i-have-adhd vs Proto-Mind: Features, Pricing & Which Is Better (2026)
A side-by-side comparison of i-have-adhd and Proto-Mind — features, pricing, and ideal use cases — to help you decide which AI tool fits your workflow.
i
i-have-adhd
ayghri
Coding-agent skill that forces action-first, numbered answers — kills the 'Great question! Let me think...' preamble in Claude Code, Codex, and friends.
Key features
- Action-First Output Rule: Every response leads with the next concrete action instead of preamble.
- Numbered Multi-Step Tasks: Coding tasks come back as numbered lists capped at 5 items each.
- Preamble & Closer Suppression: Eliminates 'Great question!', 'Hope this helps', and other filler.
- Specific Time Estimates: Forces the agent to answer with minutes rather than vague 'a bit' phrasing.
- One-Command Install: /i-have-adhd in Claude Code, $i-have-adhd in Codex, or persistent activation via ~/.claude/.i-have-adhd.
- Auto-Update in Claude Code: Claude Code fetches the skill from GitHub and keeps it up to date — no local clone needed.
- Multi-Language Skill Docs: README available in English, Simplified Chinese, Japanese, Korean, Vietnamese, and Portuguese (BR).
- Fork-and-Tune: Copy skills/i-have-adhd/SKILL.md, edit the 10 rules to taste, restart the agent, and re-invoke.
Best for
- Reduce Preamble Fatigue: Developers who lose time scanning past 'Great question!' openings get straight-to-the-point agent output.
- ADHD-Friendly Workflow: Neurodivergent developers get responses formatted the way their attention can actually consume.
- Terminal-First Sessions: Users driving Claude Code or Codex from a terminal want short, numbered instructions rather than essays.
- Team Style Standard: Teams adopt the skill so every developer's coding agent responds in the same terse format.
- Custom Response Rules: Fork the SKILL.md and hand-tune the 10 rules to fit an internal engineering culture or accessibility need.
Proto-Mind
VIRENCORE
A native macOS floating workspace that keeps AI conversations, project memory, files and live voice together on your Mac.
Key features
- Floating Cube Workspace: Hover the cube to reveal the workspace and click to pin it, or move away to hide it while tasks keep running in the background.
- Per-Conversation Model Routing: Each chat picks its own model and account — ChatGPT with Codex access, supported model APIs, or a local Ollama model.
- Editable Project Memory: Notes, decisions and preferences stay attached to a project and carry into later conversations, and you can review, change or remove any of them.
- Live Voice Control: Speak to open a project, steer a running task or send new work, and add a correction while the task is still going.
- Detachable Companion Windows: Pull out and resize a browser, a file or a second conversation so reference material sits beside the work.
- Explicit Mac Access: Codex can work with files and run commands only after you turn Mac access on; screen control additionally requires Codex Desktop's signed Computer Use helper.
- Local Data Storage: Conversation history and saved memory live on your Mac, and cloud processing happens only when you choose a cloud model or voice.
- Open Source Beta: The macOS installer and the Apache 2.0 source are both published, so the workspace can be inspected and built from source.
Best for
- Long-Running Project Work: Keep a website or client project's decisions in project memory so each session resumes instead of re-explaining the brief.
- Brief to Deliverable: Have the agent read a client brief and save a proposal document, then open it in a companion window next to the conversation.
- Parallel Task Execution: Start several tasks across different models at once and check back on them without blocking the conversation you are in.
- Hands-Free Steering: Dictate a correction or open a project by voice while your hands are busy elsewhere on the Mac.
- Privacy-Sensitive Drafting: Run a local Ollama model so conversation content never leaves the machine.
- Model Comparison: Put the same question to a Codex route and a local model in adjacent windows to compare the answers side by side.