adhd is a skill AI agent for Enable AI coding assistants to explore multiple code paths in parallel and prune poor options to arrive at better solutions. Pricing: Not specified. As of 2026-10-27, KanonAgent records 2.4k upvotes. First indexed by KanonAgent on 2026-07-28.
An ADHD skill for coding agents that uses tree-of-thought with pruning to enhance creativity and accuracy in code generation.
2.4k upvotes
Tracked by Kanon since Jul 28, 2026
Status basis: npm_downloads_7d gained 6 in the last 3d after a flat 3d baseline (no prior movement to compare a ratio against)
📈 Timelinewhat changed, and when
- Accelerating npm_downloads_7d gained 6 in the last 3d after a flat 3d baseline (no prior movement to compare a ratio against)
- Cooling npm_downloads_7d momentum fell to 7 per 3d from 18 (<= 40% of the prior window)
- Accelerating npm_downloads_7d gained 7 in the last 3d after a flat 3d baseline (no prior movement to compare a ratio against)
- Cooling npm_downloads_7d momentum fell to 1 per 3d from 18 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to 0 per 3d from 16 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to 0 per 3d from 16 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to -8 per 3d from 20 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to -6 per 3d from 25 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to -4 per 3d from 31 (<= 40% of the prior window)
- Accelerating npm_downloads_7d gained 20 in the last 3d vs 7 in the 3d before (ratio 2.9x, threshold 1.5x)
- Cooling npm_downloads_7d momentum fell to -4 per 3d from 31 (<= 40% of the prior window)
- Accelerating npm_downloads_7d gained 25 in the last 3d after a flat 3d baseline (no prior movement to compare a ratio against)
- Anomaly daily change 24.0 is 4.6 standard deviations from this entity's own prior mean (-0.7±5.4, baseline excludes this point) — unusual, not necessarily adoption
- Anomaly daily change 24.0 is 4.6 standard deviations from this entity's own prior mean (-0.7±5.4, baseline excludes this point) — unusual, not necessarily adoption
- Cooling npm_downloads_7d momentum fell to -10 per 3d from 16 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to -11 per 3d from 17 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to -20 per 3d from 30 (<= 40% of the prior window)
- Accelerating npm_downloads_7d gained 16 in the last 3d after a flat 3d baseline (no prior movement to compare a ratio against)
- Cooling npm_downloads_7d momentum fell to -14 per 3d from 30 (<= 40% of the prior window)
- Accelerating npm_downloads_7d gained 17 in the last 3d after a flat 3d baseline (no prior movement to compare a ratio against)
- Accelerating npm_downloads_7d gained 30 in the last 3d after a flat 3d baseline (no prior movement to compare a ratio against)
- Accelerating npm_downloads_7d gained 30 in the last 3d vs 1 in the 3d before (ratio 30.0x, threshold 1.5x)
- first observed Kanon started keeping permanent history for this agent
🔎 Known / Unknown
15 of 23 fields unknown
| Machine-callable | — | unknown | — |
| Open source | 1 | verified | 1 quote(s) |
| Self-hostable | — | unknown | — |
| Bring your own key | — | unknown | — |
| Autonomy level | 2 | inferred | 2 quote(s) |
| Pricing model | — | unknown | — |
| Integrations | — | unknown | — |
“Unknown” means we have not verified it — it is not a “no”. Hard filters never treat unknown as false.
🤖 Agent teardown · skill
Job to be doneEnable AI coding assistants to explore multiple code paths in parallel and prune poor options to arrive at better solutions.
AutonomyL2 · tool-calling(evidence: "Tree-of-Thought with pruning…")
Who it is forDevelopers
Prerequisitesopen source
PricingNot specified
Traction · why it is rising983 votes on Product Hunt far exceed similar projects, indicating deep resonance with developer communities.
Why it matters
It applies cognitive science principles to AI coding, enabling deeper, more effective problem-solving in complex programming tasks.
Evidence quotesverbatim, from the product’s own materials
“public GitHub repository (README fetched)”— structural
“Tree-of-Thought with pruning”— description
“scores, prunes traps, deepens the survivors”— description
“ADHD — a skill for coding agents. Tree-of-thought with pruning, built on the Claude & Codex Agent SDK.”— readme
Signal source: GitHub
Visit official site →
📛 Official badgefor your site / README
Building adhd? Pick a style above — the embed code updates live. Deep color control via URL params: bg= / fg= / accent= (hex). It links back to this page.
On mobile tap Share for WeChat / RED (Xiaohongshu) / X; on desktop use Copy text and paste into the app.
FAQ
What is adhd?
An ADHD skill for coding agents that uses tree-of-thought with pruning to enhance creativity and accuracy in code generation.
What does adhd do?
Enable AI coding assistants to explore multiple code paths in parallel and prune poor options to arrive at better solutions.
Why does adhd matter?
It applies cognitive science principles to AI coding, enabling deeper, more effective problem-solving in complex programming tasks.
How much does adhd cost?
Not specified
Is adhd open source?
Yes — adhd is open source.
How popular is adhd?
As tracked by KanonAgent: 2.4k upvotes (first indexed 2026-07-28).
What are the best adhd alternatives?
Similar AI agents tracked by KanonAgent: Stealth Venture, taste-skill, archify, open-design, deer-flow, ruflo.