Prompt capture

v2.1.288 system prompt

CLI The system prompt of v2.1.288, as Claude Code, interactive mode, seeded with this account's feature flags 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.

This arm was captured with the sandbox seeded from flags-account, this account's own GrowthBook payload, seeded into the sandbox .claude.json. 805 flags from data/flags/snapshots/flags-20261002T183505Z.json. What a seeded capture does and does not tell you.

Released02 Oct 26captured 02 Oct 26

Compared withv2.1.287the previous capture taken the same way

Prompt215 ln27,373 characters

Model strings274 copies of the prompt between them

Tool descriptions30 3 moved this release, 27 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 → 215 lines, 27,373 characters, with a reading view and a copy button

As plain textthe same prompt as a .txt, to download or diff
30 tool descriptionsthe text the model is given for each tool
12 appended blocks118,520 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

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

2 of 30 tool descriptions changed. 1 of 27 tool schemas changed. The appended system-reminder blocks moved: 4 lines added, 1 line removed. Compared against v2.1.287.

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 12 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...

Read, Opus 14 ln 1 of 27 arms +0−1 - This tool can read PDF files (.pdf). For large PDFs (more than 10 pages), you MUST provide the pages parameter to read specific page ranges (e.g., p...

The blocks the client appends after the system prompt moved as well, and this table does not cover them. The appended blocks, and which of them moved →

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 215 ln · 27.4k 15 of 27 3 copies

2 Fable and Mythos, 2 model strings 76 ln · 10.2k 2 of 27 2 copies

3 Opus 5 family, 2 model strings 67 ln · 9.3k 2 of 27 1 copy

4 Opus and Sonnet, 8 model strings 53 ln · 5.9k 8 of 27 2 copies

Tool descriptions

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

All 30 tool descriptions →

ToolDescriptionCopiesMoved

Agent 1,811 chars 2 ○same

AskUserQuestion 1,786 chars 2 ○same

Bash 1,030 chars 3 ◆moved

CronCreate 2,595 chars 1 ○same

CronDelete 100 chars 1 ○same

CronList 60 chars 1 ○same

Edit 360 chars 2 ○same

EndConversation 4,500 chars 1 ○same

EnterPlanMode 4,011 chars 1 ○same

EnterWorktree 3,220 chars 1 ○same

ExitPlanMode 1,849 chars 1 ○same

ExitWorktree 1,923 chars 1 ○same

ListAgents 777 chars 1 ○same

Monitor 6,354 chars 1 ○same

NotebookEdit 619 chars 1 ○same

PushNotification 1,362 chars 1 ○same

Read 790 chars 3 ◆moved

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 378 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