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 |
|---|---|---|
v2.1.277/stats |
Documentation arrivedAnthropic's documentation has since written up /stats, on Explore the .claude directory.
the line in the docs| `~/.claude/stats-cache.json` | Historical totals shown by `/usage` | |
|
v2.1.277TMPDIR |
Documentation arrivedAnthropic's documentation has since written up TMPDIR, on Explore the .claude directory.
the line in the docs| `image-cache/<session>/` | Attached images saved by Claude Code v2.1.274 and earlier. Later versions save pasted and attached images outside `~/.claude`, in an `images/` directory for each session under the temp directory that [`CLAUDE_C… |
|
v2.1.277TMPDIR |
Documentation arrivedAnthropic's documentation has since written up TMPDIR, on Explore the .claude directory.
the line in the docs| `image-cache/<session>/` | Attached images saved by Claude Code v2.1.274 and earlier. Later versions save pasted and attached images outside `~/.claude`, in an `images/` directory for each session under the temp directory that [`CLAUDE_C… |
|
v2.1.277/cost |
Documentation arrivedAnthropic's documentation has since written up /cost, on Explore the .claude directory.
the line in the docs| `usage-data/` | `report.html` and timestamped report copies written by [`/insights`](/docs/en/costs#analyze-your-usage-patterns), plus cached per-session analysis data used to build them | |
|
v2.1.277/plugin |
Documentation arrivedAnthropic's documentation has since written up /plugin, on Explore the .claude directory.
the line in the docs| Installed plugins | `~/.claude/plugins` | Cloned marketplaces, installed plugin versions, and per-plugin data, managed by `claude plugin` commands. Plugins [synced from your claude.ai account](/docs/en/plugins-reference#synced-plugins) d… |
|
v2.1.277/plugin |
Documentation arrivedAnthropic's documentation has since written up /plugin, on Explore the .claude directory.
the line in the docs| Installed plugins | `~/.claude/plugins` | Cloned marketplaces, installed plugin versions, and per-plugin data, managed by `claude plugin` commands. Plugins [synced from your claude.ai account](/docs/en/plugins-reference#synced-plugins) d… |
|
v2.1.277AGENTS.md |
Documentation arrivedAnthropic's documentation has since written up AGENTS.md, on Explore the .claude directory.
the line in the docs| `AGENTS.md` | Project root, `.claude/`, or any directory | Project instructions you write for AI coding agents. Claude Code can [load it](/docs/en/memory#agents-md) on its own or alongside `CLAUDE.md`. | |
|
v2.1.277AGENTS.md |
Documentation arrivedAnthropic's documentation has since written up AGENTS.md, on Explore the .claude directory.
the line in the docs| `AGENTS.md` | Project root, `.claude/`, or any directory | Project instructions you write for AI coding agents. Claude Code can [load it](/docs/en/memory#agents-md) on its own or alongside `CLAUDE.md`. | |
|
v2.1.277AGENTS.md |
Documentation arrivedAnthropic's documentation has since written up AGENTS.md, on Explore the .claude directory.
the line in the docs| `AGENTS.md` | Project root, `.claude/`, or any directory | Project instructions you write for AI coding agents. Claude Code can [load it](/docs/en/memory#agents-md) on its own or alongside `CLAUDE.md`. | |
|
v2.1.277CLAUDE.md |
Documentation arrivedAnthropic's documentation has since written up CLAUDE.md, on Explore the .claude directory.
the line in the docs| `CLAUDE.local.md` | Project root | Your private preferences for this project, loaded alongside CLAUDE.md. Create it manually and add it to `.gitignore`. | |
|
v2.1.277CLAUDE.md |
Documentation arrivedAnthropic's documentation has since written up CLAUDE.md, on Explore the .claude directory.
the line in the docs| `CLAUDE.local.md` | Project root | Your private preferences for this project, loaded alongside CLAUDE.md. Create it manually and add it to `.gitignore`. | |
|
v2.1.247ctrl+x enter |
Documentation arrivedAnthropic's documentation has since written up ctrl+x enter, on Customize keyboard shortcuts.
the line in the docsClaude Code binds these default chords on the `ctrl+x` prefix: `ctrl+x ctrl+k`, `ctrl+x ctrl+e`, `ctrl+x enter`, `ctrl+x ctrl+a`, `ctrl+x ctrl+s`, and `ctrl+x tab` in `Chat`, `ctrl+x ctrl+b` in `Task`, and `ctrl+x b` in `DiffPanel`. The `c… |
|
v2.1.257chat:externalEditor |
Documentation arrivedAnthropic's documentation has since written up chat:externalEditor, on Customize keyboard shortcuts.
the line in the docs| `chat:externalEditor` | Ctrl+G, Ctrl+X Ctrl+E | Open in external editor. The [agent view dispatch input](/docs/en/agent-view#keyboard-shortcuts) follows this action's single-keystroke bindings too | |
|
v2.1.277chat:cancel |
Documentation arrivedAnthropic's documentation has since written up chat:cancel, on Customize keyboard shortcuts.
the line in the docs| `chat:cancel` | Escape | Cancel current input | |
|
v2.1.278Escape |
Documentation arrivedAnthropic's documentation has since written up Escape, on Customize keyboard shortcuts.
the line in the docs| `chat:cancel` | Escape | Cancel current input | |
|
v2.1.268Escape |
Documentation arrivedAnthropic's documentation has since written up Escape, on Customize keyboard shortcuts.
the line in the docs| `chat:cancel` | Escape | Cancel current input | |
|
v2.1.275chat:sendNow |
Documentation arrivedAnthropic's documentation has since written up chat:sendNow, on Interactive mode.
the line in the docsIn terminals that don't report extended keys, `Ctrl+Enter` arrives as plain `Enter` and queues the draft instead; `Ctrl+X Ctrl+S` works in any terminal. Both keys are bindings of the [`chat:sendNow` action](/docs/en/keybindings#chat-action… |
|
v2.1.274CLAUDE_CODE_DISABLE_BG_SHELL_PRESSURE_REAP |
Documentation arrivedAnthropic's documentation has since written up CLAUDE_CODE_DISABLE_BG_SHELL_PRESSURE_REAP, on Interactive mode.
the line in the docs* Set [`CLAUDE_CODE_DISABLE_BG_SHELL_PRESSURE_REAP`](/docs/en/env-vars) to `1` to turn off memory-pressure stops |
|
v2.1.277/usage |
Documentation arrivedAnthropic's documentation has since written up /usage, on user-management.
the line in the docs| Usage and cost reports | Available; see the [Usage and Cost API](https://platform.claude.com/docs/en/manage-claude/usage-cost-api) | Available through the [Claude Enterprise Analytics API](https://platform.claude.com/docs/en/manage-claud… |
|
v2.1.275memory_delete |
Documentation arrivedA small documentation edit on Fetch the first page (newest activities first) and capture its trailing cursor. touched a line naming memory_delete after this was published.
the line in the docsA `user_actor` activity does not always mean the user took the action. Processes that Anthropic runs on a user's behalf can currently appear as `user_actor` for the affected user rather than as `system_actor`, and this attribution may chan… |
|
v2.1.277claude-opus-5 |
Documentation arrivedAnthropic's documentation has since written up claude-opus-5, on skills-guide.
the line in the docs"model": "claude-opus-5", |
|
v2.1.274contentType |
Documentation arrivedAnthropic's documentation has since written up contentType, on skills-guide.
the line in the docs.contentType("text/markdown") |
|
v2.1.246contentType |
Documentation arrivedAnthropic's documentation has since written up contentType, on skills-guide.
the line in the docs.contentType("text/markdown") |
|
v2.1.275SKILL.md |
Documentation arrivedAnthropic's documentation has since written up SKILL.md, on skills-guide.
the line in the docs-F "files[]=@dcf_skill/SKILL.md;filename=dcf_skill/SKILL.md" |
|
v2.1.274position |
Documentation arrivedAnthropic's documentation has since written up position, on preserved-thinking.
the line in the docs* [Compaction at a token threshold](https://platform.claude.com/docs/en/build-with-claude/compaction-threshold) summarizes older turns into a compaction block when the context approaches a threshold you set, and the checked prefix restarts… |
|
v2.1.277headers |
Documentation arrivedAnthropic's documentation has since written up headers, on overview.
the line in the docs| **Beta** | Preview features used for gathering feedback and iterating on a less mature use case. Availability may be limited, including through sign-up requirements or waitlists, and may not be publicly announced. Features may change sig… |
|
v2.1.277headers |
Documentation arrivedAnthropic's documentation has since written up headers, on overview.
the line in the docs| **Beta** | Preview features used for gathering feedback and iterating on a less mature use case. Availability may be limited, including through sign-up requirements or waitlists, and may not be publicly announced. Features may change sig… |
|
v2.1.277surface |
Documentation arrivedA small documentation edit on List local sessions touched a line naming surface after this was published.
the line in the docsThe product the session ran in: `cowork` (Cowork in Claude Desktop on the user's machine), `claude_code` (Claude Code), `claude_science` (Claude Science), `claude_in_chrome` (the Claude in Chrome browser extension's built-in chat), or one … |
|
v2.1.277surface |
Documentation arrivedAnthropic's documentation has since written up surface, on Beta.
the line in the docsDeprecated: use `group.type` instead. The kind of rate-limit group this entry represents. `model_group` entries apply to a family of models (listed in `models`); other values apply to an API-surface category and have `models` set to `null`… |
|
v2.1.274sdk |
Documentation arrivedA small documentation edit on Log at info level touched a line naming sdk after this was published.
the line in the docsFor long-running agentic tasks, the TypeScript and Ruby tool runners support automatic [compaction](https://platform.claude.com/docs/en/build-with-claude/context-editing#client-side-compaction-sdk), which generates summaries when token usa… |
|
v2.1.274sdk |
Documentation arrivedA small documentation edit on Log at info level touched a line naming sdk after this was published.
the line in the docsFor long-running agentic tasks, the TypeScript and Ruby tool runners support automatic [compaction](https://platform.claude.com/docs/en/build-with-claude/context-editing#client-side-compaction-sdk), which generates summaries when token usa… |
|
v2.1.277headers |
Documentation arrivedA small documentation edit on computer-use-tool touched a line naming headers after this was published.
the line in the docsExisting `computer_20251124` integrations keep working on the models listed for it under [Earlier tool versions](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#earlier-tool-versions), and earlier tool versi… |
|
v2.1.277headers |
Documentation arrivedA small documentation edit on computer-use-tool touched a line naming headers after this was published.
the line in the docsExisting `computer_20251124` integrations keep working on the models listed for it under [Earlier tool versions](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#earlier-tool-versions), and earlier tool versi… |
|
v2.1.275/advisor |
Documentation arrivedA small documentation edit on optimizing-for-cost-and-intelligence touched a line naming /advisor after this was published.
the line in the docsIn agent loops the cache-read term is usually the largest of the five; if not, check that caching is engaged. When the [advisor tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/advisor-tool#usage-and-billing) or [compact… |
|
v2.1.277builtin |
Documentation arrivedAnthropic's documentation has since written up builtin, on Telemetry and egress.
the line in the docs| Web Fetch domain check in [Code](/docs/third-party/claude-desktop/code) sessions | The hostname of each page Claude Code fetches, sent to `api.anthropic.com` before the fetch. See [Web Fetch](/docs/third-party/claude-desktop/web-tools#we… |
|
v2.1.274--model |
Documentation arrivedAnthropic's documentation has since written up --model, on Model configuration.
the line in the docsThe plan-mode Opus phase uses the same context window as the `opus` model setting, and the execution phase uses the same window as `sonnet`. When `opus` and `sonnet` resolve to models that run with the [1M context window](#extended-context… |
|
v2.1.275SKILL.md |
Documentation arrivedA small documentation edit on Skills in Claude Desktop touched a line naming SKILL.md after this was published.
the line in the docs**Write the skill.** A skill is a folder named after the skill, holding a `SKILL.md` file. The file starts with YAML frontmatter carrying `name` and `description`, followed by the instructions as markdown. The folder name must match the `n… |
|
v2.1.257SKILL.md |
Documentation arrivedA small documentation edit on Skills in Claude Desktop touched a line naming SKILL.md after this was published.
the line in the docs**Write the skill.** A skill is a folder named after the skill, holding a `SKILL.md` file. The file starts with YAML frontmatter carrying `name` and `description`, followed by the instructions as markdown. The folder name must match the `n… |
|
v2.1.265/design |
Documentation arrivedA small documentation edit on Commands touched a line naming /design after this was published.
the line in the docs| `/design [brief]` | **[Skill](/docs/en/skills#bundled-skills).** Draft UI mockups, screen flows, landing pages, or posters as artboards on one canvas, published as a Design [artifact](/docs/en/artifacts#draft-a-design-canvas), for exampl… |
|
v2.1.265/design |
Documentation arrivedAnthropic's documentation has since written up /design, on Share session output as artifacts.
the line in the docsTo mock up a UI, a screen flow, a landing page, or a poster rather than build a page, run `/design` with a brief. Claude drafts the design as artboards on one canvas and publishes the canvas as a Design artifact. The brief names what you w… |
|
v2.1.265/design |
Documentation arrivedAnthropic's documentation has since written up /design, on Share session output as artifacts.
the line in the docsTo mock up a UI, a screen flow, a landing page, or a poster rather than build a page, run `/design` with a brief. Claude drafts the design as artboards on one canvas and publishes the canvas as a Design artifact. The brief names what you w… |
|
v2.1.265/design |
Documentation arrivedAnthropic's documentation has since written up /design, on Share session output as artifacts.
the line in the docsTo mock up a UI, a screen flow, a landing page, or a poster rather than build a page, run `/design` with a brief. Claude drafts the design as artboards on one canvas and publishes the canvas as a Design artifact. The brief names what you w… |
|
v2.1.265/design |
Documentation arrivedAnthropic's documentation has since written up /design, on Share session output as artifacts.
the line in the docsTo mock up a UI, a screen flow, a landing page, or a poster rather than build a page, run `/design` with a brief. Claude drafts the design as artboards on one canvas and publishes the canvas as a Design artifact. The brief names what you w… |
|
v2.1.251/design |
Documentation arrivedAnthropic's documentation has since written up /design, on Share session output as artifacts.
the line in the docsTo mock up a UI, a screen flow, a landing page, or a poster rather than build a page, run `/design` with a brief. Claude drafts the design as artboards on one canvas and publishes the canvas as a Design artifact. The brief names what you w… |
|
v2.1.275/status |
Documentation arrivedAnthropic's documentation has since written up /status, on Claude Code changelog.
the line in the docs* Added an `Auto mode server` row to `/status` showing whether this session's auto mode classifier runs on the server |
|
v2.1.271CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS |
Documentation arrivedA small documentation edit on Choose a permission mode touched a line naming CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS after this was published.
the line in the docsOn Enterprise plans and accounts that use the Claude API, on [Claude Platform on AWS](/docs/en/claude-platform-on-aws), Amazon Bedrock, Google Cloud's Agent Platform, and Microsoft Foundry, and whenever you point `ANTHROPIC_BASE_URL` at an… |
|
v2.1.275icon |
Documentation arrivedAnthropic's documentation has since written up icon, on Configure cloud environments.
the line in the docsShared environments appear in each member's [environment selector](#configure-your-environment) under an **Organization** heading, after the member's own environments under **Personal**, so a team can standardize on one configuration inste… |
|
v2.1.275icon |
Documentation arrivedAnthropic's documentation has since written up icon, on Configure cloud environments.
the line in the docsShared environments appear in each member's [environment selector](#configure-your-environment) under an **Organization** heading, after the member's own environments under **Personal**, so a team can standardize on one configuration inste… |
|
v2.1.274store.connect_timeout_seconds |
Documentation arrivedAnthropic's documentation has since written up store.connect_timeout_seconds, on Claude apps gateway deployment and operations.
the line in the docs| Log: `could not connect to Postgres at boot, attempt 1 of 3` | The database wasn't reachable yet when the gateway started, for example on a cold instance whose network is still coming up | If the gateway then finishes booting, no action … |
|
v2.1.275NODE_EXTRA_CA_CERTS |
Documentation arrivedAnthropic's documentation has since written up NODE_EXTRA_CA_CERTS, on Claude apps gateway deployment and operations.
the line in the docs| CLI `/login`: "Could not verify the gateway's TLS certificate" or `SELF_SIGNED_CERT_IN_CHAIN` | Gateway's TLS chain is signed by a private CA not in the CLI host's trust store | Claude Code reads the OS trust store by default on the nati… |