Capture
One read of Claude Code CLI
8 pages moved out of 186 read.
mcp Changed · +60 / -0 lines
### Add a server from setup instructions written for another client #### From a URL #### From an `npx`, `uvx`, or binary command #### From an `mcpServers` JSON block
from line 149
The `type: "ws"` entry accepts the same `url`, `headers`, `headersHelper`, `timeout`, and `alwaysLoad` fields as `http`. Authentication is header-only, so pass a static token in `headers` or generate one at connect time with [`headersHelper`](#use-dynamic-headers-for-custom-authentication). The `claude mcp add --transport` flag doesn't accept `ws`. +### Add a server from setup instructions written for another client + +MCP servers aren't specific to Claude Code, so a server's setup instructions may be written for Claude Desktop, Cursor, or another MCP client and give no `claude mcp add` command. To add the server anyway, look in those instructions for one of these three things: + +* **A URL** such as `https://mcp.example.com/mcp`: the server is remote. +* **A launch command** such as `npx -y @example/mcp-server`: the server runs on your machine. +* **An `mcpServers` JSON block**: configuration written for another client's settings file. + +Each is one of the inputs the four options in [Installing MCP servers](#installing-mcp-servers) take. Find the shape you have below to turn it into the command Claude Code accepts. Each command writes to [local scope](#local-scope) unless you add `--scope project` or `--scope user`. + +#### From a URL + +A URL means the server is remote. For an `https://` endpoint, add it with `--transport http`, or with `--transport sse` when the instructions say the endpoint uses SSE. For a `wss://` endpoint, use [Option 4](#option-4-add-a-remote-websocket-server) instead, since `--transport` doesn't accept `ws`: + +```bash theme={null} +claude mcp add --transport http example https://mcp.example.com/mcp +``` + +If the instructions also give an API key or token header, pass it with `--header` as shown in [Option 1](#option-1-add-a-remote-http-server). + +#### From an `npx`, `uvx`, or binary command + +A launch command means the server runs as a local stdio process. Put the whole command after `--`, so Claude Code passes flags such as `-y` to the command that starts the server instead of reading them as its own options. Pass any environment variables the instructions ask for with `--env`, after the server name and before `--`: + +```bash theme={null} +claude mcp add example --env API_KEY=your-key -- npx -y @example/mcp-server +``` + +[Option 3](#option-3-add-a-local-stdio-server) covers the `--` separator in full. + +#### From an `mcpServers` JSON block + +An `mcpServers` block written for another MCP client, such as Claude Desktop, uses the wrapper key and entry shape Claude Code reads. Pass `claude mcp add-json` the object inside `mcpServers`, not the wrapper. Two entries need a repair first: + +* **A `url` with no `type`**: add `"type": "http"`, `"type": "sse"`, or `"type": "ws"` to match the endpoint. Claude Code reads an entry with no `type` as a stdio server, so a `url` entry without a `type` fails. +* **A key with characters other than letters, numbers, hyphens, and underscores**: pick a server name that uses only those characters. Otherwise the key is the server name. + +For example, this block: + +```json theme={null} +{ + "mcpServers": { + "example": { + "command": "npx", + "args": ["-y", "@example/mcp-server"] + } + } +} +``` + +becomes this command: + +```bash theme={null} +claude mcp add-json example '{"command":"npx","args":["-y","@example/mcp-server"]}' +``` + +[Add MCP servers from JSON configuration](#add-mcp-servers-from-json-configuration) covers shell escaping and the `--scope` flag for `add-json`. To share the server with your team instead, add `--scope project`, or add the entry under `mcpServers` in `.mcp.json` at your project root and commit it. [Project scope](#project-scope) covers how Claude Code loads and approves that file. + +Each `claude mcp add` and `claude mcp add-json` command prints an `Added ...` line. To check that Claude Code connected, run `claude mcp get <name>`; [Server status](#server-status) covers the statuses it shows and the approval step for `.mcp.json` servers. + ### Managing your servers Once configured, you can manage your MCP servers with these commands:
statusline Changed · +1 / -1 lines
from line 1068
* Terminal.app does not support clickable links -* If link text appears but isn't clickable, Claude Code may not have detected hyperlink support in your terminal. This commonly affects Windows Terminal and other emulators not in the auto-detection list. Set the `FORCE_HYPERLINK` environment variable to override detection before launching Claude Code: +* If link text appears but isn't clickable, Claude Code may not have detected hyperlink support in your terminal. Set the `FORCE_HYPERLINK` environment variable to override detection before launching Claude Code: ```bash theme={null} FORCE_HYPERLINK=1 claude
interactive-mode Changed · +97 / -0 lines
## Check spelling as you type ### Prerequisites ### Turn spell checking on or off ### What Claude Code underlines ### When Claude Code underlines nothing
from line 380
To turn the feature off, set [`emojiCompletionEnabled`](/docs/en/settings#available-settings) to `false` in `settings.json`. This disables both the suggestion popup and the inline replacement. +## Check spelling as you type + +Claude Code can underline misspelled words in the prompt input while you type. It checks only the text in the input box, never Claude's replies or your files. It also checks nothing while the input box is in [shell mode](#shell-mode-with-prefix), `Ctrl+R` history search, or [voice dictation](/docs/en/voice-dictation). + +Spell checking is off by default, and Claude Code checks nothing in [screen reader mode](/docs/en/accessibility). Requires Claude Code v2.1.235 or later. + +### Prerequisites + +* Install [aspell](https://github.com/GNUAspell/aspell), [hunspell](https://github.com/hunspell/hunspell), or [ispell](https://en.wikipedia.org/wiki/Ispell) and make sure it's on your `PATH`. Claude Code runs the first of the three it finds, in that order, on every platform, including a `.cmd` shim a package manager installs on Windows. +* To check that the program is on your `PATH`, run `aspell --version`, `hunspell --version`, or `ispell -v` in your terminal. A "command not found" error means it isn't on your `PATH` yet. + +### Turn spell checking on or off + +Claude Code reads the [`spellcheck`](/docs/en/settings#available-settings) setting from three places, and ignores it in a project's `.claude/settings.json` and `.claude/settings.local.json`. Turn it on from whichever one you use: + +<Tabs> + <Tab title="User settings"> + Add `spellcheck` to `~/.claude/settings.json`. It applies in every project you open, like the rest of your [user settings](/docs/en/settings#settings-files): + + ```json theme={null} + { + "spellcheck": { "enabled": true } + } + ``` + </Tab> + + <Tab title="Command line"> + Save `spellcheck` in a JSON file, such as `spellcheck.json`: + + ```json theme={null} + { + "spellcheck": { "enabled": true } + } + ``` + + Then pass the file to `--settings`. It applies to that session only: + + ```bash theme={null} + claude --settings spellcheck.json + ``` + </Tab> + + <Tab title="Managed settings"> + Add `spellcheck` to one of your organization's [managed settings sources](/docs/en/permissions#managed-settings). It applies to every user who receives those settings, and they can't turn it off: + + ```json theme={null} + { + "spellcheck": { "enabled": true } + } + ``` + </Tab> +</Tabs> + +To check that spell checking is on, type a misspelled word and a space. Claude Code underlines the word. If it doesn't, see [When Claude Code underlines nothing](#when-claude-code-underlines-nothing). To turn spell checking off again, set `enabled` to `false` in the same place, or remove `spellcheck`. + +To choose which of the three programs Claude Code runs, which dictionary it uses, or the underline color, add any of these fields next to `enabled`, in the same place: + +* `checker`: `aspell`, `hunspell`, or `ispell`. Claude Code doesn't fall back from a checker you name, and treats any other value as `auto`. +* `language`: a dictionary name in your checker's form, such as `en_GB`. Claude Code ignores any value that isn't a plain dictionary name, such as a path or a name with spaces, and the checker uses its default dictionary. +* `color`: a color name such as `yellow`, or a `#rrggbb`, `#rgb`, `rgb(r,g,b)`, `ansi256(n)`, or `ansi:<name>` value. Claude Code uses your theme's error color by default and for any value it doesn't recognize. + +For example, this `spellcheck` setting runs hunspell with its `en_GB` dictionary and underlines words in yellow. It works the same in `~/.claude/settings.json`, in the file you pass to `--settings`, and in managed settings: + +```json theme={null} +{ + "spellcheck": { + "enabled": true, + "checker": "hunspell", + "language": "en_GB", + "color": "yellow" + } +} +``` + +If more than one of the three places has a `spellcheck` setting, Claude Code uses only one of them: managed settings first, then `--settings`, then user settings. It doesn't combine fields from two places. For example, when `--settings` sets `spellcheck`, a `language` in your user settings has no effect. + +### What Claude Code underlines + +Shortly after you pause typing, Claude Code underlines the words the dictionary doesn't know. It leaves the word you're still typing alone until you move past it, and it never changes your text. It also skips text that looks like code: + +* Commands such as `/help`, `@` mentions, URLs, file paths, and flags such as `--verbose` +* Words with digits, underscores, or a capital letter after the first, and text in backticks + +Claude Code also skips Chinese, Japanese, Korean, Thai, Lao, Khmer, and Myanmar text. + +Claude Code has no word list of its own: a word is misspelled when your checker says so. To stop Claude Code from underlining a word, add the word to your checker's personal dictionary, following the checker's own documentation. Claude Code picks up the new word after you restart it. + +### When Claude Code underlines nothing + +Claude Code underlines nothing when it can't keep a checker running: + +* No checker is installed, or the one you named in `checker` is missing +* The checker fails twice in a row, at startup or later in the session. Claude Code restarts it after the first failure and stops checking after the second, until you restart Claude Code +* The checker takes more than 15 seconds to answer, three times. Each time, Claude Code leaves the words it was waiting on unmarked; after the third, it stops checking until you restart Claude Code + +To find out which of these happened, start `claude --debug` with spell checking on and type a word. Then look for the `[spellcheck]` lines in the debug log at `~/.claude/debug/<session-id>.txt`. One line names the program Claude Code started, or lists the ones it looked for and didn't find. Later lines say why it stopped. A missing-dictionary error there means the checker has no dictionary for your `language` value, or no default one when `language` is unset. Install one, or set `language` to a dictionary you have. + ## Side questions with /btw Use `/btw` to ask a question about your current work without adding to the conversation history.
settings Changed · +2 / -1 lines
This page is larger than the 256 KiB this site keeps, so one side of the diff below stops where the stored text does.
from line 179
### Invalid entries in managed settings -Managed settings parse tolerantly. When a managed configuration contains an entry that fails schema validation, Claude Code strips that entry, records a warning, and enforces every remaining valid policy. A single typo cannot disable the rest of your organization's policy. Run [`/doctor`](/docs/en/debug-your-config#check-resolved-settings) to list stripped entries with their source file and field. +Managed settings parse tolerantly. When a managed configuration contains an entry that fails schema validation, Claude Code strips that entry, records a warning, and enforces every remaining valid policy. A single typo cannot disable the rest of your organization's policy. Run [`/doctor`](/docs/en/commands#all-commands) to list stripped entries with their source file and field. This behavior is consistent across all three delivery mechanisms: [server-managed settings](/docs/en/server-managed-settings), plist and registry policies deployed through MDM, and `managed-settings.json` files. Requires Claude Code v2.1.169 or later.
from line 323
| `skillListingMaxDescChars` | **Default**: `1536`. Per-skill character cap on the combined `description` and `when_to_use` text in the [skill listing](/docs/en/skills#skill-descriptions-are-cut-short) Claude sees each turn. Text longer than this is truncated. Raise to keep long descriptions intact at the cost of more context per turn; lower to fit more skills under [`skillListingBudgetFraction`](#available-settings) | `2048` | | `skillOverrides` | Per-skill visibility overrides keyed by skill name. Value is `"on"`, `"name-only"`, `"user-invocable-only"`, or `"off"`. Lets you hide or collapse a skill without editing its SKILL.md. Does not apply to plugin skills, which are managed through `/plugin`. The `/skills` menu writes these to `.claude/settings.local.json`. See [Override skill visibility from settings](/docs/en/skills#override-skill-visibility-from-settings) | `{"legacy-context": "name-only", "deploy": "off"}` | | `skipWebFetchPreflight` | Skip the [WebFetch domain safety check](/docs/en/data-usage#webfetch-domain-safety-check) that sends each requested hostname to `api.anthropic.com` before fetching. Set to `true` in environments that block traffic to Anthropic, such as Amazon Bedrock, Google Cloud's Agent Platform, or Microsoft Foundry deployments with restrictive egress. When skipped, WebFetch attempts any URL without consulting the blocklist | `true` | +| `spellcheck` | Underline misspelled words in the prompt input as you type, using a spell checker you install. Read from user settings, the `--settings` flag, and managed settings only. See [Check spelling as you type](/docs/en/interactive-mode#check-spelling-as-you-type). Requires Claude Code v2.1.235 or later | `{"enabled": true, "language": "en_GB"}` | | `spinnerTipsEnabled` | **Default**: `true`. Show tips in the spinner while Claude is working. Set to `false` to disable tips | `false` | | `spinnerTipsOverride` | Override spinner tips with custom strings. `tips`: array of tip strings. `excludeDefault`: if `true`, only show custom tips; if `false` or absent, custom tips are merged with built-in tips | `{ "excludeDefault": true, "tips": ["Use our internal tool X"] }` | | `spinnerVerbs` | Customize the action verbs shown while a turn is in progress. Set `mode` to `"replace"` to use only your verbs, or `"append"` to add them to the defaults | `{"mode": "append", "verbs": ["Pondering", "Crafting"]}` |
from line 436
| `credentials.envVars[].injectHosts` | Hosts where the sandbox proxy substitutes the real value of a `mask` entry. The proxy injects only on connections `network.allowedDomains` admits, so each destination must also pass that list. When unset, the proxy substitutes the value on requests to every host in `network.allowedDomains`. Write an IPv6 destination as the bare canonical compressed address, such as `"::1"`, not the bracketed form. See [IPv6 destinations in `injectHosts`](/docs/en/sandboxing#ipv6-destinations-in-injecthosts) for what each list matches. Accepted but ignored when `mode` is `deny`. Requires Claude Code v2.1.199 or later. | `["api.github.com"]` | | `credentials.allowPlaintextInject` | Allow `mask` substitution on plain HTTP requests as well as TLS-terminated HTTPS. On plain HTTP the upstream identity is unverified and the credential travels in cleartext, so leave this off outside trusted test networks. Only honored from user, managed, or CLI `--settings` settings, not from `.claude/settings.json` or `.claude/settings.local.json`. Default: false. Requires Claude Code v2.1.199 or later. | `true` | | `credentials.awsPairs` | Groups of masked environment variables that form one AWS credential for [SigV4 re-signing](/docs/en/sandboxing#re-sign-aws-requests), for non-standard variable names; Claude Code links the conventional `AWS_ACCESS_KEY_ID`, `AWS_SECRET_ACCESS_KEY`, and `AWS_SESSION_TOKEN` trio automatically when those variables are masked whole-value. Each entry names the `credentials.envVars` entry holding each part in `accessKeyIdVar`, `secretAccessKeyVar`, and optionally `sessionTokenVar`. Each named variable must be a whole-value `mask` entry, without `extract` or `decode`, and can fill only one slot across all pairs. Only honored from user, managed, or CLI `--settings` settings. Requires Claude Code v2.1.224 or later. | `[{ "accessKeyIdVar": "MY_KEY_ID", "secretAccessKeyVar": "MY_SECRET_KEY" }]` | -| `credentials.sigv4` | Policies for AWS request forms the sandbox proxy [can't re-sign](/docs/en/sandboxing#re-sign-aws-requests): `streaming` for aws-chunked streaming uploads, `presigned` for presigned URLs, and `sigv4a` for SigV4A asymmetric signatures. Each accepts `deny`, the default, which fails the request at the proxy, or `passthrough`, which forwards the request with its signature computed from the masked placeholder, so AWS rejects it. Applies only to requests signed with a masked pair's placeholder access key ID. Only honored from user, managed, or CLI `--settings` settings. Requires Claude Code v2.1.224 or later. | `{ "streaming": "passthrough" }` | -| `network.allowUnixSockets` | (macOS only) Unix socket paths accessible in sandbox. Ignored on Linux and WSL2, where the seccomp filter cannot inspect socket paths; use `allowAllUnixSockets` instead. +| `credentials.sigv4` | Policies for AWS request forms the sandbox proxy [can't re-sign](/docs/en/sandboxing#re-sign-aws-requests): `streaming` for aws-chunked streaming uploads, `presigned` for presigned URLs, and `sigv4a` for SigV4A asymmetric signatures. Each accepts `deny`, the default, which fails the request at the proxy, or
errors Changed · +1 / -1 lines
from line 1943
**What to do:** -* Usually nothing: the message lists the subagents the session does have, and Claude retries with one of them +* Usually nothing: the message lists the subagents the session does have, so Claude can retry with one of them * If Claude keeps failing, add `general-purpose` to the `tools: Agent(...)` allowlist, or unset `CLAUDE_AGENT_SDK_DISABLE_BUILTIN_AGENTS` Before v2.1.235, the same call failed with `Agent type 'general-purpose' not found`.
env-vars Changed · +1 / -1 lines
This page is larger than the 256 KiB this site keeps, so one side of the diff below stops where the stored text does.
from line 184
| `CLAUDECODE` | Set to `1` in subprocesses Claude Code spawns (Bash and PowerShell tools, tmux sessions, [hook](/docs/en/hooks) commands, [status line](/docs/en/statusline) commands, stdio [MCP server](/docs/en/mcp) subprocesses). IDE extensions also set this in their integrated terminals. Use to detect when a script is running inside a subprocess spawned by Claude Code. To check whether the current process was spawned directly by a tool call or hook, rather than inside a stdio MCP server that Claude Code started, use `CLAUDE_CODE_CHILD_SESSION` instead | | `CLAUDE_AFK_COUNTDOWN_MS` | How many milliseconds before auto-continue the on-screen countdown appears on an unanswered [`AskUserQuestion`](/docs/en/tools-reference) dialog. Default `20000` (20 seconds), capped at the auto-continue timeout. Has no effect unless auto-continue is on; see the [`askUserQuestionTimeout`](/docs/en/settings#available-settings) setting and `CLAUDE_AFK_TIMEOUT_MS`. Requires Claude Code v2.1.198 or later | | `CLAUDE_AFK_TIMEOUT_MS` | How many milliseconds of idle time before an unanswered [`AskUserQuestion`](/docs/en/tools-reference) dialog auto-continues without you. Auto-continue is off by default; opt in with the [`askUserQuestionTimeout`](/docs/en/settings#available-settings) setting. This variable is an override for demos and automated tests: when set, it takes precedence over that setting and turns auto-continue on even when the setting is unset or `never`. Setting `0` doesn't turn the timeout off; it closes the dialog immediately. In v2.1.198 and v2.1.199, auto-continue was on by default with a `60000` (60 seconds) timeout. Requires Claude Code v2.1.198 or later | -| `CLAUDE_AGENT_SDK_DISABLE_BUILTIN_AGENTS` | Set to `1` to disable all built-in [subagent](/docs/en/sub-agents) types such as Explore and Plan. Only applies in non-interactive mode (the `-p` flag). Useful for SDK users who want a blank slate. This also removes `general-purpose`, the subagent an Agent tool call gets when it names none. Such calls then fail with [`subagent_type is required`](/docs/en/errors#subagent-type-is-required) | +| `CLAUDE_AGENT_SDK_DISABLE_BUILTIN_AGENTS` | Set to `1` to disable all built-in [subagent](/docs/en/sub-agents) types such as Explore and Plan. Only applies in non-interactive mode (the `-p` flag). Useful for SDK users who want a blank slate. This also removes `general-purpose`, the subagent Claude Code runs when an Agent tool call omits `subagent_type`. Such a call then fails with [`subagent_type is required`](/docs/en/errors#subagent-type-is-required) | | `CLAUDE_AGENT_SDK_MCP_NO_PREFIX` | Set to `1` to skip the `mcp__<server>__` prefix on tool names from SDK-created MCP servers. Tools use their original names. SDK usage only | | `CLAUDE_ASYNC_AGENT_STALL_TIMEOUT_MS` | Stall timeout in milliseconds for background subagents. Default `600000` (10 minutes). The timer resets on each streaming progress event; if no progress arrives within the window, the subagent is aborted and the task is marked failed, surfacing any partial result to the parent | | `CLAUDE_AUTOCOMPACT_PCT_OVERRIDE` | Set the percentage (1-100) of the auto-compact window at which auto-compaction triggers. Use lower values like `50` to compact earlier; the variable can't raise the threshold, so values above the default percentage are ignored. It applies only in sessions that [compact before the model's context limit](/docs/en/model-config#context-window-and-auto-compaction). Applies to both main conversations and subagents |
debug-your-config Changed · +2 / -2 lines
from line 37
Settings merge across managed, user, project, and local scopes. Managed settings apply first when present. Among the rest, the closer scope overrides the broader one in the order local, then project, then user. Some settings can also be set by command-line flags or [environment variables](/docs/en/env-vars), which act as another override layer. When a setting doesn't seem to apply, the value you set is usually being overridden by another scope or an environment variable. -Run `/doctor` to check your configuration and installation. It reports what it finds, including invalid settings files, duplicate installations, unused extensions, and checked-in `CLAUDE.md` content Claude can derive from the codebase, then proposes fixes it applies only after you confirm. The `CLAUDE.md` trim check requires Claude Code v2.1.206 or later. Before v2.1.205, `/doctor` opened a read-only diagnostics screen and pressing `f` sent the report to Claude to fix. +Run [`/doctor`](/docs/en/commands#all-commands) to find invalid settings files. From the terminal, `claude doctor` prints read-only installation and settings diagnostics without starting a session.
from line 102
| Subdirectory `CLAUDE.md` instructions seem ignored | Subdirectory files load on demand, not at session start | They load when Claude reads a file in that directory with the Read tool, not at launch and not when writing or creating files there. See [how CLAUDE.md files load](/docs/en/memory#how-claude-md-files-load). | | Subagent ignores `CLAUDE.md` instructions | The built-in Explore and Plan agents skip `CLAUDE.md`. Custom subagents load it the same way the main conversation does | For Explore or Plan, restate the instruction in your delegating prompt. For a custom subagent, put critical instructions in the agent file body, which becomes the agent's system prompt. See [what loads at startup](/docs/en/sub-agents#what-loads-at-startup). | | Cleanup logic never runs at session end | No `SessionEnd` hook configured | Add a `SessionEnd` hook in `settings.json`. See the [hook events list](/docs/en/hooks#hook-events). | -| MCP servers in `.mcp.json` never load | File is under `.claude/` or uses Claude Desktop's config format | Project MCP config goes at the repository root as `.mcp.json`, not inside `.claude/`. See [MCP configuration](/docs/en/mcp). | +| MCP servers in `.mcp.json` never load | File is under `.claude/`, or its servers sit under a top-level `servers` key, as in VS Code's `mcp.json`, instead of `mcpServers` | Project MCP config goes at the repository root as `.mcp.json`, not inside `.claude/`, with servers under the `mcpServers` key. See [MCP configuration](/docs/en/mcp). | | MCP servers added under `mcpServers` in `settings.json` never appear | `settings.json` does not read an `mcpServers` key | Define project servers in `.mcp.json` at the repository root, or run `claude mcp add --scope user` for user-scoped servers. See [MCP configuration](/docs/en/mcp). | | Project MCP server added but doesn't appear | The one-time approval prompt was dismissed | Project-scoped servers require approval. Run `/mcp` to see status and approve. | | MCP server fails to start from some directories | `command` or `args` uses a relative file path | Use absolute paths for local scripts. Executables on your `PATH` like `npx` or `uvx` work as-is. |
agent-sdk/subagents Changed · +1 / -1 lines
from line 189
<Note> Even without defining custom subagents, Claude can spawn the built-in `general-purpose` subagent. This is useful for delegating research or exploration tasks without creating specialized agents. Include `Agent` in `allowedTools` so these invocations auto-approve without a permission prompt. - A call to the Agent tool that leaves out `subagent_type` gets this built-in `general-purpose` subagent. If you disable the built-in subagents with [`CLAUDE_AGENT_SDK_DISABLE_BUILTIN_AGENTS=1`](/docs/en/env-vars), there is nothing to fall back to. Such a call then fails with `subagent_type is required: the general-purpose agent is not available in this session`, followed by the names of your subagents. Before TypeScript SDK v0.3.235 (Python SDK: bundled Claude Code earlier than v2.1.235), it failed with `Agent type 'general-purpose' not found` instead. + When Claude calls the Agent tool without a `subagent_type`, it gets this built-in `general-purpose` subagent. If you set [`CLAUDE_AGENT_SDK_DISABLE_BUILTIN_AGENTS=1`](/docs/en/env-vars), that default is gone too. Such a call then fails with `subagent_type is required: the general-purpose agent is not available in this session`. The message ends with the subagent types that are still available. Before TypeScript SDK v0.3.235 (Python SDK: bundled Claude Code before v2.1.235), the same call failed with `Agent type 'general-purpose' not found`. </Note> ## What subagents inherit