# elder-plinius/CL4R1T4S

LEAKED SYSTEM PROMPTS FOR CHATGPT, CLAUDE, GEMINI, GROK, PERPLEXITY, CURSOR, LOVABLE, REPLIT, AND MORE! - AI SYSTEMS TRANSPARENCY FOR ALL! 👐

Repository: https://github.com/elder-plinius/CL4R1T4S
Canonical: https://ross.abutalabs.com/products/cl4r1t4s
License: AGPL-3.0
License Family: copyleft
Topics: ai, chatgpt, gemini, google, grok, leak, openai, system-info, system-prompts, tools, transparency, prompt-engineering, red-team, red-teaming, agents, prompts, leaked, prompt, system, hacking
Last push: 2026-08-15T02:33:56+00:00

## Health v2 (maintenance only)
Score: 64/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 97, release rhythm 35, longevity 39
- inputs: {"age_days": 547, "days_push": 19, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 47163, forks 9552 (observed 2026-08-28T04:12:11.184337+00:00)

## What it is
A curated collection of extracted and leaked system prompts, guidelines, and tool definitions from major AI systems such as ChatGPT, Claude, Gemini, Grok, Perplexity, Cursor, Devin, and Replit. It serves as a transparency and research reference showing how AI vendors shape model behavior through hidden prompt scaffolds.

## Use cases
- study how AI vendors write system prompts
- research prompt engineering patterns used by major AI products
- red-team and security analysis of LLM behavior
- compare refusal and persona instructions across AI assistants
- build better system prompts by learning from production examples
- audit what ethical and political framing is baked into AI systems

## When to choose
- you need real-world examples of production system prompts for research or prompt engineering
- you are doing AI transparency, red-teaming, or security research
- you want to compare how different AI vendors constrain and steer their models

## When to avoid
- you need a tool or library to execute prompts rather than a reference corpus
- you require legally sanctioned or officially documented prompt specifications
- you want stable, versioned content - leaked prompts change without notice and may be outdated

## Facets
- artifact type: dataset
- maturity: active
- function: prompt-engineering, security, developer-tools
- domain: artificial-intelligence, large-language-models, security, chatbots, developer-tools
- platform: cross-platform
- tags: leaked-system-prompts, ai-transparency, red-teaming, prompt-collection, llm-behavior, reference-corpus, ai-agents

## Member repositories
- elder-plinius/CL4R1T4S (main) score 64

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:12:11.184337+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:21:10.280524+00:00, confidence not recorded.
  - readme: https://github.com/elder-plinius/CL4R1T4S (fetched 2026-08-28T04:12:11.184337+00:00, sha 1edb40f231dd)
- Data as of 2026-08-30T08:39:29.467469+00:00.