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 |
|---|---|---|
v2.1.267SubagentHandback |
Documentation arrivedA small documentation edit on Create custom subagents touched a line naming SubagentHandback after this was published.
the line in the docsThe second filter applies to subagents running in the background. Apart from `Agent` and `ExitPlanMode`, which follow the first filter's conditions wherever the subagent runs, a background subagent keeps every MCP tool but only these built… |
|
v2.1.265NotebookEdit |
Documentation arrivedA small documentation edit on Create custom subagents touched a line naming NotebookEdit after this was published.
the line in the docsThe second filter applies to subagents running in the background. Apart from `Agent` and `ExitPlanMode`, which follow the first filter's conditions wherever the subagent runs, a background subagent keeps every MCP tool but only these built… |
|
v2.1.265ExitPlanMode |
Documentation arrivedA small documentation edit on Create custom subagents touched a line naming ExitPlanMode after this was published.
the line in the docsThe second filter applies to subagents running in the background. Apart from `Agent` and `ExitPlanMode`, which follow the first filter's conditions wherever the subagent runs, a background subagent keeps every MCP tool but only these built… |
|
v2.1.259ExitPlanMode |
Documentation arrivedA small documentation edit on Create custom subagents touched a line naming ExitPlanMode after this was published.
the line in the docsThe second filter applies to subagents running in the background. Apart from `Agent` and `ExitPlanMode`, which follow the first filter's conditions wherever the subagent runs, a background subagent keeps every MCP tool but only these built… |
|
v2.1.257ToolSearch |
Documentation arrivedA small documentation edit on Create custom subagents touched a line naming ToolSearch after this was published.
the line in the docsThe second filter applies to subagents running in the background. Apart from `Agent` and `ExitPlanMode`, which follow the first filter's conditions wherever the subagent runs, a background subagent keeps every MCP tool but only these built… |
|
v2.1.268SendMessage |
Documentation arrivedA small documentation edit on Create custom subagents touched a line naming SendMessage after this was published.
the line in the docsThe second filter applies to subagents running in the background. Apart from `Agent` and `ExitPlanMode`, which follow the first filter's conditions wherever the subagent runs, a background subagent keeps every MCP tool but only these built… |
|
v2.1.268SendMessage |
Documentation arrivedA small documentation edit on Create custom subagents touched a line naming SendMessage after this was published.
the line in the docsThe second filter applies to subagents running in the background. Apart from `Agent` and `ExitPlanMode`, which follow the first filter's conditions wherever the subagent runs, a background subagent keeps every MCP tool but only these built… |
|
v2.1.251SendMessage |
Documentation arrivedA small documentation edit on Create custom subagents touched a line naming SendMessage after this was published.
the line in the docsThe second filter applies to subagents running in the background. Apart from `Agent` and `ExitPlanMode`, which follow the first filter's conditions wherever the subagent runs, a background subagent keeps every MCP tool but only these built… |
|
v2.1.251GIT_ALLOW_PROTOCOL |
Documentation arrivedAnthropic's documentation has since written up GIT_ALLOW_PROTOCOL, on Claude Code changelog.
the line in the docs* Self-hosted runner: Changed git in lifecycle hooks to ignore hook folders and programs named in the runner's shared git files; local-path and `git://` remotes there now need `GIT_ALLOW_PROTOCOL` |
|
v2.1.248GIT_ALLOW_PROTOCOL |
Documentation arrivedAnthropic's documentation has since written up GIT_ALLOW_PROTOCOL, on Claude Code changelog.
the line in the docs* Self-hosted runner: Changed git in lifecycle hooks to ignore hook folders and programs named in the runner's shared git files; local-path and `git://` remotes there now need `GIT_ALLOW_PROTOCOL` |
|
v2.1.259claude mcp remove |
Documentation arrivedAnthropic's documentation has since written up claude mcp remove, on Claude Code changelog.
the line in the docs* Fixed an MCP server re-added under the same name after `claude mcp remove` still showing as needing authentication instead of reconnecting |
|
v2.1.277claude-sonnet-5 |
Documentation arrivedA small documentation edit on Create custom subagents touched a line naming claude-sonnet-5 after this was published.
the line in the docs* **Full model ID**: use a full model ID such as `claude-opus-5-5` or `claude-sonnet-5`. Accepts the same values as the `--model` flag |
|
v2.1.242ANTHROPIC_CUSTOM_MODEL_OPTION |
Documentation arrivedAnthropic's documentation has since written up ANTHROPIC_CUSTOM_MODEL_OPTION, on Model configuration.
the line in the docsexport ANTHROPIC_CUSTOM_MODEL_OPTION="my-gateway/claude-opus-5-5" |
|
v2.1.242alwaysThinkingEnabled |
Documentation arrivedAnthropic's documentation has since written up alwaysThinkingEnabled, on Model configuration.
the line in the docs| Set the global default | Run `/config` and toggle thinking mode. Saved as `alwaysThinkingEnabled` in `~/.claude/settings.json` | |
|
v2.1.242MAX_THINKING_TOKENS |
Documentation arrivedAnthropic's documentation has since written up MAX_THINKING_TOKENS, on Environment variables.
the line in the docs| `CLAUDE_CODE_DISABLE_THINKING` | Set to `1` to omit the `thinking` parameter from API requests entirely. This is a compatibility option for proxies and gateways that reject the parameter. On models that think by default, omitting the par… |
|
v2.1.242MAX_THINKING_TOKENS |
Documentation arrivedA small documentation edit on Desktop application touched a line naming MAX_THINKING_TOKENS after this was published.
the line in the docs[Extended thinking](/docs/en/model-config#extended-thinking) is enabled by default, which improves performance on complex reasoning tasks but uses additional tokens. On the Anthropic API, set `MAX_THINKING_TOKENS` to `0` in the local envir… |
|
v2.1.260/model fable |
Documentation arrivedAnthropic's documentation has since written up /model fable, on Communications kit.
the line in the docs| Fable | The hardest, longest-running tasks. Opt-in only: select it with `/model fable`. Cybersecurity or biology content triggers [automatic model fallback to Opus](/docs/en/model-config#automatic-model-fallback) | |
|
v2.1.265/release-notes |
Documentation arrivedA small documentation edit on overview touched a line naming /release-notes after this was published.
the line in the docs<Card id="claude-opus-5-5" title="Claude Opus 5.5" icon="file" href="https://platform.claude.com/docs/en/release-notes/system-prompts/claude-opus-5-5" /> |
|
v2.1.246/release-notes |
Documentation arrivedA small documentation edit on overview touched a line naming /release-notes after this was published.
the line in the docs<Card id="claude-opus-5-5" title="Claude Opus 5.5" icon="file" href="https://platform.claude.com/docs/en/release-notes/system-prompts/claude-opus-5-5" /> |
|
v2.1.274--model |
Documentation arrivedA small documentation edit on On a remote host without a browser: touched a line naming --model after this was published.
the line in the docs--model claude-opus-5-5 \ |
|
v2.1.259unpin |
Documentation arrivedAnthropic's documentation has since written up unpin, on mcp-connector.
the line in the docsThe following example sends one request with an unpinned toolset, copies the returned list into the toolset's `tools` field, and sends the request again. The second response has no `mcp_tool_listing` block, because the API doesn't ask the … |
|
v2.1.275insert |
Documentation arrivedAnthropic's documentation has since written up insert, on optimizing-for-cost-and-intelligence.
the line in the docsAnthropic measured the triage job from [Trim input and context tokens](https://platform.claude.com/docs/en/about-claude/models/optimizing-for-cost-and-intelligence#trim-input-and-context-tokens) with pauses inserted before some turns to si… |
|
v2.1.277claude-opus-5 |
Documentation arrivedA small documentation edit on model-deprecations touched a line naming claude-opus-5 after this was published.
the line in the docs| claude-opus-5-5 | Active | N/A | Not sooner than September 22, 2027 | |
|
v2.1.275claude-opus-5 |
Documentation arrivedA small documentation edit on model-deprecations touched a line naming claude-opus-5 after this was published.
the line in the docs| claude-opus-5-5 | Active | N/A | Not sooner than September 22, 2027 | |
|
v2.1.274Markdown |
Documentation arrivedA small documentation edit on Artifacts touched a line naming Markdown after this was published.
the line in the docsWhen Claude saves the same filename again in the same session, the artifact gains a new version. You can also edit text-based artifacts (Markdown, code, plain text) directly: click **Edit content**, make changes, and **Save** to create a n… |
|
v2.1.267assets |
Documentation arrivedA small documentation edit on Skills in Claude Desktop touched a line naming assets after this was published.
the line in the docs**Mind the text-only rule.** A skill delivered through the admin portal can contain only text files, in these formats: `.md`, `.txt`, `.json`, `.yaml`, `.yml`, `.csv`. The skill authoring guide describes scripts and binary assets such as i… |
|
v2.1.275icon |
Documentation arrivedA small documentation edit on Manage plugins and connectors touched a line naming icon after this was published.
the line in the docsApart from the optional icon, everything in an archive must be text in UTF-8. There is no way to ship a script, or any other binary asset such as an image, through the card. File and folder names must be ASCII. Nothing in the archive may s… |
|
v2.1.275icon |
Documentation arrivedA small documentation edit on Manage plugins and connectors touched a line naming icon after this was published.
the line in the docsApart from the optional icon, everything in an archive must be text in UTF-8. There is no way to ship a script, or any other binary asset such as an image, through the card. File and folder names must be ASCII. Nothing in the archive may s… |
|
v2.1.275statusLine |
Documentation arrivedA small documentation edit on Customize your status line touched a line naming statusLine after this was published.
the line in the docsRun `/statusline` and ask it to remove or clear your status line (for example, `/statusline delete`, `/statusline clear`, `/statusline remove it`). You can also manually delete the `statusLine` field from your settings.json. |
|
v2.1.277skillOverrides |
Documentation arrivedA small documentation edit on Extend Claude with skills touched a line naming skillOverrides after this was published.
the line in the docsTo raise the budget, set the [`skillListingBudgetFraction`](/docs/en/settings-reference#skilllistingbudgetfraction) setting (for example, `0.02` = 2%) or the `SLASH_COMMAND_TOOL_CHAR_BUDGET` environment variable to a fixed character count.… |
|
v2.1.275maxTokens |
Documentation arrivedAnthropic's documentation has since written up maxTokens, on preserved-thinking.
the line in the docs.maxTokens(16000L) |
|
v2.1.268tool_use_id |
Documentation arrivedA small documentation edit on Run Claude Code programmatically touched a line naming tool_use_id after this was published.
the line in the docsWhen you enable either option, Claude Code forwards messages from [subagents at every nesting depth](/docs/en/sub-agents#let-subagents-spawn-their-own-subagents), whether each one was spawned with the Agent tool or started as a [forked ski… |
|
v2.1.277/cost |
Documentation arrivedA small documentation edit on Run Claude Code programmatically touched a line naming /cost after this was published.
the line in the docsWith `--output-format json`, the response payload includes `total_cost_usd` and a per-model cost breakdown, so scripted callers can track spend without consulting the [usage dashboard](/docs/en/costs). When you continue an earlier conversa… |
|
v2.1.242--output-format |
Documentation arrivedA small documentation edit on Run Claude Code programmatically touched a line naming --output-format after this was published.
the line in the docsWith `--output-format json`, the response payload includes `total_cost_usd` and a per-model cost breakdown, so scripted callers can track spend without consulting the [usage dashboard](/docs/en/costs). When you continue an earlier conversa… |
|
v2.1.277claude-md |
Documentation arrivedA small documentation edit on Extend Claude Code touched a line naming claude-md after this was published.
the line in the docs* **CLAUDE.md files** are additive: all levels contribute content to Claude's context simultaneously. Files from your working directory and above load at launch; subdirectories load as you work in them. When instructions conflict, Claude u… |
|
v2.1.246--max-budget-usd |
Documentation arrivedA small documentation edit on Manage costs effectively touched a line naming --max-budget-usd after this was published.
the line in the docsFor a response from the Claude API billed at the 1.1× [data residency rate](https://platform.claude.com/docs/en/about-claude/pricing#data-residency-pricing), Claude Code multiplies the list price of that response's tokens by 1.1 in the ses… |
|
v2.1.275/status |
Documentation arrivedA small documentation edit on Manage costs effectively touched a line naming /status after this was published.
the line in the docsFor a response from the Claude API billed at the 1.1× [data residency rate](https://platform.claude.com/docs/en/about-claude/pricing#data-residency-pricing), Claude Code multiplies the list price of that response's tokens by 1.1 in the ses… |
|
v2.1.273/status |
Documentation arrivedA small documentation edit on Manage costs effectively touched a line naming /status after this was published.
the line in the docsFor a response from the Claude API billed at the 1.1× [data residency rate](https://platform.claude.com/docs/en/about-claude/pricing#data-residency-pricing), Claude Code multiplies the list price of that response's tokens by 1.1 in the ses… |
|
v2.1.273/status |
Documentation arrivedA small documentation edit on Manage costs effectively touched a line naming /status after this was published.
the line in the docsFor a response from the Claude API billed at the 1.1× [data residency rate](https://platform.claude.com/docs/en/about-claude/pricing#data-residency-pricing), Claude Code multiplies the list price of that response's tokens by 1.1 in the ses… |
|
v2.1.269viewMode |
Documentation arrivedAnthropic's documentation has since written up viewMode, on CLI reference.
the line in the docs| `--verbose` | Enable verbose logging, shows full turn-by-turn output. Overrides the [`viewMode`](/docs/en/settings-reference#viewmode) setting for this session | `claude --verbose` | |
|
v2.1.267claude remote-control |
Documentation arrivedAnthropic's documentation has since written up claude remote-control, on CLI reference.
the line in the docs| `--remote-control-session-name-prefix <prefix>` | Prefix for auto-generated [Remote Control](/docs/en/remote-control) session names when no explicit name is set. Defaults to your machine's hostname, producing names like `myhost-graceful-… |
|
v2.1.265claude remote-control |
Documentation arrivedAnthropic's documentation has since written up claude remote-control, on CLI reference.
the line in the docs| `--remote-control-session-name-prefix <prefix>` | Prefix for auto-generated [Remote Control](/docs/en/remote-control) session names when no explicit name is set. Defaults to your machine's hostname, producing names like `myhost-graceful-… |
|
v2.1.275--remote |
Documentation arrivedAnthropic's documentation has since written up --remote, on CLI reference.
the line in the docs| `--remote` | Deprecated alias for `--cloud`, including the existing-session form | `claude --remote "Fix the login bug"` | |
|
v2.1.248--ref |
Documentation arrivedAnthropic's documentation has since written up --ref, on CLI reference.
the line in the docs| `--ref <branch>` | With `--environment`, base the new session's checkout on a named ref instead of local `HEAD` | `claude -p "Run the smoke test" --environment ccpool_abc123 --ref main` | |
|
v2.1.273--no-chrome |
Documentation arrivedAnthropic's documentation has since written up --no-chrome, on CLI reference.
the line in the docs| `--no-chrome` | Disable [Chrome browser integration](/docs/en/chrome) for this session | `claude --no-chrome` | |
|
v2.1.273--no-chrome |
Documentation arrivedAnthropic's documentation has since written up --no-chrome, on CLI reference.
the line in the docs| `--no-chrome` | Disable [Chrome browser integration](/docs/en/chrome) for this session | `claude --no-chrome` | |
|
v2.1.277/mcp |
Documentation arrivedAnthropic's documentation has since written up /mcp, on CLI reference.
the line in the docs| `--mcp-config` | Load MCP servers from JSON files or strings (space-separated). When you pass this flag with `-p`, Claude Code waits for still-pending servers to connect before running the first turn, up to the [`MCP_TIMEOUT`](/docs/en/e… |
|
v2.1.246--max-budget-usd |
Documentation arrivedAnthropic's documentation has since written up --max-budget-usd, on CLI reference.
the line in the docs| `--max-budget-usd` | Maximum dollar amount to spend on API calls before stopping (print mode only). Spend from [subagents](/docs/en/sub-agents) counts toward the cap. When you return to a conversation with `--continue` or `--resume`, tot… |
|
v2.1.278--verbose |
Documentation arrivedAnthropic's documentation has since written up --verbose, on CLI reference.
the line in the docs| `--forward-subagent-text` | Emit [subagent](/docs/en/sub-agents) text and thinking blocks in the output stream as `assistant` and `user` messages with `parent_tool_use_id` set, so you can reconstruct each subagent's transcript. Without t… |
|
v2.1.278--verbose |
Documentation arrivedAnthropic's documentation has since written up --verbose, on CLI reference.
the line in the docs| `--forward-subagent-text` | Emit [subagent](/docs/en/sub-agents) text and thinking blocks in the output stream as `assistant` and `user` messages with `parent_tool_use_id` set, so you can reconstruct each subagent's transcript. Without t… |