marketing-shibata50/claude-code-ultimate-guide
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

docs: add system prompts official sources (Anthropic + community analyses)

Browse source 
- Add System Prompt Contents section in architecture.md (line 300-326)
  - Official Anthropic sources (Tier 1, 100% confidence)
  - Community analyses (Simon Willison, PromptHub)
  - Claude.ai vs API vs Code CLI distinctions

- Update reference.yaml with 4 new system prompts entries
  - system_prompts_official, willison_analysis, prompthub, architecture

- Create resource evaluation: system-prompts-official-vs-community.md
  - Score evolution: 4/5 → 3/5 → 2/5 (after Perplexity fact-check)
  - Decision: Do not integrate x1xhlol repository (redundant)
  - Use official Anthropic sources instead

- Create watchlist for non-integrated resources
  - claudedocs/resource-evaluations/watch-list.md (gitignored)
  - Re-evaluation triggers: Q2 2026 or if 10+ user requests

Related evaluation: docs/resource-evaluations/system-prompts-official-vs-community.md

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
This commit is contained in:
Florian BRUNIAUX 2026-01-26 17:03:42 +01:00
parent ab8bfcf782
commit 08a2a4261f
4 changed files with 428 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

31
guide/architecture.md
View file

@ -270,6 +270,7 @@ Claude Code operates within a fixed context window (200K tokens for Claude 3.5 S
│ │ • Tool definitions │ │
│ │ • Safety instructions │ │
│ │ • Behavioral guidelines │ │
│ │ • See detailed breakdown below ↓ │ │
│ ├──────────────────────────────────────────────────────┤ │
│ │ CLAUDE.md Files (~1-10K) │ │
│ │ • Global ~/.claude/CLAUDE.md │ │
@ -296,6 +297,36 @@ Claude Code operates within a fixed context window (200K tokens for Claude 3.5 S
└─────────────────────────────────────────────────────────────┘
```
### System Prompt Contents
**Confidence**: 100% (Tier 1 - Official Anthropic Documentation)
**Sources**:
- [Anthropic System Prompts Release Notes](https://platform.claude.com/docs/en/release-notes/system-prompts)
- [Anthropic Engineering: Claude Code Best Practices](https://www.anthropic.com/engineering/claude-code-best-practices)
Claude system prompts (~5-15K tokens) are **publicly published** by Anthropic as part of their transparency commitment. These prompts define:
**Core Components**:
- **Tool definitions**: Bash, Read, Edit, Write, Grep, Glob, Task, TodoWrite
- **Safety instructions**: Content policies, refusal patterns (see [Security Hardening](./security-hardening.md))
- **Behavioral guidelines**: Task-first approach, MVP-first, no over-engineering
- **Context instructions**: How to gather and use project context
**Important Distinctions**:
- **Claude.ai/Mobile**: Published prompts available publicly
- **Anthropic API**: Different default instructions, configurable by developers
- **Claude Code CLI**: Agentic coding assistant with context-gathering behavior
**Community Analysis** (for deeper understanding):
- **Simon Willison's Claude 4 Analysis** (May 2025): [Deep-dive into thinking blocks, search rules, safety guardrails](https://simonwillison.net/2025/May/25/claude-4-system-prompt/)
- **PromptHub Technical Breakdown** (June 2025): [Detailed analysis of prompt engineering patterns](https://www.prompthub.us/blog/an-analysis-of-the-claude-4-system-prompt)
→ **Cross-reference**: For security implications, see [Section 5: Permission & Security Model](#5-permission--security-model)
**Note**: Claude Code system prompts may differ from Claude.ai/mobile versions. The above sources cover the Claude family; Code-specific prompts are integrated into the CLI tool's behavior.
---
### Auto-Compaction
**Confidence**: 50% (Tier 3 - Conflicting reports)