# UditAkhourii/adhd

ADHD — a skill for coding agents. Tree-of-thought with pruning, built on the Claude & Codex Agent SDK. Fans out parallel divergent thoughts under different cognitive frames, scores, prunes traps, deepens the survivors. The no-brainer skill for creative and interdisciplinary work.

Repository: https://github.com/UditAkhourii/adhd
Canonical: https://ross.abutalabs.com/products/adhd
Homepage: https://divergent.sh
Language: TypeScript
License: MIT
License Family: permissive
Topics: adhd, agents, ai, ai-agents, brainstorm, chain-of-thought, claude, claude-agent-sdk, creativity, divergent-thinking, ideation, interdisciplinary, llm, llm-tools, nodejs, prompt-engineering, tree-of-thought, typescript
Last push: 2026-08-23T12:38:43+00:00

## Health v2 (maintenance only)
Score: 65/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 54, longevity 7
- inputs: {"age_days": 100, "days_push": 10, "days_rel": 95, "gap_med": null, "n_releases_24m": 1}
- flags: young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3953, forks 270 (observed 2026-08-28T04:08:30.410096+00:00)

## What it is
ADHD is a TypeScript skill for coding agents built on the Claude and Codex Agent SDKs that implements parallel divergent ideation via tree-of-thought with pruning. It spawns isolated reasoning processes under different cognitive frames, then scores, prunes, and deepens the surviving branches to counter premature convergence.

## Use cases
- explore multiple design approaches before committing to one
- brainstorm naming options for an API or library
- debug a fuzzy problem from several angles at once
- design an API surface with divergent alternatives
- generate strategy options for an architectural decision
- get several ways to solve an open-ended problem

## When to choose
- you use Claude Code or Codex agents and want better reasoning on open-ended design or ideation tasks
- linear chain-of-thought keeps anchoring on the first plausible answer
- you want a drop-in agent skill for divergent exploration with pruning

## When to avoid
- you need deterministic, single-answer reasoning with minimal token cost
- your project does not use Claude or Codex agent SDKs
- you need a general-purpose agent framework rather than an ideation skill

## Facets
- artifact type: library
- maturity: active
- function: agent-framework, prompt-engineering, llm-inference, nlp
- domain: artificial-intelligence, large-language-models, developer-tools
- platform: cli, cross-platform
- tags: tree-of-thought, divergent-thinking, claude-agent-sdk, codex-agent-sdk, ideation, brainstorming, reasoning, agent-skill, ai-agents, nodejs

## Member repositories
- UditAkhourii/adhd (main) score 65

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:30.410096+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:24:30.792027+00:00, confidence not recorded.
  - readme: https://github.com/UditAkhourii/adhd (fetched 2026-08-28T04:08:30.410096+00:00, sha 9f9850f77529)
  - homepage: https://divergent.sh (fetched 2026-08-29T09:18:16.440522+00:00, sha d547862a977c)
- Data as of 2026-08-30T08:39:29.467469+00:00.