A repo called ponytail passed 120,000 stars by teaching ai agents to think like the laziest senior…
a repo called ponytail passed 120,000 stars by teaching ai agents to think like the laziest senior dev in the room, preferring the simplest fix and the least code. the most viral coding idea of september is not a new model, it is permission to do less.
over-engineering finally met its match in a personality trait.
Context
The dietrichgebert/ponytail repository describes itself as making your AI agent think like the laziest senior dev in the room, with the line the best code is the code you never wrote. It is MIT licensed, was created 12 June 2026, and is tagged agent-skills. Its page showed 120,236 stars as fetched. Its README reports about 54% less code on average across 12 feature tasks with Haiku 4.5 (n=4), up to 94% on one task, against a no-skill baseline in a FastAPI plus React repository.
The star count is current with no capture date, so it shows the repository is above 120,000 now, not when it passed 120,000 or that this happened in September. A second snapshot of a differently cased URL showed 111,828 stars, undated. A dev.to post of 25 June 2026 says about 44,000 stars in under 9 days, a different interval and a secondary source. The most viral coding idea of September has no dated interval evidence, and the repository was created in June. It is a skill for agents, not a model. The code-reduction measurement is maker-reported, small and not independent. Over-engineering finally met its match is the author's opinion.
Related work
- Ponytail: the AI coding skill taking GitHub by storm (dev.to, 25 Jun 2026) ↗Secondary, snippet only.
- Hacker News thread ↗Undated, snippet only.
Watch next
- A dated star history and independent evaluations.
Sources
- dietrichgebert/ponytail (GitHub)github.com
Provenance
The note above is reproduced unedited from the original post, first published on Threads on 18 September 2026 at 18:37 IST. Sources are the papers and datasets the note draws on.
View the original post ↗Embed this note
More notes
The air is now being asked to keep its own ledger
the air is now being asked to keep its own ledger: ecmwf’s aifs compo becomes the first ai model to forecast atmospheric composition globally every three hours, cleanair simulates 365 days of pm2.5 over china in ten seconds, and a unified framework maps six pollutants at one kilometer across the whole country. the air now files its own composition report.
read the note →The current is now being asked to draw its own map
the current is now being asked to draw its own map: china’s langya 2.0 predicts six ocean phenomena including internal waves and mesoscale eddies, a deep net called wenhai resolves eddies globally with air sea flux formulas built in, and scripps infers surface currents from the way temperature patterns deform in satellite images. the ocean now files its own circulation report.
read the note →The soil is now being asked to report its own carbon
the soil is now being asked to report its own carbon: a nix color sensor paired with generative data augmentation predicts soil organic carbon without a lab, random forest drives 74 percent of soil health mapping studies, and sentinel 2 tracks five year carbon change across france and italy from 922 samples. the dirt now files its own carbon account.
read the note →