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 |
|---|---|---|
v2.1.265ANTHROPIC_AUTH_TOKEN |
Documentation arrivedAnthropic's documentation has since written up ANTHROPIC_AUTH_TOKEN, on Connect Claude Code to an LLM gateway.
the line in the docs* **Amazon Bedrock, Google Cloud's Agent Platform, or Claude Platform on AWS**: add `ANTHROPIC_AUTH_TOKEN` after the block. Claude Code sends it to the gateway as an `Authorization: Bearer` header. For a credential in a different scheme or… |
|
v2.1.257ANTHROPIC_AUTH_TOKEN |
Documentation arrivedAnthropic's documentation has since written up ANTHROPIC_AUTH_TOKEN, on Connect Claude Code to an LLM gateway.
the line in the docs* **Amazon Bedrock, Google Cloud's Agent Platform, or Claude Platform on AWS**: add `ANTHROPIC_AUTH_TOKEN` after the block. Claude Code sends it to the gateway as an `Authorization: Bearer` header. For a credential in a different scheme or… |
|
v2.1.257ANTHROPIC_AUTH_TOKEN |
Documentation arrivedAnthropic's documentation has since written up ANTHROPIC_AUTH_TOKEN, on Connect Claude Code to an LLM gateway.
the line in the docs* **Amazon Bedrock, Google Cloud's Agent Platform, or Claude Platform on AWS**: add `ANTHROPIC_AUTH_TOKEN` after the block. Claude Code sends it to the gateway as an `Authorization: Bearer` header. For a credential in a different scheme or… |
|
v2.1.233ANTHROPIC_AUTH_TOKEN |
Documentation arrivedAnthropic's documentation has since written up ANTHROPIC_AUTH_TOKEN, on Connect Claude Code to an LLM gateway.
the line in the docs* **Amazon Bedrock, Google Cloud's Agent Platform, or Claude Platform on AWS**: add `ANTHROPIC_AUTH_TOKEN` after the block. Claude Code sends it to the gateway as an `Authorization: Bearer` header. For a credential in a different scheme or… |
|
v2.1.229ANTHROPIC_AUTH_TOKEN |
Documentation arrivedAnthropic's documentation has since written up ANTHROPIC_AUTH_TOKEN, on Connect Claude Code to an LLM gateway.
the line in the docs* **Amazon Bedrock, Google Cloud's Agent Platform, or Claude Platform on AWS**: add `ANTHROPIC_AUTH_TOKEN` after the block. Claude Code sends it to the gateway as an `Authorization: Bearer` header. For a credential in a different scheme or… |
|
v2.1.260PostModelSwitch |
Documentation arrivedAnthropic's documentation has since written up PostModelSwitch, on Hooks reference.
the line in the docs| SessionStart, SubagentStart, PostModelSwitch | Context only | `hookSpecificOutput.additionalContext` adds context for Claude. SessionStart also accepts [`initialUserMessage`, `watchPaths`, `sessionTitle`, and `reloadSkills`](#sessionstar… |
|
v2.1.251PostModelSwitch |
Documentation arrivedAnthropic's documentation has since written up PostModelSwitch, on Hooks reference.
the line in the docs| SessionStart, SubagentStart, PostModelSwitch | Context only | `hookSpecificOutput.additionalContext` adds context for Claude. SessionStart also accepts [`initialUserMessage`, `watchPaths`, `sessionTitle`, and `reloadSkills`](#sessionstar… |
|
v2.1.260PreModelSwitch |
Documentation arrivedAnthropic's documentation has since written up PreModelSwitch, on Hooks reference.
the line in the docs| PreModelSwitch | `hookSpecificOutput` or top-level `decision` | `permissionDecision` (allow/deny/ask), `permissionDecisionReason`. `decision: "block"` also [cancels the switch](#premodelswitch-decision-control) | |
|
v2.1.251PreModelSwitch |
Documentation arrivedAnthropic's documentation has since written up PreModelSwitch, on Hooks reference.
the line in the docs| PreModelSwitch | `hookSpecificOutput` or top-level `decision` | `permissionDecision` (allow/deny/ask), `permissionDecisionReason`. `decision: "block"` also [cancels the switch](#premodelswitch-decision-control) | |
|
v2.1.251PreModelSwitch |
Documentation arrivedAnthropic's documentation has since written up PreModelSwitch, on Hooks reference.
the line in the docs| PreModelSwitch | `hookSpecificOutput` or top-level `decision` | `permissionDecision` (allow/deny/ask), `permissionDecisionReason`. `decision: "block"` also [cancels the switch](#premodelswitch-decision-control) | |
|
v2.1.251PreModelSwitch |
Documentation arrivedAnthropic's documentation has since written up PreModelSwitch, on Hooks reference.
the line in the docs| PreModelSwitch | `hookSpecificOutput` or top-level `decision` | `permissionDecision` (allow/deny/ask), `permissionDecisionReason`. `decision: "block"` also [cancels the switch](#premodelswitch-decision-control) | |
|
v2.1.248TeammateIdle |
Documentation arrivedAnthropic's documentation has since written up TeammateIdle, on Hooks reference.
the line in the docs| TeammateIdle, TaskCompleted | Exit code or `continue: false` | Exit code 2 blocks the action with stderr feedback. JSON `{"continue": false, "stopReason": "..."}` also stops the teammate entirely, matching `Stop` hook behavior; [TaskComp… |
|
v2.1.248TaskCompleted |
Documentation arrivedAnthropic's documentation has since written up TaskCompleted, on Hooks reference.
the line in the docs| TeammateIdle, TaskCompleted | Exit code or `continue: false` | Exit code 2 blocks the action with stderr feedback. JSON `{"continue": false, "stopReason": "..."}` also stops the teammate entirely, matching `Stop` hook behavior; [TaskComp… |
|
v2.1.251additionalContext |
Documentation arrivedAnthropic's documentation has since written up additionalContext, on Hooks reference.
the line in the docs| UserPromptSubmit, UserPromptExpansion, PostToolUse, PostToolUseFailure, PostToolBatch, Stop, SubagentStop, ConfigChange, PreCompact | Top-level `decision` | `decision: "block"`, `reason`. Stop and SubagentStop also accept `hookSpecificOu… |
|
v2.1.248UserPromptExpansion |
Documentation arrivedAnthropic's documentation has since written up UserPromptExpansion, on Hooks reference.
the line in the docs| UserPromptSubmit, UserPromptExpansion, PostToolUse, PostToolUseFailure, PostToolBatch, Stop, SubagentStop, ConfigChange, PreCompact | Top-level `decision` | `decision: "block"`, `reason`. Stop and SubagentStop also accept `hookSpecificOu… |
|
v2.1.238UserPromptExpansion |
Documentation arrivedAnthropic's documentation has since written up UserPromptExpansion, on Hooks reference.
the line in the docs| UserPromptSubmit, UserPromptExpansion, PostToolUse, PostToolUseFailure, PostToolBatch, Stop, SubagentStop, ConfigChange, PreCompact | Top-level `decision` | `decision: "block"`, `reason`. Stop and SubagentStop also accept `hookSpecificOu… |
|
v2.1.261claude ultrareview |
Documentation arrivedAnthropic's documentation has since written up claude ultrareview, on CLI reference.
the line in the docs| `claude ultrareview [target]` | Run [ultrareview](/docs/en/ultrareview#run-ultrareview-non-interactively) non-interactively. Prints findings to stdout and exits 0 on success or 1 on failure. Use `--json` for the raw payload and `--timeou… |
|
v2.1.259--timeout |
Documentation arrivedAnthropic's documentation has since written up --timeout, on CLI reference.
the line in the docs| `claude ultrareview [target]` | Run [ultrareview](/docs/en/ultrareview#run-ultrareview-non-interactively) non-interactively. Prints findings to stdout and exits 0 on success or 1 on failure. Use `--json` for the raw payload and `--timeou… |
|
v2.1.257--post |
Documentation arrivedAnthropic's documentation has since written up --post, on CLI reference.
the line in the docs| `claude ultrareview [target]` | Run [ultrareview](/docs/en/ultrareview#run-ultrareview-non-interactively) non-interactively. Prints findings to stdout and exits 0 on success or 1 on failure. Use `--json` for the raw payload and `--timeou… |
|
v2.1.242--post |
Documentation arrivedAnthropic's documentation has since written up --post, on CLI reference.
the line in the docs| `claude ultrareview [target]` | Run [ultrareview](/docs/en/ultrareview#run-ultrareview-non-interactively) non-interactively. Prints findings to stdout and exits 0 on success or 1 on failure. Use `--json` for the raw payload and `--timeou… |
|
v2.1.234setup-token |
Documentation arrivedAnthropic's documentation has since written up setup-token, on CLI reference.
the line in the docs| `claude setup-token` | Generate a long-lived OAuth token for CI and scripts. Prints the token to the terminal without saving it. Requires a Claude subscription. See [Generate a long-lived token](/docs/en/authentication#generate-a-long-li… |
|
v2.1.234claude setup-token |
Documentation arrivedAnthropic's documentation has since written up claude setup-token, on CLI reference.
the line in the docs| `claude setup-token` | Generate a long-lived OAuth token for CI and scripts. Prints the token to the terminal without saving it. Requires a Claude subscription. See [Generate a long-lived token](/docs/en/authentication#generate-a-long-li… |
|
v2.1.246--name |
Documentation arrivedAnthropic's documentation has since written up --name, on CLI reference.
the line in the docs| `claude remote-control` | Start a [Remote Control](/docs/en/remote-control) server to control Claude Code from Claude.ai or the Claude app. Runs in server mode (no local interactive session). See [Server mode flags](/docs/en/remote-contr… |
|
v2.1.232--name |
Documentation arrivedAnthropic's documentation has since written up --name, on CLI reference.
the line in the docs| `claude remote-control` | Start a [Remote Control](/docs/en/remote-control) server to control Claude Code from Claude.ai or the Claude app. Runs in server mode (no local interactive session). See [Server mode flags](/docs/en/remote-contr… |
|
v2.1.257.claude.json |
Documentation arrivedAnthropic's documentation has since written up .claude.json, on CLI reference.
the line in the docs| `claude project purge [path]` | Delete all local Claude Code state for a project: transcripts, task lists, debug logs, file-edit history, prompt history lines, and the project's entry in `~/.claude.json`. Omit `[path]` to pick from an in… |
|
v2.1.247~/.claude.json |
Documentation arrivedAnthropic's documentation has since written up ~/.claude.json, on CLI reference.
the line in the docs| `claude project purge [path]` | Delete all local Claude Code state for a project: transcripts, task lists, debug logs, file-edit history, prompt history lines, and the project's entry in `~/.claude.json`. Omit `[path]` to pick from an in… |
|
v2.1.238~/.claude.json |
Documentation arrivedAnthropic's documentation has since written up ~/.claude.json, on CLI reference.
the line in the docs| `claude project purge [path]` | Delete all local Claude Code state for a project: transcripts, task lists, debug logs, file-edit history, prompt history lines, and the project's entry in `~/.claude.json`. Omit `[path]` to pick from an in… |
|
v2.1.234~/.claude.json |
Documentation arrivedAnthropic's documentation has since written up ~/.claude.json, on CLI reference.
the line in the docs| `claude project purge [path]` | Delete all local Claude Code state for a project: transcripts, task lists, debug logs, file-edit history, prompt history lines, and the project's entry in `~/.claude.json`. Omit `[path]` to pick from an in… |
|
v2.1.265claude import |
Documentation arrivedAnthropic's documentation has since written up claude import, on CLI reference.
the line in the docs| `claude import [source]` | Start an interactive session that runs [`/import`](/docs/en/commands#all-commands) to bring configuration from other coding agents into Claude Code. Accepts the same `--dry-run` and `--yes` options as the comma… |
|
v2.1.265claude import |
Documentation arrivedAnthropic's documentation has since written up claude import, on CLI reference.
the line in the docs| `claude import [source]` | Start an interactive session that runs [`/import`](/docs/en/commands#all-commands) to bring configuration from other coding agents into Claude Code. Accepts the same `--dry-run` and `--yes` options as the comma… |
|
v2.1.265/import |
Documentation arrivedAnthropic's documentation has since written up /import, on CLI reference.
the line in the docs| `claude import [source]` | Start an interactive session that runs [`/import`](/docs/en/commands#all-commands) to bring configuration from other coding agents into Claude Code. Accepts the same `--dry-run` and `--yes` options as the comma… |
|
v2.1.265/import |
Documentation arrivedAnthropic's documentation has since written up /import, on CLI reference.
the line in the docs| `claude import [source]` | Start an interactive session that runs [`/import`](/docs/en/commands#all-commands) to bring configuration from other coding agents into Claude Code. Accepts the same `--dry-run` and `--yes` options as the comma… |
|
v2.1.265/import |
Documentation arrivedAnthropic's documentation has since written up /import, on CLI reference.
the line in the docs| `claude import [source]` | Start an interactive session that runs [`/import`](/docs/en/commands#all-commands) to bring configuration from other coding agents into Claude Code. Accepts the same `--dry-run` and `--yes` options as the comma… |
|
v2.1.265/import |
Documentation arrivedAnthropic's documentation has since written up /import, on CLI reference.
the line in the docs| `claude import [source]` | Start an interactive session that runs [`/import`](/docs/en/commands#all-commands) to bring configuration from other coding agents into Claude Code. Accepts the same `--dry-run` and `--yes` options as the comma… |
|
v2.1.261/doctor |
Documentation arrivedAnthropic's documentation has since written up /doctor, on CLI reference.
the line in the docs| `claude doctor` | Print read-only installation and settings diagnostics from the terminal without starting a session, including install health, settings-file validation errors, and Remote Control eligibility. For the in-session setup che… |
|
v2.1.257/doctor |
Documentation arrivedAnthropic's documentation has since written up /doctor, on CLI reference.
the line in the docs| `claude doctor` | Print read-only installation and settings diagnostics from the terminal without starting a session, including install health, settings-file validation errors, and Remote Control eligibility. For the in-session setup che… |
|
v2.1.239/doctor |
Documentation arrivedAnthropic's documentation has since written up /doctor, on CLI reference.
the line in the docs| `claude doctor` | Print read-only installation and settings diagnostics from the terminal without starting a session, including install health, settings-file validation errors, and Remote Control eligibility. For the in-session setup che… |
|
v2.1.233/doctor |
Documentation arrivedAnthropic's documentation has since written up /doctor, on CLI reference.
the line in the docs| `claude doctor` | Print read-only installation and settings diagnostics from the terminal without starting a session, including install health, settings-file validation errors, and Remote Control eligibility. For the in-session setup che… |
|
v2.1.233/doctor |
Documentation arrivedAnthropic's documentation has since written up /doctor, on CLI reference.
the line in the docs| `claude doctor` | Print read-only installation and settings diagnostics from the terminal without starting a session, including install health, settings-file validation errors, and Remote Control eligibility. For the in-session setup che… |
|
v2.1.232/doctor |
Documentation arrivedAnthropic's documentation has since written up /doctor, on CLI reference.
the line in the docs| `claude doctor` | Print read-only installation and settings diagnostics from the terminal without starting a session, including install health, settings-file validation errors, and Remote Control eligibility. For the in-session setup che… |
|
v2.1.229/doctor |
Documentation arrivedAnthropic's documentation has since written up /doctor, on CLI reference.
the line in the docs| `claude doctor` | Print read-only installation and settings diagnostics from the terminal without starting a session, including install health, settings-file validation errors, and Remote Control eligibility. For the in-session setup che… |
|
v2.1.261claude doctor |
Documentation arrivedAnthropic's documentation has since written up claude doctor, on CLI reference.
the line in the docs| `claude doctor` | Print read-only installation and settings diagnostics from the terminal without starting a session, including install health, settings-file validation errors, and Remote Control eligibility. For the in-session setup che… |
|
v2.1.248claude doctor |
Documentation arrivedAnthropic's documentation has since written up claude doctor, on CLI reference.
the line in the docs| `claude doctor` | Print read-only installation and settings diagnostics from the terminal without starting a session, including install health, settings-file validation errors, and Remote Control eligibility. For the in-session setup che… |
|
v2.1.229claude doctor |
Documentation arrivedAnthropic's documentation has since written up claude doctor, on CLI reference.
the line in the docs| `claude doctor` | Print read-only installation and settings diagnostics from the terminal without starting a session, including install health, settings-file validation errors, and Remote Control eligibility. For the in-session setup che… |
|
v2.1.259--permission-mode |
Documentation arrivedAnthropic's documentation has since written up --permission-mode, on CLI reference.
the line in the docs| `claude agents` | Open [agent view](/docs/en/agent-view) to monitor and dispatch parallel background sessions. Use `--cwd <path>` to show only sessions started under that directory, or `--json` to print active sessions as a JSON array fo… |
|
v2.1.246--permission-mode |
Documentation arrivedAnthropic's documentation has since written up --permission-mode, on CLI reference.
the line in the docs| `claude agents` | Open [agent view](/docs/en/agent-view) to monitor and dispatch parallel background sessions. Use `--cwd <path>` to show only sessions started under that directory, or `--json` to print active sessions as a JSON array fo… |
|
v2.1.267--effort |
Documentation arrivedAnthropic's documentation has since written up --effort, on CLI reference.
the line in the docs| `claude agents` | Open [agent view](/docs/en/agent-view) to monitor and dispatch parallel background sessions. Use `--cwd <path>` to show only sessions started under that directory, or `--json` to print active sessions as a JSON array fo… |
|
v2.1.236--model |
Documentation arrivedAnthropic's documentation has since written up --model, on CLI reference.
the line in the docs| `claude agents` | Open [agent view](/docs/en/agent-view) to monitor and dispatch parallel background sessions. Use `--cwd <path>` to show only sessions started under that directory, or `--json` to print active sessions as a JSON array fo… |
|
v2.1.257--add-dir |
Documentation arrivedAnthropic's documentation has since written up --add-dir, on CLI reference.
the line in the docs| `claude agents` | Open [agent view](/docs/en/agent-view) to monitor and dispatch parallel background sessions. Use `--cwd <path>` to show only sessions started under that directory, or `--json` to print active sessions as a JSON array fo… |
|
v2.1.234--add-dir |
Documentation arrivedAnthropic's documentation has since written up --add-dir, on CLI reference.
the line in the docs| `claude agents` | Open [agent view](/docs/en/agent-view) to monitor and dispatch parallel background sessions. Use `--cwd <path>` to show only sessions started under that directory, or `--json` to print active sessions as a JSON array fo… |