Source Intelligence
Sweep 28 Aug 2026 · 00:00Z Build v2.1.250 478 read Stable v2.1.236 Latest v2.1.250 Next v2.1.250 Feeds RSS JSON llms.txt

DisclaimerUnofficial, and not affiliated with Anthropic. Nearly all of this is read straight out of what ships: npm bundles, captured prompts, published docs. Anthropic's own notes go in verbatim, marked as theirs. The rest is my reading, and every entry carries the strings behind it. If one looks wrong, vote it down and say why.

Search the documentation

50 pages for watch.

Titles and paths first, then pages whose text carries it. Each row opens that page as this site last read it. Cut at 50, so a narrower query shows the rest.

Watch monitors and alerts Claude Documentation · title claude-tag/users/use-cases/watch-monitors optimizing-for-cost-and-intelligence Claude Developer Platform · in the page about-claude/models/optimizing-for-cost-and-intelligence …nder-calling executor and capping calls client-side to bound cost. So watch the consult rate: prompt for it, measure it, and restore the executor's effort if it collapses. **When it pays on cost.** A… PDF Processing Claude Developer Platform · in the page agents-and-tools/agent-skills/best-practices …n Skills, pay attention to how Claude actually uses them in practice. Watch for: * **Unexpected exploration paths:** Does Claude read files in an order you didn't anticipate? This might indicate your… fine-grained-tool-streaming Claude Developer Platform · in the page agents-and-tools/tool-use/fine-grained-tool-streaming …and asks Claude for a long poem, so the tool input is large enough to watch it stream in: <CodeGroup> ```bash cURL curl https://api.anthropic.com/v1/messages \ -H "content-type: application/j… memory-tool Claude Developer Platform · in the page agents-and-tools/tool-use/memory-tool …aining sequences such as `../`, `..\\`, or other traversal patterns * Watch for URL-encoded traversal sequences (`%2e%2e%2f`) * Use your language's built-in path security utilities (for example, Pytho… routines-fire Claude Developer Platform · in the page api/claude-code/routines-fire …string | A link to the session on claude.ai. Open it in a browser to watch the run, review changes, or continue the conversation. | ### Errors Errors use the standard Anthropic [error envelope](htt… claude-in-amazon-bedrock Claude Developer Platform · in the page build-with-claude/claude-in-amazon-bedrock …itoring and logging Claude in Amazon Bedrock emits logs to both CloudWatch and CloudTrail. Anthropic recommends retaining activity logs on at least a 30-day rolling basis to understand usage patterns… context-editing Claude Developer Platform · in the page build-with-claude/context-editing …er` supports compaction but does not log events. Detect compaction by watching `runner.params.messages.length` shrink between turns: ```typescript TypeScript let prevMsgCount = 0; for awa… claude-prompting-best-practices Claude Developer Platform · in the page build-with-claude/prompt-engineering/claude-prompting-best-practices …Claude will delegate appropriately without explicit instruction. 3. **Watch for overuse:** Claude Opus 4.6 has a strong predilection for subagents and may spawn them in situations where a simpler, dir… prompting-claude-fable-5 Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-fable-5 …minder: ```text wrap You are operating autonomously. The user is not watching in real time and cannot answer questions mid-task, so asking "Want me to…?" or "Shall I…?" will block the work. For rever… scripting Claude Developer Platform · in the page cli-sdks-libraries/cli/scripting …to maintain and refactor with confidence. ``` <Tip> To watch a session as it runs, use `ant beta:sessions:events stream --session-id session_01JZCh78XvmxJjiXVy3oSi7K`. Events are writte… apple-foundation-models Claude Developer Platform · in the page cli-sdks-libraries/libraries/apple-foundation-models …-sdks). </Info> ## Requirements * iOS 27, macOS 27, visionOS 27, or watchOS 27 (all in beta): the OS releases whose Foundation Models framework supports server-side language models * Xcode 27 (beta)… compliance-errors Claude Developer Platform · in the page manage-claude/compliance-errors …linked organizations, and concurrent workers) below the shared limit. Watch `anthropic-ratelimit-requests-remaining` to slow down before you reach it. See [Design your compliance integration](https://… dreams Claude Developer Platform · in the page managed-agents/dreams …eft as-is. | ### Watch the pipeline run Once a dream is `running`, its `session_id` field points at the underlying [session](https://platform.clau… events-and-streaming Claude Developer Platform · in the page managed-agents/events-and-streaming …on-level stream, whose previews stay scoped to the primary thread. To watch a subagent's text as the model generates it, open that subagent's thread stream. The thread stream's path is easy to get wr… multiagent-orchestration Claude Developer Platform · in the page managed-agents/multiagent-orchestration …ild thread's previews never appear on the session-level stream, so to watch a subagent live, open its own thread stream. See [Preview session thread events](https://platform.claude.com/docs/en/managed… onboarding Claude Developer Platform · in the page managed-agents/onboarding …your agent, you can start a test session directly, send messages, and watch the event stream without leaving the page. This is the fastest way to check that your system prompt and tool selection produ… spawn.sh: called once per claimed work item Claude Developer Platform · in the page managed-agents/self-hosted-sandboxes …same checks but only logs what it would have deleted, which lets you watch what your workers would delete before you trust the enabled mode; when disabled, it never deletes from the store. Uploads an… overview Claude Developer Platform · in the page release-notes/overview …API as Apple's on-device model on iOS 27, macOS 27, visionOS 27, and watchOS 27 (beta). ### June 5, 2026 * We announced the deprecation of the Claude Opus 4.1 model (`claude-opus-4-1-20250805`), wi… How the agent loop works Claude Code CLI · in the page agent-sdk/agent-loop …n-configuration) to scope subagents to the minimum set they need. * **Watch MCP server costs.** [MCP tool search](/docs/en/agent-sdk/mcp#mcp-tool-search) defers MCP tool schemas by default and loads t… Track cost and usage Claude Code CLI · in the page agent-sdk/cost-tracking …result's `usage`, or from `modelUsage` for a per-model breakdown. To watch a response's output count grow while it streams, set `includePartialMessages`, or `include_partial_messages` in Python, and… Rewind file changes with checkpointing Claude Code CLI · in the page agent-sdk/file-checkpointing …hange the prompt to name files that exist in your project, so you can watch files change and see the rewind restore them. <CodeGroup> ```python Python theme={null} import asyncio from claude_ag… Intercept and control agent behavior with hooks Claude Code CLI · in the page agent-sdk/hooks …| No | Yes | A watched file is modified, created, or deleted… Hosting the Agent SDK Claude Code CLI · in the page agent-sdk/hosting …nd subagents only, `CLAUDE_ASYNC_AGENT_STALL_TIMEOUT_MS` sets a stall watchdog that fires when a `run_in_background` subagent stops producing output; it is not a total-runtime deadline. | ## Next ste… Modifying system prompts Claude Code CLI · in the page agent-sdk/modifying-system-prompts …e `claude_code` preset for CLI or IDE-like coding tools where a human watches and steers the work. Write your own prompt for agents with a different surface, identity, or permission model. ## How sys… Agent SDK reference - Python Claude Code CLI · in the page agent-sdk/python …uns that need to wait through longer outages, set [`CLAUDE_CODE_RETRY_WATCHDOG=1`](/docs/en/errors#tune-retry-behavior): it retries transient capacity errors indefinitely and, on Claude Code v2.1.199… Subagents in the SDK Claude Code CLI · in the page agent-sdk/subagents …s appropriately ### Filesystem-based agents not loading Claude Code watches `~/.claude/agents/` and `.claude/agents/` and picks up a new or edited agent file within a few seconds, with no restart ne… Track todos Claude Code CLI · in the page agent-sdk/todo-tracking …nt messages. </Note> ### Monitor todo changes The following example watches the assistant stream for `TaskCreate` and `TaskUpdate` `tool_use` blocks and prints a `+` line with each new task's subjec… Agent SDK reference - TypeScript Claude Code CLI · in the page agent-sdk/typescript …uns that need to wait through longer outages, set [`CLAUDE_CODE_RETRY_WATCHDOG=1`](/docs/en/errors#tune-retry-behavior): it retries transient capacity errors indefinitely and, on Claude Code v2.1.199… Manage multiple agents with agent view Claude Code CLI · in the page agent-view …nning, what needs your input, and what's done. Dispatch new sessions, watch their state at a glance instead of scrolling through transcripts, and step in only when one needs you. Each background sessi… Run agents in parallel Claude Code CLI · in the page agents …nage agents with agent view](/docs/en/agent-view): dispatch sessions, watch their state, and attach when one needs you. * [Orchestrate agent teams](/docs/en/agent-teams): set up a lead and teammates,… Share session output as artifacts Claude Code CLI · in the page artifacts …nts on its own After your session publishes an artifact, Claude Code watches that artifact for comments for as long as the session runs. When a commenter sends a comment to Claude, it reaches your se… Best practices for Claude Code Claude Code CLI · in the page best-practices …mands, make changes, and autonomously work through problems while you watch, redirect, or step away entirely. This changes how you work. Instead of writing code yourself and asking Claude to review i… Champion kit Claude Code CLI · in the page champion-kit …good answer to one person frequently unblocks several others who are watching the same channel. ### Answer with a prompt rather than an explanation When a colleague asks how you accomplished someth… Claude Code changelog Claude Code CLI · in the page changelog …d managed settings: client-side timeout, MCP startup-mode, and stream-watchdog env vars no longer trigger the settings-approval prompt * Improved `/ultrareview <PR#>` to check before launch that the… Channels reference Claude Code CLI · in the page channels-reference …API/Server-sent_events) (SSE), so `curl -N localhost:8788/events` can watch them live; inbound chat arrives on `POST /`: ```ts title="Full webhook.ts with reply tool" expandable theme={null} #!/usr/b… Claude apps gateway for Amazon Bedrock, Claude Platform on AWS, Google Cloud, and Microsoft Foundry Claude Code CLI · in the page claude-apps-gateway …instance credentials resolve on the first request, not at boot. Watch stderr for the boot sequence. Log lines use the format `[gateway] <timestamp> <level> <message>`, audit events are single-li… Deploy Claude apps gateway on AWS Claude Code CLI · in the page claude-apps-gateway-on-aws …operational logs. Retention is a separate call, and without one CloudWatch keeps the logs forever; align the 90 days with your audit retention policy: ```bash theme={null} aws ecs cr… Use Claude Code on the web Claude Code CLI · in the page claude-code-on-the-web …m before a session is deleted. ## Auto-fix pull requests Claude can watch a pull request and automatically respond to CI failures and review comments. Claude subscribes to GitHub activity on the PR,… CLI reference Claude Code CLI · in the page cli-reference …om Claude Code's, like a non-coding agent in a pipeline that no human watches. Replacing drops all of the default prompt, including tool guidance and safety instructions, so you take responsibility fo… Commands Claude Code CLI · in the page commands …(/docs/en/claude-code-on-the-web#auto-fix-pull-requests) session that watches the current branch's PR and pushes fixes when CI fails or reviewers leave comments. Detects the open PR from your checked-… Communications kit Claude Code CLI · in the page communications-kit …curity Where to go with questions: #claude-code. [Owner name] is watching it this week. - [Name] P.S. Prefer your editor? There is a VS Code extension and a JetBrains plugin. Sa… Let Claude use your computer from the CLI Claude Code CLI · in the page computer-use …nal window stays visible and is excluded from screenshots, so you can watch the session and Claude never sees its own output. When Claude finishes the turn, hidden apps are restored automatically. #… Explore the context window Claude Code CLI · in the page context-window …0, textAlign: 'center', lineHeight: 1.5 }}> Watch what loads into context, from the moment you run <code style={{ fontFamily: mono }}>claude</code> through a full conve… Message your other Claude Code sessions Claude Code CLI · in the page cross-session-messaging …ork**: have a migration or test run report back to the session you're watching, or ask it yourself from there. If that session is on this machine, Claude can also [ask it for one notice when it next g… Debug your configuration Claude Code CLI · in the page debug-your-config …hooks` shows the hook but it still does not fire, the next step is to watch hook evaluation live. Start a session with `claude --debug` and trigger the tool call. The debug log records each event, whi… Desktop application Claude Code CLI · in the page desktop …[Review and comment on diffs](#review-changes-with-diff-view), then [watch the resulting PR through CI](#monitor-pull-request-status) * [Preview your running app](#preview-your-app) in the Browser pa… Test iOS apps in the simulator Claude Code CLI · in the page desktop-ios-simulator …ane opens automatically and streams the device screen live. Use it to watch Claude run and test your app, or to tap through the app yourself while Claude keeps working. The simulator pane drives the… Get started with the desktop app Claude Code CLI · in the page desktop-quickstart …h in its own Git worktree, and open the [tasks pane](/docs/en/desktop#watch-background-tasks) to watch the subagents and background commands a session has running. Open a [side chat](/docs/en/desktop#… Schedule recurring tasks in Claude Code Desktop Claude Code CLI · in the page desktop-scheduled-tasks …wer later. To avoid stalls, click **Run now** after creating a task, watch for permission prompts, and select "always allow" for each one. Future runs of that task auto-approve the same tools without…