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.

Prompt capture

v2.1.12 tool descriptions

Agent SDK, print mode

17 tools, as the client described them to the model in this release. Where a tool has more than one description the difference is usually a single interpolated string.

AskUserQuestion Use this tool when you need to ask the user questions during execution. 813 chars Read → Bash Executes a given bash command in a persistent shell session with optional timeout, ensuring proper handling and... 9,798 chars Read → Edit Performs exact string replacements in files. 1,110 chars Read → EnterPlanMode Use this tool proactively when you're about to start a non-trivial implementation task. 4,021 chars Read → ExitPlanMode Use this tool when you are in plan mode and have finished writing your plan to the plan file and are ready for user... 3,915 chars Read → Glob - Fast file pattern matching tool that works with any codebase size - Supports glob patterns like "**/*.js" or... 530 chars Read → Grep A powerful search tool built on ripgrep Usage: - ALWAYS use Grep for search tasks. 865 chars Read → KillShell - Kills a running background bash shell by its ID - Takes a shell_id parameter identifying the shell to kill - Returns... 263 chars Read → NotebookEdit Completely replaces the contents of a specific cell in a Jupyter notebook (.ipynb file) with new source. 513 chars Read → Read Reads a file from the local filesystem. 1,752 chars Read → Skill Execute a skill within the main conversation When users ask you to perform tasks, check if any of the available skills... 1,610 chars Read → Task Launch a new agent to handle complex, multi-step tasks autonomously. 6,079 chars Read → TaskOutput - Retrieves output from a running or completed task (background shell, agent, or remote session) - Takes a task_id... 446 chars Read → TodoWrite Use this tool to create and manage a structured task list for your current coding session. 9,701 chars Read → WebFetch - Fetches content from a specified URL and processes it using an AI model - Takes a URL and a prompt as input - Fetches... 1,112 chars Read → WebSearch - Allows Claude to search the web and use the results to inform responses - Provides up-to-date information for current... 1,313 chars Read → Write Writes a file to the local filesystem. 622 chars Read →