The agent's answer order just became configurable. the i-have-adhd skill, trending on github since…
the agent's answer order just became configurable. the i-have-adhd skill, trending on github since september 17, rewrites claude code's replies to lead with the answer, number the steps and end with one concrete next action.
the fix is a plain-text rule file.
Context
The i-have-adhd repository by ayghri, MIT licensed and created on 2026-05-13, describes itself as a skill to stop your coding agent from burying the answer. Its README lists 10 rules, including lead with the next action, number multi-step tasks, end with one concrete next step, suppress tangents, cap lists at 5, and no preamble, recap or closers. It is a prose rule file with plugin manifests that users can fork and edit, and the README says it is loosely based on The Adult ADHD Tool Kit and that no ADHD diagnosis is needed. The Trendshift tracker shows it first reached number one on GitHub Trending on September 8, 2026.
The skill instructs the model to format replies this way and does not rewrite output after the fact, and how closely models follow it was not read. The README lists Claude Code and secondary articles add Codex and Cursor, so Claude Code only is narrower than the sources. Trending since September 17 is not supported, as Trendshift shows September 8 and a September 14 article already calls it weekly-trending, which does not disprove trending since September 17 unless a start date was meant. Star counts differ by tracker and date and were not reconciled. No clinical benefit or measured outcome was read, and the name and framing are the author's.
Watch next
- Evidence on how models follow the rules.
Sources
- ayghri/i-have-adhd on GitHubgithub.com
- Trendshift: i-have-adhdtrendshift.io
- Oflight: i-have-adhd and agent skills (September 14, 2026)oflight.co.jp
Provenance
The note above is reproduced unedited from the original post, first published on Threads on 22 September 2026 at 11:01 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 →