at the cap instead, including one from `/effort`, the `/model` picker, `--effort`, [`CLAUDE_CODE_EFF… |
|
v2.1.246/model |
Documentation arrivedAnthropic's documentation has since written up /model, on All settings.
the line in the docsCap the [effort level](/docs/en/model-config#adjust-effort-level) a session can use, leaving lower levels available. Any higher level runs at the cap instead, including one from `/effort`, the `/model` picker, `--effort`, [`CLAUDE_CODE_EFF… |
|
v2.1.242/model |
Documentation arrivedAnthropic's documentation has since written up /model, on All settings.
the line in the docsCap the [effort level](/docs/en/model-config#adjust-effort-level) a session can use, leaving lower levels available. Any higher level runs at the cap instead, including one from `/effort`, the `/model` picker, `--effort`, [`CLAUDE_CODE_EFF… |
|
v2.1.239/model |
Documentation arrivedAnthropic's documentation has since written up /model, on All settings.
the line in the docsCap the [effort level](/docs/en/model-config#adjust-effort-level) a session can use, leaving lower levels available. Any higher level runs at the cap instead, including one from `/effort`, the `/model` picker, `--effort`, [`CLAUDE_CODE_EFF… |
|
v2.1.236/model |
Documentation arrivedAnthropic's documentation has since written up /model, on All settings.
the line in the docsCap the [effort level](/docs/en/model-config#adjust-effort-level) a session can use, leaving lower levels available. Any higher level runs at the cap instead, including one from `/effort`, the `/model` picker, `--effort`, [`CLAUDE_CODE_EFF… |
|
v2.1.234/model |
Documentation arrivedAnthropic's documentation has since written up /model, on All settings.
the line in the docsCap the [effort level](/docs/en/model-config#adjust-effort-level) a session can use, leaving lower levels available. Any higher level runs at the cap instead, including one from `/effort`, the `/model` picker, `--effort`, [`CLAUDE_CODE_EFF… |
|
v2.1.232/model |
Documentation arrivedAnthropic's documentation has since written up /model, on All settings.
the line in the docsCap the [effort level](/docs/en/model-config#adjust-effort-level) a session can use, leaving lower levels available. Any higher level runs at the cap instead, including one from `/effort`, the `/model` picker, `--effort`, [`CLAUDE_CODE_EFF… |
|
v2.1.248remote-control |
Documentation arrivedA small documentation edit on Continue local sessions from any device with Remote Control touched a line naming remote-control after this was published.
the line in the docsAll traffic travels through the Anthropic API over TLS, the same transport security as any Claude Code session. The connection uses multiple short-lived credentials, each scoped to a single purpose and expiring independently. When a `claud… |
|
v2.1.248remote-control |
Documentation arrivedA small documentation edit on Continue local sessions from any device with Remote Control touched a line naming remote-control after this was published.
the line in the docsAll traffic travels through the Anthropic API over TLS, the same transport security as any Claude Code session. The connection uses multiple short-lived credentials, each scoped to a single purpose and expiring independently. When a `claud… |
|
v2.1.248claude remote-control |
Documentation arrivedA small documentation edit on Continue local sessions from any device with Remote Control touched a line naming claude remote-control after this was published.
the line in the docsAll traffic travels through the Anthropic API over TLS, the same transport security as any Claude Code session. The connection uses multiple short-lived credentials, each scoped to a single purpose and expiring independently. When a `claud… |