Practical patterns, starters & CLI tools for loop engineering with AI coding agents. Design systems that prompt and orchestrate agents (inspired by Addy Osmani and Boris Cherny). Includes loop-audit, loop-init, loop-cost.
cobusgreyling/loop-engineering is drawing steady momentum at +6.7 stars/day (63rd percentile in the tracked cohort), for a momentum score of 42.6/100. Forks are climbing too, at +1.1/day.
Low breakout odds over the next 14 days, led by push recency (99th pctl) and star velocity (63th pctl). Confidence is high given the available history.
Reconstructed from 257 snapshots — the time-series GitHub’s API doesn’t expose.
~58 forks/day, 3.6× the trailing baseline.
~61 forks/day, 7.0× the trailing baseline.
~22 forks/day, 4.0× the trailing baseline.
Live score, refreshed every 6 hours. Links back to this page.
[](https://repoclimb.com/repo/cobusgreyling/loop-engineering)Transparent heuristic · logged for model training
Percentile rank within the tracked cohort. The score self-calibrates — it answers “accelerating vs. everything else,” not raw size.
~10 forks/day, 3.4× the trailing baseline.
~10 forks/day, 4.2× the trailing baseline.
~14 forks/day, 4.2× the trailing baseline.
~10 forks/day, 4.1× the trailing baseline.
~11 forks/day, 4.4× the trailing baseline.
~11 forks/day, 9.9× the trailing baseline.
~20 forks/day, 6.8× the trailing baseline.
~20 forks/day, 5.7× the trailing baseline.
~23 forks/day, 5.5× the trailing baseline.