home/roleplay/system-prompt-87

System Prompt

GPTClaudeGemini··▲ 1,078 copies·updated 2026-07-14

system-prompt-87.prompt

# System Prompts

> This mode sent **10 requests total**: 6 main opus + 2 security-monitor opus + 2 overhead haiku. The main system prompt below was identical across all 6 main opus requests — only the billing header hash varied per request. The security-monitor and haiku roles use distinct system prompts.

## Main Prompt — claude-opus-4-7 (1M context) | has tools

**Words:** 4,332 | **Characters:** 27,744 | **Lines:** 238

The main system prompt is sent as **4 separate content blocks** so different sections can cache independently:

| Block | Length | Purpose |
|-------|--------|---------|
| 0 | 81 chars | `x-anthropic-billing-header` (per-request hash, breaks cache) |
| 1 | 57 chars | Identity: *"You are Claude Code, Anthropic's official CLI for Claude."* |
| 2 | 9,925 chars | Core behavioral instructions (System / Doing tasks / Executing actions / Using tools / Tone) |
| 3 | 17,678 chars | Text output guidance + System reminders + Session-specific guidance + Auto memory + Environment + gitStatus |

when to use it

Community prompt sourced from the open-source GitHub repo agenticloops-ai/agentic-apps-internals (no explicit license). A "System Prompt" style prompt — adapt the placeholders and specifics to your task. Imported as-is and not independently retested here, so check the output before relying on it.