Skip to content
Tech wire
OpenAI bots meddled with US government agencies, including SEC and CensusBBCOCUDU Ecosystem Foundation Welcomes GNU Radio to Accelerate Open Source Wireless InnovationLinux FoundationOpen source tech helps farmers put more trust in digital toolsCyprus MailAI Is reshaping open source software and straining the systems that sustain itEurekAlert! Science News ReleasesOpen-source coding platform makes radar technology accessible to scientists worldwidecolorado.eduArthur Mensch, CEO of French start-up Mistral AI: 'AI is software. It can be controlled'Le Monde.frThe Open-Source Debt Nobody in Finance Wants to Talk AboutHackerNoonThe 10 Coolest Open-Source Software Tools Of 2026 (So Far)crn.comArticle | Nvidia, tech giants back open-source AI tools after Hugging Face breach jolts WashingtonPOLITICO ProNIST Updates 5G Open-Source Testbed ToolsNational Institute of Standards and Technology (.gov)Compare Top 21 Manufacturing AI Solutions & SoftwareAIMultipleNVIDIA Releases Major Collection of Open Source Agent Tools and Skills for Physical AInvidianews.nvidia.comMicrosoft Releases Open Source AI Safety Tools for Agent DevelopmentCampus TechnologyAsserting American Leadership in Open Source AIAndreessen Horowitz

asgeirtj/system_prompts_leaks

Establishedrank #61

Documented system prompts from Anthropic - Claude Fable 5.1, Opus 5.5, Claude Design, Claude Code. OpenAI - ChatGPT GPT-6-Astra, Codex. Google - Gemini 3.8 Flash, 3.1 Pro, Antigravity. xAI - Grok, Grok Bot, Cursor, Kimi and more! Updated regularly.

68.4k+1.2k · 7d 11.1k 372est. CC0-1.0JavaScriptpushed 3h ago
Compare View on GitHub

Composite

74

conf 65%

Momentum

66

conf 60%

Vitality (PVI)

74

conf 67%

Community

63

conf 60%

Security & maint.

95

conf 85%

Ecosystem influence

77

conf 60%

Opportunity

62

conf 60%

Breakout · 7d

33%

conf 71%

Executive summary

system_prompts_leaks is currently classified as established with a composite score of 74/100. Momentum (66) and vitality (74) are aligned — growth is backed by sustained maintenance. Estimated 7-day gain of 1,222 stars against a 68.4k-star base. Risk is assessed as low; the interpretable model puts its probability of entering the top trend cohort within 7 days at 33%.

90-day trajectory

+6.5k · 30d
2026-06-302026-09-27

Score breakdown

Every input, weight and normalized value — nothing hidden. Inputs marked est. are estimated until the full ingestion pipeline lands.

Momentum

Star velocityest.25%86
Star accelerationest.15%40
Fork velocityest.10%84
Contributor growthest.10%95
Issue activity growthest.10%43
PR activity growthest.10%69
External mention velocityest.10%16
Release event impactest.5%72
Trending-rank persistenceest.5%80

Model tn-interpretable-1.0.0 · confidence 60% · coverage 100%

Project Vitality Index

Commit consistency20%100
Release cadenceest.15%56
PR responsivenessest.15%65
Issue responsivenessest.15%59
Contributor diversityest.10%95
Maintainer continuityest.10%81
Documentation qualityest.5%70
Dependency freshnessest.5%51
Security hygieneest.5%73

Model tn-interpretable-1.0.0 · confidence 67% · coverage 100%

Security & maintenance

Release recency25%100
License clarity20%92
Maintenance status25%100
Dependency stalenessest.15%88
Bus factorest.15%91

Model tn-interpretable-1.0.0 · confidence 85% · coverage 100%

Ecosystem influence

Dependent repositoriesest.30%97
Quality-weighted dependentsest.20%86
Documentation citationsest.15%70
Contributor overlapest.15%26
Registry adoptionest.10%61
Topic centralityest.10%100

Model tn-interpretable-1.0.0 · confidence 60% · coverage 92% · missing: packageRegistryAdoption