Source Intelligence
Sweep 28 Aug 2026 ยท 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 sandbox.

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.

cloud-sandboxes-reference Claude Developer Platform · title managed-agents/cloud-sandboxes-reference self-hosted-sandboxes-security Claude Developer Platform · title managed-agents/self-hosted-sandboxes-security Choose a sandbox environment Claude Code CLI · title sandbox-environments Configure the sandboxed Bash tool Claude Code CLI · title sandboxing spawn.sh: called once per claimed work item Claude Developer Platform · path managed-agents/self-hosted-sandboxes optimizing-for-cost-and-intelligence Claude Developer Platform · in the page about-claude/models/optimizing-for-cost-and-intelligence …h Anthropic's implementation on Claude Managed Agents (standard cloud sandbox; advisor configurations use the Managed Agents advisor). Claude Sonnet 4.6 grades instead of the reference judge and the b… claude-api-skill Claude Developer Platform · in the page agents-and-tools/agent-skills/claude-api-skill …opic-hosted tool execution, persistent agent configs, and per-session sandboxes. It covers eight programming languages for both the Messages API and Managed Agents: Python, TypeScript, C#, Go, Java,… enterprise Claude Developer Platform · in the page agents-and-tools/agent-skills/enterprise …. **Verify script behavior matches stated purpose.** Run scripts in a sandboxed environment and confirm outputs align with the Skill's description. 3. **Check for adversarial instructions.** Look for… PDF Processing Claude Developer Platform · in the page agents-and-tools/agent-skills/overview …e: all workspace members can access them. Skills on the API run in a sandboxed container with no network access and no runtime package installation. See [Limitations and constraints](https://platform… bash-tool Claude Developer Platform · in the page agents-and-tools/tool-use/bash-tool …arate execution environments: your local bash session and Anthropic's sandboxed container. State is not shared between them. See [Using code execution with other execution tools](https://platform.clau… code-execution-tool Claude Developer Platform · in the page agents-and-tools/tool-use/code-execution-tool …ol-use/code-execution-tool description: Run Python and bash code in a sandboxed container to analyze data, generate files, and iterate on solutions. --- Claude can analyze data, create visualizations… computer-use-tool Claude Developer Platform · in the page agents-and-tools/tool-use/computer-use-tool …-prompting)). ### The computing environment Computer use requires a sandboxed computing environment where Claude can safely interact with applications and the web. This environment includes: 1. **V… how-tool-use-works Claude Developer Platform · in the page agents-and-tools/tool-use/how-tool-use-works …/tool-reference) | | Server-executed tools | Web search, code sandbox, web fetch | Anthropic handles execution; you read the results instead of producing… manage-tool-context Claude Developer Platform · in the page agents-and-tools/tool-use/manage-tool-context …a single code block that Claude writes and Anthropic's code execution sandbox runs. Rather than five roundtrips of `tool_use` and `tool_result`, Claude emits one script that calls all five functions f… overview Claude Developer Platform · in the page agents-and-tools/tool-use/overview …ools/tool-use/code-execution-tool"> Run Python and bash code in a sandboxed container to analyze data and generate files. </Card> <Card title="Advisor tool" icon="lightbulb" href="https://pla… Process results programmatically Claude Developer Platform · in the page agents-and-tools/tool-use/programmatic-tool-calling …ool calls and pre/post-processing logic 2. Claude runs this code in a sandboxed container through code execution 3. When a tool function is called, code execution pauses and the API returns a `tool_us… server-tools Claude Developer Platform · in the page agents-and-tools/tool-use/server-tools …ools/tool-use/code-execution-tool"> Run Python and bash code in a sandboxed container to analyze data, generate files, and iterate on solutions. </Card> <Card title="Tool search tool" icon="c… tool-combinations Claude Developer Platform · in the page agents-and-tools/tool-use/tool-combinations …ced a gap. Code execution runs server-side, so there's no client-side sandbox to manage. ## Coding agent: text\_editor + bash The text editor reads and modifies files; bash runs tests and build comm… tool-reference Claude Developer Platform · in the page agents-and-tools/tool-use/tool-reference …/agents-and-tools/tool-use/programmatic-tool-calling) from within the sandbox; `code_execution_20260521` discloses the per-cell time limit in the tool description. In each case, both the new and old v… web-fetch-tool Claude Developer Platform · in the page agents-and-tools/tool-use/web-fetch-tool …="Code execution tool" icon="code"> Run Python and bash code in a sandboxed container to analyze data, generate files, and iterate on solutions. </Card> <Card href="https://platform.claude.co… Admin Claude Developer Platform · in the page api/admin …ber or null` Number of API requests in this row's scope. For sandbox / code-execution events, this counts execution spans rather than HTTP requests (these rows surface with `product: null`).… Analytics Claude Developer Platform · in the page api/admin/analytics …ber or null` Number of API requests in this row's scope. For sandbox / code-execution events, this counts execution spans rather than HTTP requests (these rows surface with `product: null`).… Cost Claude Developer Platform · in the page api/admin/analytics/cost …per-component attribution; read it from the ungrouped response). For sandbox / code-execution events, this counts execution spans rather than HTTP requests (these rows surface with `product: null`).… Get Cost Over Time Claude Developer Platform · in the page api/admin/analytics/cost/list …per-component attribution; read it from the ungrouped response). For sandbox / code-execution events, this counts execution spans rather than HTTP requests (these rows surface with `product: null`).… Get Per-User Cost Claude Developer Platform · in the page api/admin/analytics/cost/list_by_user …per-component attribution; read it from the ungrouped response). For sandbox / code-execution events, this counts execution spans rather than HTTP requests (these rows surface with `product: null`).… Usage Claude Developer Platform · in the page api/admin/analytics/usage …ber or null` Number of API requests in this row's scope. For sandbox / code-execution events, this counts execution spans rather than HTTP requests (these rows surface with `product: null`).… Get Token Usage Over Time Claude Developer Platform · in the page api/admin/analytics/usage/list …ber or null` Number of API requests in this row's scope. For sandbox / code-execution events, this counts execution spans rather than HTTP requests (these rows surface with `product: null`).… Get Per-User Token Usage Claude Developer Platform · in the page api/admin/analytics/usage/list_by_user …umber or null` Number of API requests in this row's scope. For sandbox / code-execution events, this counts execution spans rather than HTTP requests (these rows surface with `product: null`).… Environments Claude Developer Platform · in the page api/beta/environments …ided in the SDKs and CLI, for orchestrating sessions with self-hosted sandbox environments. They are included here as a reference; you do not need to invoke them directly. Retrieve detailed informati… Work Claude Developer Platform · in the page api/beta/environments/work …ided in the SDKs and CLI, for orchestrating sessions with self-hosted sandbox environments. They are included here as a reference; you do not need to invoke them directly. Retrieve detailed informati… Acknowledge Work Claude Developer Platform · in the page api/beta/environments/work/ack …ided in the SDKs and CLI, for orchestrating sessions with self-hosted sandbox environments. They are included here as a reference; you do not need to invoke them directly. Acknowledge receipt of a wo… Record Heartbeat Claude Developer Platform · in the page api/beta/environments/work/heartbeat …ided in the SDKs and CLI, for orchestrating sessions with self-hosted sandbox environments. They are included here as a reference; you do not need to invoke them directly. Record a heartbeat for a wo… List Work Items Claude Developer Platform · in the page api/beta/environments/work/list …ided in the SDKs and CLI, for orchestrating sessions with self-hosted sandbox environments. They are included here as a reference; you do not need to invoke them directly. List work items in an envir… Poll for Work Claude Developer Platform · in the page api/beta/environments/work/poll …ided in the SDKs and CLI, for orchestrating sessions with self-hosted sandbox environments. They are included here as a reference; you do not need to invoke them directly. Long poll for work items in… Get Work Item Claude Developer Platform · in the page api/beta/environments/work/retrieve …ided in the SDKs and CLI, for orchestrating sessions with self-hosted sandbox environments. They are included here as a reference; you do not need to invoke them directly. Retrieve detailed informati… Stop Work Claude Developer Platform · in the page api/beta/environments/work/stop …ided in the SDKs and CLI, for orchestrating sessions with self-hosted sandbox environments. They are included here as a reference; you do not need to invoke them directly. Stop a work item, initiatin… Update Work Item Claude Developer Platform · in the page api/beta/environments/work/update …ided in the SDKs and CLI, for orchestrating sessions with self-hosted sandbox environments. They are included here as a reference; you do not need to invoke them directly. Update work item metadata w… Events Claude Developer Platform · in the page api/beta/sessions/events …olset tool execution. Only valid on `self_hosted` environments, where sandbox-routed tools are executed by the client rather than the server. - `id: string` Unique identifier for this even… List Events Claude Developer Platform · in the page api/beta/sessions/events/list …olset tool execution. Only valid on `self_hosted` environments, where sandbox-routed tools are executed by the client rather than the server. - `id: string` Unique identifier for this even… Send Events Claude Developer Platform · in the page api/beta/sessions/events/send …olset tool execution. Only valid on `self_hosted` environments, where sandbox-routed tools are executed by the client rather than the server. - `tool_use_id: string` The id of the `agent.t… Stream Events Claude Developer Platform · in the page api/beta/sessions/events/stream …olset tool execution. Only valid on `self_hosted` environments, where sandbox-routed tools are executed by the client rather than the server. - `id: string` Unique identifier for this even… Threads Claude Developer Platform · in the page api/beta/sessions/threads …olset tool execution. Only valid on `self_hosted` environments, where sandbox-routed tools are executed by the client rather than the server. - `id: string` Unique identifier for this even… Events Claude Developer Platform · in the page api/beta/sessions/threads/events …olset tool execution. Only valid on `self_hosted` environments, where sandbox-routed tools are executed by the client rather than the server. - `id: string` Unique identifier for this even… List Session Thread Events Claude Developer Platform · in the page api/beta/sessions/threads/events/list …olset tool execution. Only valid on `self_hosted` environments, where sandbox-routed tools are executed by the client rather than the server. - `id: string` Unique identifier for this even… Stream Session Thread Events Claude Developer Platform · in the page api/beta/sessions/threads/events/stream …olset tool execution. Only valid on `self_hosted` environments, where sandbox-routed tools are executed by the client rather than the server. - `id: string` Unique identifier for this even… claude-platform-on-aws-iam-actions Claude Developer Platform · in the page api/claude-platform-on-aws-iam-actions …</Note> <Note> `ProcessEnvironmentWork` authorizes a [self-hosted sandbox](https://platform.claude.com/docs/en/managed-agents/self-hosted-sandboxes) worker to poll for, acknowledge, heartbeat, sto… overview Claude Developer Platform · in the page api/overview …aged-agents/sessions)**: Run stateful agent sessions in managed cloud sandboxes (`POST /v1/sessions`, `GET /v1/sessions/{id}/events/stream`) * **[Environments API](https://platform.claude.com/docs/en/… claude-platform-on-aws Claude Developer Platform · in the page build-with-claude/claude-platform-on-aws …out of the box. * **Code execution:** Run code in Anthropic's managed sandbox using the [code execution tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/code-execution-tool). * **To… files Claude Developer Platform · in the page build-with-claude/files …ools/tool-use/code-execution-tool"> Run Python and bash code in a sandboxed container to analyze data, generate files, and iterate on solutions. </Card> <Card title="Vision" icon="image" href… mid-conversation-effort-example Claude Developer Platform · in the page build-with-claude/mid-conversation-effort-example …mall throwaway fixture directory that is removed on exit. There is no sandbox here: the command runs with the permissions of the process that launched the example. For clarity this example runs each c…