asgeirtj/system_prompts_leaks — GitHub trend

FINDING #254 · UNIT ID 976921297

asgeirtj/system_prompts_leaks

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.

[ PYTHON ][ GITHUB ↗ ]

SURPRISE SCORE

0.00

Score Breakdown

SURPRISE0.000777

ENGAGEMENT1.17

FRESHNESS1.38

SCORE = SURPRISE × ENGAGEMENT^0.7 × FRESHNESS × VISIBILITY × CONFIDENCE

SURPRISE = WINDOW STARS / DAYS / (AUDIENCE + FLOOR)

0% OF STARS IN ARCHIVE

Growth Telemetry

VELOCITY /D

7.20

ACCEL

-0.93

RETENTION

3.5%

PEAK 2026-09-13 · FORK-RETENTION 60.0% · 216 STARS / WINDOW

Author Audience

AUDIENCE

9,225

FOLLOWERS

2,272

OWNER ★

69,532

Engagement Signals

FORKS

11,301

ISSUE AUTH

PR AUTH

UNIQUE STARGAZERS 216 / 216 (DIVERSITY 1.00)

Why This Is A Finding

asgeirtj/system_prompts_leaks собрал 216 звёзд за окно, тогда как у автора всего 2,272 подписчиков — эффективная аудитория ≈ 9,225. Это даёт surprise-индекс 0.000777 (звёзды относительно охвата автора, а не в абсолюте). Удержание форков 60.0% и 2 внешних контрибьюторов отделяют реальный инструмент от разовой вспышки. Акселерация отрицательная — внимание остывает после пика.

Related Findings

RANKS ABOVE 62% OF 663 FINDINGS

#05rehan-remade/universal-modder[ PYTHON ]0.0201 #06arnegiacomo/fugleramme[ PYTHON ]0.0196 #16debpalash/VoiceStudio[ PYTHON ]0.0133 #38NandhaKishorM/laya[ PYTHON ]0.00998 #44firelex/jeff[ PYTHON ]0.00935

METRICS IN CONTEXT

MEDIAN ACROSS ALL 663 FINDINGS · Δ vs MEDIAN · PERCENTILE = SHARE RANKED BELOW

METRICVALUEMEDIANΔ MEDPERCENTILE

SCORE0.000.00+0.00ABOVE 62%

VELOCITY7.202.77+4.43ABOVE 86%

RETENTION3.5%11.1%-7.6 PPABOVE 14%

FORKS11,3011,805+9,496ABOVE 85%

SURPRISE0.000.00+0.00ABOVE 56%