Source Intelligence
Sweep 28 Aug 2026 · 00:00Z Build v2.1.250 478 read Stable v2.1.236 Latest v2.1.250 Next v2.1.251 Feeds RSS JSON llms.txt
Reading a new release v2.1.251 Analysing changes · 2/5 Ordering the sections · 3/4 steps 470 findings $18.91 so far

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

Read tool description

10 model strings share this prompt, byte for byte.

v2.1.236 9 lines 790 chars sha256 80fb15d2d15c Plain text Whole capture

1Reads a file from the local filesystem.
3- `file_path` must be an absolute path.
4- Reads up to 2000 lines by default.
5- When you already know which part of the file you need, only read that part. This can be important for larger files.
6- Results are returned using cat -n format, with line numbers starting at 1
7- Reads images (PNG, JPG, …) and presents them visually. Reads PDFs via the `pages` parameter (e.g. "1-5", max 20 pages/request; required for PDFs over 10 pages). Reads Jupyter notebooks (.ipynb) as cells with outputs.
8- Reading a directory, a missing file, or an empty file returns an error or system reminder rather than content.
9- Do NOT re-read a file you just edited to verify — Edit/Write would have errored if the change failed, and the harness tracks file state for you.