shareAI-lab/learn-claude-code — GitHub trend

◂ BACK TO LEADERBOARD

FINDING #5153 · UNIT ID 1010681419

shareAI-lab/learn-claude-code

Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1

[ PYTHON ][ ORG ][ GITHUB ↗ ]

SURPRISE SCORE

0.00

Score Breakdown

SURPRISE0.00381

ENGAGEMENT0.43

FRESHNESS1.00

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

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

1% OF STARS IN ARCHIVE

Growth Telemetry

VELOCITY /D

93.71

ACCEL

-6.00

RETENTION

50.3%

PEAK 2026-08-25 · FORK-RETENTION 43.0% · 656 STARS / WINDOW

Author Audience

AUDIENCE

24,558

FOLLOWERS

3,706

OWNER ★

85,848

Engagement Signals

FORKS

12,194

ISSUE AUTH

PR AUTH

UNIQUE STARGAZERS 656 / 656 (DIVERSITY 1.00)

Why This Is A Finding

shareAI-lab/learn-claude-code собрал 656 звёзд за окно, тогда как у автора всего 3,706 подписчиков — эффективная аудитория ≈ 24,558. Это даёт surprise-индекс 0.00381 (звёзды относительно охвата автора, а не в абсолюте). Удержание форков 43.0% и 0 внешних контрибьюторов отделяют реальный инструмент от разовой вспышки. Акселерация отрицательная — внимание остывает после пика.

Related Findings

RANKS ABOVE 47% OF 9771 FINDINGS

#05MddIdd/mdd-sim-gateway[ PYTHON ]0.41 #08zeenie-ai/OpenCompany[ PYTHON ]0.38 #15litaolemo/xtquant_big_convert[ PYTHON ]0.33 #23917Dhj/DeepPaperNote[ PYTHON ]0.27 #24LBH-123-AI/Comfyui_Minimax_h3_latent_Upscaler[ PYTHON ]0.27

METRICS IN CONTEXT

MEDIAN ACROSS ALL 9771 FINDINGS · Δ vs MEDIAN · PERCENTILE = SHARE RANKED BELOW

METRICVALUEMEDIANΔ MEDPERCENTILE

SCORE0.000.00-0.00ABOVE 47%

VELOCITY93.713.71+90.00ABOVE 98%

RETENTION50.3%39.3%+11.0 PPABOVE 69%

FORKS12,19491+12,103ABOVE 100%

SURPRISE0.000.01-0.01ABOVE 29%