One read of Claude Code CLIclaude-code-20261008T220701Z
5 pages moved out of 221 read.
Pages moved
5
significant first
Pages read
221
in this capture
Captured
22:07 UTC
Corpus hash
c10f97772030
corpus-hash
What this read moved
1-5 of 5plugins/mods/reference Changed · +9 / -0 lines
#### Agent and organization fields on `tool.check`
from line 54
5454| [`tool.check`](/docs/en/plugins/mods/events#where-settings-hooks-run-in-the-order) | Claude Code decides whether a tool call may run, after the `tool.call` and `PreToolUse` hooks. `next(e)` resolves to the decision the rules, the permission mode, and those hooks reached. | `{ decision }`, which is `allow`, `ask`, or `deny` |
5555| `tool.describe` | Once for each tool, when its description is first sent to Claude | `{ description }`, optionally with `isDeferred` set to `true` to put the tool behind [tool search](/docs/en/mcp#scale-with-mcp-tool-search) or `false` to load it upfront |
5656
57#### Agent and organization fields on `tool.check`
58
59In a `tool.check` hook, read these fields to tell a subagent's call from the main conversation's, and to see whether your organization requires approval for a connector tool:
60
61* **`e.agentId`**: set when a [subagent](/docs/en/sub-agents) or an [in-process teammate](/docs/en/agent-teams#choose-a-display-mode) makes the call, and absent when the main conversation does
62* **`e.ceiling`**: `ask` for a connector tool your organization set to `ask`, in [sessions where that setting reaches Claude Code](/docs/en/mcp#organization-controls-on-connector-tools)
63
64On `tool.check`, `e.agentId` and `e.ceiling` require Claude Code v2.1.290 or later.
65
5766### Prompts and what Claude reads
5867
5968Prompt events cover the text the user types and the text Claude Code sends to Claude on its own, such as the system prompt and reminders:
settings-reference Changed · +4 / -2 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 2924
29242924
29252925 Ignoring this group in project and local settings requires Claude Code v2.1.282 or later.
29262926 * Variables that change how Claude Code starts or syncs, such as `CLAUDE_CODE_PROCESS_WRAPPER`, `CLAUDE_CODE_SYNC_SKILLS`, `CLAUDE_CODE_SYNC_PLUGINS`, `CLAUDE_CODE_PLUGIN_CACHE_DIR`, and `CLAUDE_CODE_PLUGIN_SEED_DIR`.
2927 * Variables that set the timers on an unanswered dialog: [`CLAUDE_CODE_USER_DIALOG_TIMEOUT_MS`, `CLAUDE_AFK_TIMEOUT_MS`, and `CLAUDE_AFK_COUNTDOWN_MS`](/docs/en/env-vars#variables).
2928 * [`CLAUDE_CODE_DISABLE_ATTACHMENTS`](/docs/en/env-vars#variables), which turns off attachment processing.
29272929
2928 Before v2.1.251, project and local settings could also set the variables in this list that choose where Claude Code writes its files or that export session content, except `HOME` and `XDG_CONFIG_HOME`.
2930 Before v2.1.251, project and local settings could also set the variables in this list that choose where Claude Code writes its files or that export session content, except `HOME` and `XDG_CONFIG_HOME`. Before v2.1.290, they could also set the dialog timer variables and `CLAUDE_CODE_DISABLE_ATTACHMENTS`.
29292931* Identity variables that Claude Code's hosting environments own, such as `CLAUDE_CODE_REMOTE` and `CLAUDE_CODE_ACCOUNT_UUID`, are ignored from every file.
29302932* [`CLAUDE_CODE_MESSAGING_SOCKET` and `CLAUDE_CODE_MESSAGING_TOKEN`](/docs/en/env-vars#variables), which Claude Code exports itself, are ignored from every file. Ignoring the socket variable requires Claude Code v2.1.224 or later, and ignoring the token requires v2.1.228 or later.
29312933* [`CLAUDE_CODE_PROJECT_DIR_NAME`](/docs/en/sessions#name-the-project-directory-yourself), which Claude Code reads from the launch environment only, is ignored from every file; requires v2.1.234 or later.
from line 4044
40424044The reach depends on which file carries the key:
40434045
40444046* **In managed settings**: Claude Code disables every configured hook, including managed ones, and keeps running the hooks the [Agent SDK](/docs/en/agent-sdk/overview) registers in process
4045* **In any other settings file**: Claude Code disables user, project, local, and plugin hooks; managed hooks, Agent SDK hooks, and hooks from plugins force-enabled in managed [`enabledPlugins`](#enabledplugins) keep running
4046
4047The key also stops [mods](/docs/en/plugins/mods/overview), which are plugins whose code registers hooks:
4048
4049* **In managed settings**: the mods in every installed plugin stop, your organization's included
4050* **In any other settings file**: the mods you installed stop, and [your organization's mods](/docs/en/plugin
4047* **In any other settings file**: Claude Code disables user, project, local, and plugin hooks; managed hooks, Agent SDK hooks, and hooks from
sub-agents Changed · +8 / -2 lines
### Choose an effort level
from line 309
309309| `memory` | No | [Persistent memory scope](#enable-persistent-memory): `user`, `project`, or `local`. Enables cross-session learning |
310310| `background` | No | Set to `true` to keep this subagent in the background even when Claude asks to run it in the foreground. Where [fork mode](#turn-fork-mode-on-or-off) is on, Claude Code already runs the subagents Claude spawns [in the background](#run-subagents-in-foreground-or-background) |
311311| `omitClaudeMd` | No | Set to `true` to launch this subagent without the user, project, and local CLAUDE.md files; [managed policy files](/docs/en/memory#how-claude-md-files-load) still load, except for [managed subagents](#choose-the-subagent-scope). Use it for subagents that take everything they need from the [delegation prompt](#what-loads-at-startup). Ignored when the agent runs as the main session agent via `--agent` or the `agent` setting. Requires Claude Code v2.1.271 or later |
312| `effort` | No | Effort level when this subagent is active. Overrides the session effort level, but not the [`CLAUDE_CODE_EFFORT_LEVEL`](/docs/en/env-vars#variables) environment variable. Options: `low`, `medium`, `high`, `xhigh`, `max`; available levels depend on the model |
312| `effort` | No | Effort level when this subagent is active. Overrides the session effort level, but not the [`CLAUDE_CODE_EFFORT_LEVEL`](/docs/en/env-vars#variables) environment variable. Options: `low`, `medium`, `high`, `xhigh`, `max`; available levels depend on the model. See [Choose an effort level](#choose-an-effort-level) |
313313| `isolation` | No | Set to `worktree` to run the subagent in a temporary [git worktree](/docs/en/worktrees), giving it an isolated copy of the repository branched by default from your [default branch](/docs/en/worktrees#choose-the-base-branch) rather than the parent session's `HEAD`. The worktree is automatically cleaned up if the subagent makes no changes |
314314| `color` | No | Display color for the subagent in the task list and transcript. Accepts `red`, `blue`, `green`, `yellow`, `purple`, `orange`, `pink`, or `cyan` |
315315| `initialPrompt` | No | Auto-submitted as the first user turn when this agent runs as the main session agent (via `--agent` or the `agent` setting). [Commands](/docs/en/commands) and [skills](/docs/en/skills) are processed. Prepended to any user-provided prompt. Ignored for [plugin subagents](#choose-the-subagent-scope) |
from line 381
381381
382382In interactive sessions, Claude Code shows a warning naming the requested model and the model the subagent runs on, for either substitution.
383383
384To check which model a subagent is running on, run [`/tasks`](/docs/en/commands). Claude Code names the model on the subagent's row, and adds the [effort level](/docs/en/model-config#adjust-effort-level) when the subagent's definition, or the skill it forked from, sets [`effort`](#supported-frontmatter-fields). Requires Claude Code v2.1.242 or later.
384To check which model a subagent is running on, run [`/tasks`](/docs/en/commands). Claude Code names the model on the subagent's row, and adds the [effort level](/docs/en/model-config#adjust-effort-level) set for that subagent, if any. Requires Claude Code v2.1.242 or later.
385385
386386A per-invocation `model` parameter also applies when the subagent is [resumed or sent a follow-up message](#resume-subagents), so the subagent stays on that model. Before v2.1.211, resuming dropped the per-invocation value and the subagent reverted to its definition's `model` field or, without one, the main conversation's model.
387387
from line 411
411411
412412* A [fork](#fork-the-current-conversation)
413413* A [skill that runs in a subagent](/docs/en/skills#run-skills-in-a-subagent) with `model: inherit`
414
415### Choose an effort level
416
417To run a subagent at its own [effort level](/docs/en/model-config#adjust-effort-level), set the [`effort`](#supported-frontmatter-fields) field in its definition.
418
419When you ask Claude to run a non-fork subagent at a specific effort level, it can also pass an `effort` parameter for that invocation. The parameter overrides the `effort` field and stays in effect when the subagent is [resumed](#resume-subagents). The [`CLAUDE_CODE_EFFORT_LEVEL`](/docs/en/env-vars#variables) environment variable takes precedence over both. The per-invocation parameter requires Claude Code v2.1.292 or later.
414420
415421### Control subagent capabilities
416422
agent-sdk/typescript Changed · +1 / -0 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 2906
29062906 prompt: string;
29072907 subagent_type?: string;
29082908 model?: "sonnet" | "opus" | "haiku" | "fable";
2909 effort?: "low" | "medium" | "high" | "xhigh" | "max";
29092910 run_in_background?: boolean;
29102911 name?: string;
29112912 team_name?: string; // Deprecated; ignored
from line 5360
53595360
53605361Emitted while Claude is producing a thinking block, including a redacted one. `estimated_tokens` is a running estimate of the thinking tokens generated so far in the current block, and `estimated_tokens_delta` is the increment carried by this frame. Use these estimates for progress display.
53615362
5362When the model or provider reports a breakdown, the final count for the top-level agent loop is the result message's [`usage.output_tokens_details.thinking_tokens`](#usage), which
5363When the model or provider reports a breakdown, the final count for the top-level agent loop is the result message's [`usag
claude-tag 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.
Nothing in the body moved in this read. What changed is above.