OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Coding Agents

Adhd

Adhd is a TypeScript skill for coding agents that generates parallel ideas under different cognitive frames, then scores, clusters and prunes them before developing selected candidates. The project describes it as built on the Claude and Codex Agent SDKs and licenses it under MIT.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Adhd — OpenViST project profile in Coding Agents.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when a coding-agent task is open-ended and exploring several distinct approaches could help, rather than when the task calls for a single direct answer.

Who it is for

  • People using coding agents for design decisions, fuzzy debugging, naming, API design or strategy.
  • Agent-skill developers exploring parallel ideation and thought-pruning approaches.

Documented uses

  • Generate varied candidate approaches to an open-ended problem.
  • Review candidate thoughts for quality and traps, then narrow and develop selected ideas.
Before you choose

Requirements & limits

The repository is public and MIT-licensed. It describes the skill as built on the Claude and Codex Agent SDKs.

  • The method separates parallel idea generation from a later critic pass that scores, clusters and prunes candidates.
  • Its use depends on a coding-agent workflow; it is not presented as a standalone application.
  • The documented target use cases are open-ended reasoning tasks, including design, debugging, naming, API design and strategy.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Generate and render a set of divergent ideas with the TypeScript API

Run ADHD on a problem using parallel cognitive frames and render the resulting ideas as text.

Before you start

  • Node.js 18 or later, as indicated by the repository README.
  • The adhd-agent package and an environment where its agent calls can run; installation and agent configuration details are not included in the provided documentation.

Steps

  1. Import run and renderText from adhd-agent.

  2. Call run with a problem and options such as framesPerRun and topK.

  3. Pass the result to renderText and print the returned text.

Expected outcome

Text output for the problem, with result fields including a shortlist, non-obvious pick, traps, deepened ideas, and clusters.

Guide limitations

  • The README gives an API usage example but does not document package installation, agent credentials/configuration, or error handling here.
  • The resulting ideas and scores are generated by agent calls; no particular quality or successful execution is guaranteed.
Documentation 1 ↗
COMPARE OPTIONS

Compare options for AI coding assistance

These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.

ProjectDocumented purposePlatformAccess and requirements
AdhdGenerate varied candidate approaches to an open-ended problem.The repository is public and MIT-licensed. It describes the skill as built on the Claude and Codex Agent SDKs.
SpectraClarify requirements and compare approaches before proposing a change.CLI, DesktopThe README lists a macOS and Windows desktop app, and a Homebrew installation for macOS. The CLI is published through npm and requires Node.js 22.14 or newer.
Skills — michaelshimelesInstall reusable task-specific skills into a coding-agent setup.CLIThe repository README provides an npx installation command for most coding agents and describes automatic or explicit skill invocation in Claude Code.
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
7 October 2026
Original website title
UditAkhourii/adhd · Official homepage title · retained in its source language
How we review sourcesSuggest a correction