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 |
|---|---|---|
v2.1.246/hooks |
Documentation arrivedAnthropic's documentation has since written up /hooks, on Configure auto mode.
the line in the docsTwo other places on screen that report denials leave out the command or URL: the notice near the input box, such as `bash denied by auto mode · [Data Exfiltration] · /permissions`, gives the tool and the reason, and the **Recently denied**… |
|
v2.1.246/hooks |
Documentation arrivedAnthropic's documentation has since written up /hooks, on Configure auto mode.
the line in the docsTwo other places on screen that report denials leave out the command or URL: the notice near the input box, such as `bash denied by auto mode · [Data Exfiltration] · /permissions`, gives the tool and the reason, and the **Recently denied**… |
|
v2.1.242/hooks |
Documentation arrivedAnthropic's documentation has since written up /hooks, on Configure auto mode.
the line in the docsTwo other places on screen that report denials leave out the command or URL: the notice near the input box, such as `bash denied by auto mode · [Data Exfiltration] · /permissions`, gives the tool and the reason, and the **Recently denied**… |
|
v2.1.242/hooks |
Documentation arrivedAnthropic's documentation has since written up /hooks, on Configure auto mode.
the line in the docsTwo other places on screen that report denials leave out the command or URL: the notice near the input box, such as `bash denied by auto mode · [Data Exfiltration] · /permissions`, gives the tool and the reason, and the **Recently denied**… |
|
v2.1.248favicon |
Documentation arrivedAnthropic's documentation has since written up favicon, on Agent SDK reference - TypeScript.
the line in the docsPublishes a local `.html` or `.md` file as a hosted artifact page, or lists the user's published artifacts. Omit `action` or pass `"publish"` to publish `file_path`, which is required for the publish action along with `favicon`, one or two… |
|
v2.1.248favicon |
Documentation arrivedAnthropic's documentation has since written up favicon, on Agent SDK reference - TypeScript.
the line in the docsPublishes a local `.html` or `.md` file as a hosted artifact page, or lists the user's published artifacts. Omit `action` or pass `"publish"` to publish `file_path`, which is required for the publish action along with `favicon`, one or two… |
|
v2.1.257request_id |
Documentation arrivedAnthropic's documentation has since written up request_id, on Agent SDK reference - TypeScript.
the line in the docsThe control-response wrapper for a successful `initialize` also carries a `pending_permission_requests` array. The field is on the response wrapper itself, not in the `SDKControlInitializeResponse` payload above. Each entry is a complete `… |
|
v2.1.233CLAUDE_CODE_ENABLE_TASKS |
Documentation arrivedAnthropic's documentation has since written up CLAUDE_CODE_ENABLE_TASKS, on Agent SDK reference - Python.
the line in the docsWherever the tools are available, Claude Code provides the four Task tools, or `TodoWrite` instead when you set `CLAUDE_CODE_ENABLE_TASKS=0`. |
|
v2.1.259--bare |
Documentation arrivedAnthropic's documentation has since written up --bare, on Modifying system prompts.
the line in the docsIf you start Claude Code in [bare mode](/docs/en/headless#start-faster-with-bare-mode) by passing `--bare` through `extraArgs` or setting `CLAUDE_CODE_SIMPLE=1`, recording stays off unless you set `snapshot: true` on the object form of `sy… |
|
v2.1.242--bare |
Documentation arrivedAnthropic's documentation has since written up --bare, on Modifying system prompts.
the line in the docsIf you start Claude Code in [bare mode](/docs/en/headless#start-faster-with-bare-mode) by passing `--bare` through `extraArgs` or setting `CLAUDE_CODE_SIMPLE=1`, recording stays off unless you set `snapshot: true` on the object form of `sy… |
|
v2.1.232CLAUDE_CODE_SIMPLE |
Documentation arrivedAnthropic's documentation has since written up CLAUDE_CODE_SIMPLE, on Modifying system prompts.
the line in the docsIf you start Claude Code in [bare mode](/docs/en/headless#start-faster-with-bare-mode) by passing `--bare` through `extraArgs` or setting `CLAUDE_CODE_SIMPLE=1`, recording stays off unless you set `snapshot: true` on the object form of `sy… |
|
v2.1.257watch |
Documentation arrivedA small documentation edit on Work with Claude Tag touched a line naming watch after this was published.
the line in the docsThe usage page doesn't count usage that a credit covers, so that usage shows as \$0.00 there. While the credit covers your pilot, watch the **List price** column of the **Spend by channel** table at [`claude.ai/analytics/claude-tag`](https… |
|
v2.1.236watch |
Documentation arrivedA small documentation edit on Work with Claude Tag touched a line naming watch after this was published.
the line in the docsThe usage page doesn't count usage that a credit covers, so that usage shows as \$0.00 there. While the credit covers your pilot, watch the **List price** column of the **Spend by channel** table at [`claude.ai/analytics/claude-tag`](https… |
|
v2.1.260/memory |
Documentation arrivedA small documentation edit on Data lifecycle and deletion touched a line naming /memory after this was published.
the line in the docs* **Delete a scope's memory files**: select **View memory files** in the scope's options menu, choose a file, then select **Delete**. You can also tell Claude in the channel to forget an entry. See [Check and correct what Claude Tag rememb… |
|
v2.1.260Select |
Documentation arrivedA small documentation edit on Manage workspaces and versions touched a line naming Select after this was published.
the line in the docs| "These settings aren’t applied while Claude Tag setup is incomplete for this workspace or channel." | Select the **Resume** *workspace* **setup** button beside the notice and finish that workspace's setup. On a channel's entry, the butto… |
|
v2.1.246pages |
Documentation arrivedAnthropic's documentation has since written up pages, on Restrict where Claude Tag operates.
the line in the docsSpend trends live at [`claude.ai/analytics/claude-tag`](https://claude.ai/analytics/claude-tag), the Claude Tag section of the Analytics dashboard, refreshed once a day. It shows total and projected month-end spend for the period you pick,… |
|
v2.1.265auto-mode |
Documentation arrivedAnthropic's documentation has since written up auto-mode, on Customize Claude Tag.
the line in the docs| Auto mode allow rules | Actions pre-approved in a scope's sessions that Claude's permission checker would otherwise flag or stop | [Auto mode allow rules](#auto-mode-allow-rules) | |
|
v2.1.260Select |
Documentation arrivedAnthropic's documentation has since written up Select, on Configure per-channel access.
the line in the docsRepository grants and plugins from every bound bundle are combined as a union; a channel gets every repo and plugin from any bundle in its chain. To see what applies to a channel, select its scope on the **Slack** tab. The scope's panel li… |
|
v2.1.260copied |
Documentation arrivedAnthropic's documentation has since written up copied, on Configure per-channel access.
the line in the docs2. Pick the channel in the **Channel** field. Type a name to search public channels, or paste a channel ID or channel link copied from Slack. Private channels don't appear in the search results, so for a private channel, paste its ID from … |
|
v2.1.257/review |
Documentation arrivedAnthropic's documentation has since written up /review, on Extend Claude with skills.
the line in the docs| Plugin `skills/` subdirectory | Frontmatter `name` or the directory name, namespaced by plugin | `my-plugin/skills/review/SKILL.md` → `/my-plugin:review`, or `/my-plugin:fancy` with `name: fancy` | |
|
v2.1.260visibility |
Documentation arrivedAnthropic's documentation has since written up visibility, on Extend Claude with skills.
the line in the docs* **Bundled skill**: set [`disableBundledSkills`](#bundled-skills) to `true` to turn off bundled skills, or set one skill to `"off"` in [`skillOverrides`](#override-skill-visibility-from-settings) to hide it. |
|
v2.1.246claude --resume |
Documentation arrivedAnthropic's documentation has since written up claude --resume, on Run prompts on a schedule.
the line in the docs* Starting a fresh conversation clears all session-scoped tasks. When you resume a session with `claude --resume` or `claude --continue`, Claude Code restores the tasks scheduled with `CronCreate`, except recurring tasks that have [expired… |
|
v2.1.239claude --resume |
Documentation arrivedAnthropic's documentation has since written up claude --resume, on Run prompts on a schedule.
the line in the docs* Starting a fresh conversation clears all session-scoped tasks. When you resume a session with `claude --resume` or `claude --continue`, Claude Code restores the tasks scheduled with `CronCreate`, except recurring tasks that have [expired… |
|
v2.1.232claude --resume |
Documentation arrivedAnthropic's documentation has since written up claude --resume, on Run prompts on a schedule.
the line in the docs* Starting a fresh conversation clears all session-scoped tasks. When you resume a session with `claude --resume` or `claude --continue`, Claude Code restores the tasks scheduled with `CronCreate`, except recurring tasks that have [expired… |
|
v2.1.248--system-prompt |
Documentation arrivedAnthropic's documentation has since written up --system-prompt, on How Claude Code uses prompt caching.
the line in the docs* In sessions signed in with a claude.ai or Console account, and other sessions that [fetch feature flags](/docs/en/env-vars#features-that-need-feature-flag-fetching), the resumed conversation keeps the system prompt it started with by def… |
|
v2.1.242--system-prompt |
Documentation arrivedAnthropic's documentation has since written up --system-prompt, on How Claude Code uses prompt caching.
the line in the docs* In sessions signed in with a claude.ai or Console account, and other sessions that [fetch feature flags](/docs/en/env-vars#features-that-need-feature-flag-fetching), the resumed conversation keeps the system prompt it started with by def… |
|
v2.1.242--append-system-prompt |
Documentation arrivedAnthropic's documentation has since written up --append-system-prompt, on How Claude Code uses prompt caching.
the line in the docsThe system prompt is the one layer a resume can treat two ways. It would change after a [Claude Code upgrade](#upgrading-claude-code) or with different [`--append-system-prompt`](/docs/en/cli-reference#system-prompt-flags) text on the resu… |
|
v2.1.234--append-system-prompt |
Documentation arrivedAnthropic's documentation has since written up --append-system-prompt, on How Claude Code uses prompt caching.
the line in the docsThe system prompt is the one layer a resume can treat two ways. It would change after a [Claude Code upgrade](#upgrading-claude-code) or with different [`--append-system-prompt`](/docs/en/cli-reference#system-prompt-flags) text on the resu… |
|
v2.1.248DISABLE_AUTOUPDATER |
Documentation arrivedAnthropic's documentation has since written up DISABLE_AUTOUPDATER, on How Claude Code uses prompt caching.
the line in the docsA new Claude Code version typically updates the system prompt or tool definitions, so the first conversation you start after an upgrade builds its cache from the top. [Auto-update](/docs/en/setup#auto-updates) downloads new versions in the… |
|
v2.1.260/context |
Documentation arrivedAnthropic's documentation has since written up /context, on How Claude Code uses prompt caching.
the line in the docs[Compaction](/docs/en/context-window#what-survives-compaction) replaces your message history with a summary. By design, this invalidates the conversation layer, since the next request has a new, shorter history that doesn't share a prefix … |
|
v2.1.252/context |
Documentation arrivedAnthropic's documentation has since written up /context, on How Claude Code uses prompt caching.
the line in the docs[Compaction](/docs/en/context-window#what-survives-compaction) replaces your message history with a summary. By design, this invalidates the conversation layer, since the next request has a new, shorter history that doesn't share a prefix … |
|
v2.1.248/context |
Documentation arrivedAnthropic's documentation has since written up /context, on How Claude Code uses prompt caching.
the line in the docs[Compaction](/docs/en/context-window#what-survives-compaction) replaces your message history with a summary. By design, this invalidates the conversation layer, since the next request has a new, shorter history that doesn't share a prefix … |
|
v2.1.248/context |
Documentation arrivedAnthropic's documentation has since written up /context, on How Claude Code uses prompt caching.
the line in the docs[Compaction](/docs/en/context-window#what-survives-compaction) replaces your message history with a summary. By design, this invalidates the conversation layer, since the next request has a new, shorter history that doesn't share a prefix … |
|
v2.1.232/context |
Documentation arrivedAnthropic's documentation has since written up /context, on How Claude Code uses prompt caching.
the line in the docs[Compaction](/docs/en/context-window#what-survives-compaction) replaces your message history with a summary. By design, this invalidates the conversation layer, since the next request has a new, shorter history that doesn't share a prefix … |
|
v2.1.232/context |
Documentation arrivedAnthropic's documentation has since written up /context, on How Claude Code uses prompt caching.
the line in the docs[Compaction](/docs/en/context-window#what-survives-compaction) replaces your message history with a summary. By design, this invalidates the conversation layer, since the next request has a new, shorter history that doesn't share a prefix … |
|
v2.1.232/context |
Documentation arrivedAnthropic's documentation has since written up /context, on How Claude Code uses prompt caching.
the line in the docs[Compaction](/docs/en/context-window#what-survives-compaction) replaces your message history with a summary. By design, this invalidates the conversation layer, since the next request has a new, shorter history that doesn't share a prefix … |
|
v2.1.261/status |
Documentation arrivedA small documentation edit on Recommend your plugin from your CLI touched a line naming /status after this was published.
the line in the docs* `CLAUDE_CODE_CHILD_SESSION`: set only in subprocesses Claude Code itself spawns, such as tool calls, hook commands, and [status line](/docs/en/statusline) commands, so the tag does not normally reach a human terminal. A long-lived proces… |
|
v2.1.260/status |
Documentation arrivedA small documentation edit on Recommend your plugin from your CLI touched a line naming /status after this was published.
the line in the docs* `CLAUDE_CODE_CHILD_SESSION`: set only in subprocesses Claude Code itself spawns, such as tool calls, hook commands, and [status line](/docs/en/statusline) commands, so the tag does not normally reach a human terminal. A long-lived proces… |
|
v2.1.259/status |
Documentation arrivedA small documentation edit on Recommend your plugin from your CLI touched a line naming /status after this was published.
the line in the docs* `CLAUDE_CODE_CHILD_SESSION`: set only in subprocesses Claude Code itself spawns, such as tool calls, hook commands, and [status line](/docs/en/statusline) commands, so the tag does not normally reach a human terminal. A long-lived proces… |
|
v2.1.257/status |
Documentation arrivedA small documentation edit on Recommend your plugin from your CLI touched a line naming /status after this was published.
the line in the docs* `CLAUDE_CODE_CHILD_SESSION`: set only in subprocesses Claude Code itself spawns, such as tool calls, hook commands, and [status line](/docs/en/statusline) commands, so the tag does not normally reach a human terminal. A long-lived proces… |
|
v2.1.248/status |
Documentation arrivedA small documentation edit on Recommend your plugin from your CLI touched a line naming /status after this was published.
the line in the docs* `CLAUDE_CODE_CHILD_SESSION`: set only in subprocesses Claude Code itself spawns, such as tool calls, hook commands, and [status line](/docs/en/statusline) commands, so the tag does not normally reach a human terminal. A long-lived proces… |
|
v2.1.248/status |
Documentation arrivedA small documentation edit on Recommend your plugin from your CLI touched a line naming /status after this was published.
the line in the docs* `CLAUDE_CODE_CHILD_SESSION`: set only in subprocesses Claude Code itself spawns, such as tool calls, hook commands, and [status line](/docs/en/statusline) commands, so the tag does not normally reach a human terminal. A long-lived proces… |
|
v2.1.246/status |
Documentation arrivedA small documentation edit on Recommend your plugin from your CLI touched a line naming /status after this was published.
the line in the docs* `CLAUDE_CODE_CHILD_SESSION`: set only in subprocesses Claude Code itself spawns, such as tool calls, hook commands, and [status line](/docs/en/statusline) commands, so the tag does not normally reach a human terminal. A long-lived proces… |
|
v2.1.243/status |
Documentation arrivedA small documentation edit on Recommend your plugin from your CLI touched a line naming /status after this was published.
the line in the docs* `CLAUDE_CODE_CHILD_SESSION`: set only in subprocesses Claude Code itself spawns, such as tool calls, hook commands, and [status line](/docs/en/statusline) commands, so the tag does not normally reach a human terminal. A long-lived proces… |
|
v2.1.232/status |
Documentation arrivedA small documentation edit on Recommend your plugin from your CLI touched a line naming /status after this was published.
the line in the docs* `CLAUDE_CODE_CHILD_SESSION`: set only in subprocesses Claude Code itself spawns, such as tool calls, hook commands, and [status line](/docs/en/statusline) commands, so the tag does not normally reach a human terminal. A long-lived proces… |
|
v2.1.231/status |
Documentation arrivedA small documentation edit on Recommend your plugin from your CLI touched a line naming /status after this was published.
the line in the docs* `CLAUDE_CODE_CHILD_SESSION`: set only in subprocesses Claude Code itself spawns, such as tool calls, hook commands, and [status line](/docs/en/statusline) commands, so the tag does not normally reach a human terminal. A long-lived proces… |
|
v2.1.229/status |
Documentation arrivedA small documentation edit on Recommend your plugin from your CLI touched a line naming /status after this was published.
the line in the docs* `CLAUDE_CODE_CHILD_SESSION`: set only in subprocesses Claude Code itself spawns, such as tool calls, hook commands, and [status line](/docs/en/statusline) commands, so the tag does not normally reach a human terminal. A long-lived proces… |
|
v2.1.260/statusline |
Documentation arrivedA small documentation edit on Recommend your plugin from your CLI touched a line naming /statusline after this was published.
the line in the docs* `CLAUDE_CODE_CHILD_SESSION`: set only in subprocesses Claude Code itself spawns, such as tool calls, hook commands, and [status line](/docs/en/statusline) commands, so the tag does not normally reach a human terminal. A long-lived proces… |
|
v2.1.229/statusline |
Documentation arrivedA small documentation edit on Recommend your plugin from your CLI touched a line naming /statusline after this was published.
the line in the docs* `CLAUDE_CODE_CHILD_SESSION`: set only in subprocesses Claude Code itself spawns, such as tool calls, hook commands, and [status line](/docs/en/statusline) commands, so the tag does not normally reach a human terminal. A long-lived proces… |
|
v2.1.248CLAUDE_CODE_MAX_RETRIES |
Documentation arrivedAnthropic's documentation has since written up CLAUDE_CODE_MAX_RETRIES, on Monitoring.
the line in the docsThe `attempt` attribute on the event records the total number of attempts. `CLAUDE_CODE_MAX_RETRIES` defaults to 10 and is capped at 15. On v2.1.199 or later, you can set `CLAUDE_CODE_RETRY_WATCHDOG` to raise the default and remove the cap. |