Prompt capture

v2.1.292 system prompt

SDK-CLI The system prompt of v2.1.292, as Agent SDK, print mode sent it to the model, read out of the request it put on the wire. The text comes first; what changed since the previous capture is further down, kept apart from it.

Released06 Oct 26captured 06 Oct 26

Compared withv2.1.291the previous capture taken the same way

Prompt218 ln27,201 characters

Model strings274 copies of the prompt between them

Tool descriptions24 2 moved this release, 23 with a parameter schema

Captured 6 ways. Each is a separate prompt with its own history, and a change is only ever measured against the previous capture taken the same way, never across these.

Default settings

Claude Code, interactive mode Agent SDK, print mode

a clean sandbox with no stored flags, as a fresh install runs

Seeded with feature flags

Claude Code, interactive mode, seeded with this account's feature flags Claude Code, interactive mode, seeded with anonymous feature flags Agent SDK, print mode, seeded with this account's feature flags Agent SDK, print mode, seeded with anonymous feature flags

the same client started with a stored set of feature flags on, so it can send text a default install does not. What that tells you

Read it The whole system prompt → 218 lines, 27,201 characters, with a reading view and a copy button

As plain textthe same prompt as a .txt, to download or diff
24 tool descriptionsthe text the model is given for each tool
12 appended blocks106,508 more characters the client sends after the system prompt
4 copies by modelthe prompt is not one text; which models get which copy
18 prompts in this releasecompaction, subagents, reminders: each its own request

What changed since the previous capture

2 One line per document that moved, the system prompt and the tool descriptions in the same table.

1 of 24 tool descriptions changed. 2 of 23 tool schemas changed. Compared against v2.1.291.

PromptReachMovedThe first line that changed

Bash 113 ln 15 of 27 arms +1−1 - You can use the `run_in_background` parameter to run the command in the background. Only use this if you don't need the result immediately and are...

Bash 13 ln, and 1 other copy of it moved the same way 12 of 27 arms +1−1 - `run_in_background` runs the command detached: it keeps running across turns and re-invokes you when it exits. With it, `timeout` is how long the co...

The prompt by model

4 The client does not send one system prompt: each model gets its own copy with its name and a few lines worked in. A row is one copy and how many of the 27 model strings get it, most first. Every copy opens with the same line: You are an interactive agent that helps users with software engineering tasks.

#CopyLengthSent toDocuments

1 Haiku, Sonnet and Opus, 15 model strings 218 ln · 27.2k 15 of 27 3 copies

2 Fable and Mythos, 2 model strings 78 ln · 9.9k 2 of 27 2 copies

3 Opus 5 family, 2 model strings 69 ln · 9k 2 of 27 1 copy

4 Opus and Sonnet, 8 model strings 55 ln · 5.6k 8 of 27 2 copies

Tool descriptions

24 The text the model is given for each tool, on this arm.

All 24 tool descriptions →

ToolDescriptionCopiesMoved

Agent 1,668 chars 3 ○same

Bash 1,096 chars 3 ◆moved

CronCreate 2,924 chars 1 ○same

CronDelete 167 chars 1 ○same

CronList 106 chars 1 ○same

Edit 360 chars 2 ○same

EnterWorktree 3,220 chars 1 ○same

ExitWorktree 1,923 chars 1 ○same

ListAgents 777 chars 1 ○same

NotebookEdit 619 chars 1 ○same

Read 790 chars 3 ○same

ReportFindings 574 chars 1 ○same

ScheduleWakeup 3,396 chars 1 ○same

SendMessage 4,259 chars 1 ○same

Skill 1,417 chars 1 ○same

TaskCreate 2,146 chars 1 ○same

TaskGet 732 chars 1 ○same

TaskList 998 chars 1 ○same

TaskStop 364 chars 1 ○same

TaskUpdate 2,243 chars 1 ○same

WebFetch 469 chars 2 ○same

WebSearch 334 chars 2 ○same

Workflow 3,480 chars 1 ○same

Write 240 chars 2 ○same