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

◂ BACK TO LEADERBOARD

FINDING #3920 · 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

SURPRISE0.00309

ENGAGEMENT0.40

FRESHNESS1.00

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

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

0% OF STARS IN ARCHIVE

Growth Telemetry

VELOCITY /D

76.00

ACCEL

-19.50

RETENTION

73.9%

PEAK 2026-08-27 · FORK-RETENTION 53.6% · 228 STARS / WINDOW

Author Audience

AUDIENCE

24,558

FOLLOWERS

3,706

OWNER ★

85,848

Engagement Signals

FORKS

12,194

ISSUE AUTH

PR AUTH

UNIQUE STARGAZERS 228 / 228 (DIVERSITY 1.00)

Why This Is A Finding

shareAI-lab/learn-claude-code собрал 228 звёзд за окно, тогда как у автора всего 3,706 подписчиков — эффективная аудитория ≈ 24,558. Это даёт surprise-индекс 0.00309 (звёзды относительно охвата автора, а не в абсолюте). Удержание форков 53.6% и 0 внешних контрибьюторов отделяют реальный инструмент от разовой вспышки. Акселерация отрицательная — внимание остывает после пика.

Related Findings

RANKS ABOVE 57% OF 9102 FINDINGS

#08User0332/rewards-farmer[ PYTHON ]0.75 #09wang2122/sprix-sage-router[ PYTHON ]0.62 #16amagine-ai/Amagine3D[ PYTHON ]0.50 #19framepipe-dev/media-inference-worker[ PYTHON ]0.47 #24zeenie-ai/OpenCompany[ PYTHON ]0.44

METRICS IN CONTEXT

MEDIAN ACROSS ALL 9102 FINDINGS · Δ vs MEDIAN · PERCENTILE = SHARE RANKED BELOW

METRICVALUEMEDIANΔ MEDPERCENTILE

SCORE0.000.00+0.00ABOVE 57%

VELOCITY76.005.67+70.33ABOVE 97%

RETENTION73.9%45.5%+28.5 PPABOVE 80%

FORKS12,194340+11,855ABOVE 98%

SURPRISE0.000.00-0.00ABOVE 45%