An output style for your coding agent: the next action first, numbered steps, no preamble and no tangents. No ADHD diagnosis needed.
by ayghri· WritingUnclaimed · Yours? Claim it
4 images
About
i-have-adhd is an open-source output-style skill by ayghri that stops your coding agent from burying the answer. Its replies lead with the next action, number the steps and end with one concrete thing to do. The maker calls it ADHD-friendly output and says no diagnosis is needed: it's a way of writing replies for anyone who wants answers they can act on. What changes in the replies - The first line is the action: a command, a path or a snippet, with any prose after it - Multi-step work comes as a numbered list, one bounded action per step - Each reply ends with one next step you can do in under two minutes - Tangents wait: it finishes the current issue, then offers the next one as a separate question - Progress is restated each turn ("Step 3 of 5 done"), time estimates come in minutes or hours, and finished work is made visible - Errors are matter-of-fact, lists stop at five items, and there's no preamble, recap or "Hope this helps!" How it works - Turn it on with /i-have-adhd. It stays on for the rest of the session until you say "stop adhd mode" or "normal mode". - In Claude Code it installs as a plugin from the maker's own marketplace (ayghri/i-have-adhd). An optional always-on mode loads the rules at the start of every session once you create a flag file; installing the plugin changes nothing by itself. - It also installs as a Gemini CLI extension, and the maker's install guide covers Codex, Cursor, GitHub Copilot and more. Good to know - It still explains in full when you ask it to explain, confirms before destructive actions, and asks one short question when a request is ambiguous. - Fork it and edit the rules in skills/i-have-adhd/SKILL.md to tune them. - The rules are loosely based on The Adult ADHD Tool Kit by J. Russell Ramsay and Anthony L. Rostain, adapted for how an AI model should write its replies. It's a writing style, not a health tool. - MIT licensed. A community project by ayghri.
Once it’s added
“/i-have-adhd, then: why is my auth test failing?”
“Explain how to create an empty Git repository in a new folder”
“Walk me through upgrading jsonwebtoken, one step at a time”
“How long will this migration take?”
“Where are we on the refactor?”
“stop adhd mode”
Each with its own page
From people who use it
Step by step
Nothing new reaches your agent until a person has looked at it.
Plugins people install alongside i-have-adhd.
No reviews yet. Used i-have-adhd? Say how it went.
Write a reviewRuns on your machine.
Runs on your machine.
/plugin marketplace add ayghri/i-have-adhd /plugin install i-have-adhd@i-have-adhd
Runs on your machine.
gemini extensions install https://github.com/ayghri/i-have-adhd
Scanned and passed · checked 46 min ago
Scanned on every change, and again when our rules improve.
Claude CodeSupported
Gemini CLISupportedTell us and a person on the trust team will look at it. Or email [email protected].
Nobody has shared how they use i-have-adhd yet.
Security scan
Passed
Safe to install in every agent it supports. Claude plugins, Extensions.
Plugins people install alongside i-have-adhd.
Ask a hard question and get a readable one-page answer with diagrams, tables and code, instead of a wall of text.
A Claude Code blog engine: strategy, briefs, writing, rewrites, SEO and AI-citation audits, translation and refreshes, gated for quality.
Mintlify's Claude plugin: a skill for building Mintlify docs (components, docs.json, navigation, API pages) plus its docs search server.
