{"data":{"slug":"asgeirtj-system-prompts-leaks","name":"system_prompts_leaks","tagline":"Extracted system prompts from various AI agents and LLMs","github_url":"https://github.com/asgeirtj/system_prompts_leaks","owner":"asgeirtj","repo":"system_prompts_leaks","owner_avatar_url":"https://avatars.githubusercontent.com/u/27446620?v=4","primary_language":"JavaScript","stars":62977,"forks":10337,"topics":["ai","ai-agents","ai-prompts","anthropic","chatbot","chatgpt","claude","claude-code","codex","cursor","gemini","generative-ai","google","grok","llm","openai","prompt","prompt-engineering","system-prompt","system-prompts"],"archived":false,"github_pushed_at":"2026-08-15T03:58:20+00:00","maintenance_label":"Very active","stars_delta_30d":4621,"url":"https://www.graphcanon.com/tools/asgeirtj-system-prompts-leaks","markdown_url":"https://www.graphcanon.com/tools/asgeirtj-system-prompts-leaks.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/asgeirtj-system-prompts-leaks","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=asgeirtj-system-prompts-leaks","description":"Extracted system prompts from Anthropic - Claude Fable 5, Opus 5, Claude Design, Claude Code. OpenAI - ChatGPT GPT-5.6-Sol, Codex. Google - Gemini 3.5 Flash, 3.1 Pro, Antigravity. xAI - Grok, Cursor, Copilot, VS Code, Perplexity, and more. Updated regularly.","homepage_url":null,"license":"CC0-1.0","open_issues":55,"watchers":717,"ai_summary":"Repository containing extracted system prompts for multiple AI agents and large language models (LLMs) including Claude, ChatGPT, Gemini, Grok and more. Updated regularly.","readme_excerpt":"<p align=\"center\">\n  <sub>Thanks to</sub>  \n</p>\n\n<p align=\"center\">\n  <a href=\"https://go.asgeirtj.workers.dev/latitude\">\n    <img src=\"assets/latitude-dark.png\" alt=\"Latitude Logo\" width=\"700\"/>\n  </a>\n</p>\n\n<div align=\"center\" markdown=\"1\">\n\n### [Open Source Agent Analytics](https://go.asgeirtj.workers.dev/latitude)  \n[Understand your agents in production](https://go.asgeirtj.workers.dev/latitude)\n\n</div>\n\n---\n\n> **The Washington Post** built its interactive story on prompts from this repo: [See the hidden rules behind AI. Then use them to rewrite this article.](https://wapo.st/49t4gSb) (May 11, 2026)\n> \n> **CEPS' AI World** built a live data dashboard from this repo's files: [System prompts and what they tell us about the chat before the chat](https://aiworld.eu/story/system-prompts-and-what-they-tell-us-about-the-chat-before-the-chat)  (July 10, 2026)\n# System Prompts Leaks\nLeaked system prompts, captured verbatim — the hidden instructions and rules that ChatGPT, Claude, Gemini, Grok and every other AI chatbot receives before your first message.\n\n<picture>\n  <source media=\"(prefers-color-scheme: dark)\" srcset=\".github/banner-dark.png\">\n  <source media=\"(prefers-color-scheme: light)\" srcset=\".github/banner-light.png\">\n  <img alt=\"ChatGPT leaking its system prompt after being asked to repeat all of the above\" src=\".github/banner-light.png\">\n</picture>\n\n\n\n\n\n\n\n## Recently Updated\n\n| What | Date | Link |\n|------|------|------|\n| **Codex GPT-5.6 (Sol variant)** | July 26, 2026 | [Codex GPT-5.6 system prompt (Terra/Luna)](OpenAI/Codex/gpt-5.6.md) · [Sol](OpenAI/Codex/gpt-5.6-sol.md) |\n| **Grok 4.5** | July 26, 2026 | [Grok 4.5 system prompt](xAI/grok-4.5.md) |\n| **Claude Opus 5** | July 24, 2026 | [Claude Opus 5 system prompt](Anthropic/claude-opus-5.md) · [Claude Code (Opus 5)](Anthropic/Claude%20Code/claude-code-opus-5.md) |\n| **Claude Design (full prompt + 53 tools + 22 skills + 10 starter components)** | July 23, 2026 | [Claude Design system prompt](Anthropic/claude-design.md) · [skills](Anthropic/Claude%20Design/Skills) · [starter components](Anthropic/Claude%20Design/Starter%20components) |\n| **Perplexity** | July 17, 2026 | [Perplexity AI system prompt](Perplexity/perplexity-ai.md) |\n| **Claude Code (new models)** | July 16, 2026 | [Claude Code system prompt (Fable 5)](Anthropic/Claude%20Code/claude-code-fable-5.md) · [Sonnet 5](Anthropic/Claude%20Code/claude-code-sonnet-5.md)  |\n| **OpenCode · Pi · CommandCode** | July 16, 2026 | [OpenCode system prompt](OpenCode/opencode.md) · [Pi system prompt](Pi/instructions.md) · [CommandCode CLI system prompt](Misc/commandcode-cli.md) |\n| **Kimi K2.6** | July 14, 2026 | [Kimi K2.6 system prompt](Kimi/kimi-2.6.md) |\n| **Perplexity Deep Research** | July 14, 2026 | [Perplexity Deep Research system prompt](Perplexity/deep-research.md) |\n| **DeepSeek** | July 14, 2026 | [DeepSeek system prompt](DeepSeek/deepseek-chat.md) |\n| **ChatGPT 5.6** | July 10, 2026 | [ChatGPT 5.6 system prompt (Sol, extra high)](OpenAI/gpt-5.6-sol-extra-high.md) · [Codex GPT-5.6 system prompt](OpenAI/Codex/gpt-5.6.md) |\n\n\n---\n\n\n## Anthropic — Claude system prompts\n\n### Claude.ai system prompts (web, desktop & mobile)\n\n| Model | Prompt |\n|-------|--------|\n| **Claude Fable 5** | [**Claude Fable 5 system prompt**](Anthropic/claude-fable-5.md) |\n| **Claude Opus 5** | [**Claude Opus 5 system prompt**](Anthropic/claude-opus-5.md) |\n| Claude Opus 4.8 | [Claude Opus 4.8 system prompt](Anthropic/claude-opus-4.8.md) |\n| **Claude Sonnet 5** | [**Claude Sonnet 5 system prompt**](Anthropic/claude-sonnet-5.md) |\n| Claude Opus 4.7 | [Claude Opus 4.7 system prompt](Anthropic/claude-opus-4.7.md) |\n| Claude Opus 4.6 | [Claude Opus 4.6 system prompt](Anthropic/claude-opus-4.6.md) · [No tools](Anthropic/claude-opus-4.6-no-tools.md) |\n| Claude Sonnet 4.6 | [Claude Sonnet 4.6 system prompt](Anthropic/claude-sonnet-4.6.md) · [No tools](Anthropic/claude-sonnet-4.6-no-tools.md) |\n| Injected reminders | [Claude.ai injected reminders](A","github_created_at":"2025-05-03T02:43:56+00:00","created_at":"2026-07-07T17:31:13.126541+00:00","updated_at":"2026-08-16T06:02:12.78691+00:00","categories":[{"slug":"ai-agents","name":"AI Agents","url":"https://www.graphcanon.com/categories/ai-agents","markdown_url":"https://www.graphcanon.com/categories/ai-agents.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/ai-agents"},{"slug":"llm-frameworks","name":"LLM Frameworks","url":"https://www.graphcanon.com/categories/llm-frameworks","markdown_url":"https://www.graphcanon.com/categories/llm-frameworks.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/llm-frameworks"}],"tags":[{"slug":"ai-agents","name":"ai-agents"},{"slug":"anthropic","name":"anthropic"},{"slug":"google","name":"google"},{"slug":"llm","name":"llm"},{"slug":"openai","name":"openai"},{"slug":"prompt-engineering","name":"prompt-engineering"},{"slug":"xai","name":"xai"}],"trust":{"provenance":{"is_fork":false,"github_id":976921297,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-08-16T06:02:11.899Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":0,"days_since_push":1,"last_release_at":null,"stars_delta_30d":4621,"open_issues_delta_30d":20},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T10:56:57.359Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-08-16T06:02:12.363Z"},"languages":{"value":["javascript"],"source":"github.language","observed_at":"2026-08-16T06:02:12.363Z"},"license_spdx":{"value":"CC0-1.0","source":"github.license","observed_at":"2026-08-16T06:02:12.363Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["When you need to understand or reverse-engineer the guidelines that certain AI agents or LLMs are operating under for educational purposes.","For individuals who wish to benchmark their own models against publicly disclosed system prompts used by prominent AI services."],"when_not_to_use":["If you are looking for a repository focused on model training data rather than just system prompts, as this tool only contains extracted prompts and not the datasets used for training.","In scenarios where strict confidentiality is required, as using or modifying leaked prompts without authorization might compromise ethical standards or violate usage policies."],"source":"enrich:decision_facts","observed_at":"2026-07-11T12:23:57.891Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"system_prompts_leaks is a repository of extracted system prompts from various AI agents and large language models (LLMs), including Claude, ChatGPT, Gemini, Grok, among others. The repository is maintained in JavaScript,"},{"label":"License detail","value":"The license under which this repository operates (CC0-1.0) allows use, reproduction, and distribution with no attribution required. This means you can integrate the extracted system prompts for any of"}]}}