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 Writing the entries · 2/4 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

SendMessage tool description

27 model strings share this prompt, byte for byte.

v2.1.216 14 lines 778 chars sha256 8c304bf84620 Plain text Whole capture

1# SendMessage
3Send a message to another agent.
5```json
6{"to": "researcher", "summary": "assign task 1", "message": "start on task #1"}
7```
9| `to` | |
10|---|---|
11| `"researcher"` | Teammate by name |
12| `"main"` | The main conversation (background subagents only) |
14Your plain text output is NOT visible to other agents — to communicate, you MUST call this tool. Messages from teammates are delivered automatically; you don't check an inbox. Refer to agents by name — names keep working after an agent completes (a send resumes it from its transcript). Use the raw `agentId` (format `a...-...`) from its spawn result only when the agent has no name, or when a newer agent took the name (latest wins). When relaying, don't quote the original — it's already rendered to the user.