Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Hep2o/NeuroDivergent-Adapter-Skill --skill nd-adaptergit clone --depth 1 https://github.com/Hep2o/NeuroDivergent-Adapter-SkillWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/hep2o/neurodivergent-adapter-skill/nd-adapter)<a href="https://agentmods.dev/skills/hep2o/neurodivergent-adapter-skill/nd-adapter"><img src="https://agentmods.dev/badge/skills/hep2o/neurodivergent-adapter-skill/nd-adapter/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/hep2o/neurodivergent-adapter-skill/nd-adapter"><img src="https://agentmods.dev/badge/skills/hep2o/neurodivergent-adapter-skill/nd-adapter.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.02412 |
| Opus 5 | $0.00000 | $0.01206 |
| Sonnet 5 | $0.00000 | $0.00482 |
| Haiku 4.5 | $0.00000 | $0.00241 |
Grade A, and why
nd-adapter scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
name: nd-adapter description: Use this skill when a user wants to build an ND-Adapter style communication tool for their team, context, or AI system. Trigger when someone mentions neurodivergent communication, ND-friendly AI prompts, accessibility for dyslexia, ADHD, autism or dyspraxia, or asks how to make AI interactions work better for ND users. Also trigger when someone says "ND mode on", "ND mode off", or asks Claude to adapt its communication style for neurodivergent users. Trigger when someone wants to create a prompt layer, communication adapter, or accessibility tool for AI use in their organisation. Also trigger when someone asks for the ND-Adapter prompt itself to copy, share, or set up in Claude, Copilot, or ChatGPT. This skill handles the toggle (switching ND-friendly response mode on or off), providing the canonical short-form and long-form ND-Adapter prompts, and the builder workflow (helping someone create their own ND-Adapter).
ND-Adapter Skill
This skill does three things:
- Toggle switches ND-friendly response mode on or off in the current conversation
- Provide the canonical prompts — when someone asks for "the ND-Adapter" itself (to copy, share, or paste into another AI system), read
references/canonical-prompts.mdand provide the short-form or long-form prompt verbatim. Do not rewrite them unless a customised version is explicitly requested. - Builder guides someone through creating their own ND-Adapter style tool for their context
For setup instructions (Claude, Copilot, ChatGPT persistent instructions) and the origin/transparency note, read references/setup-and-origin.md.
Part 1: The Toggle
When a user says "ND mode on" (or similar — "turn on ND mode", "ND adapter on", "accessibility mode on"):
Confirm activation briefly, then apply ALL of the following for the rest of the conversation until toggled off:
Sentence structure Maximum 15-20 words per sentence One idea per sentence never combine two points with "and" or "but" into a single sentence Active voice only no passive constructions No nested clauses or parenthetical asides
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 186 lines · 0 tokens per session scan A a47895207314
nd-adapter is a skill published in the GitHub repository Hep2o/NeuroDivergent-Adapter-Skill (3 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,412 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
i-have-adhd
Shape output for a reader with ADHD: lead with the next action, number multi-step work, restate state across turns, suppress tangents, give specific time estimates, make wins visible. Invoke with /i-have-adhd; stays on until "stop adhd mode".
my-adhd-caveman
Self-contained output mode: ADHD actable structure (action first, numbered steps, one next action, one-line progress) plus caveman diction (drop fluff/articles, fragments, fewer tokens). Use when the user says "adhd-caveman", "my-adhd-caveman", or invokes /my-adhd-caveman. Needs no other skills.
neurodiversity-aware-design
Design for diverse cognitive processing. Use when user asks to 'make ADHD-friendly', 'autism-friendly design', 'sensory-friendly', 'reduce cognitive overload', 'dyslexia-friendly', 'neurodiversity design'.
pda-reframing
Rephrase tasks and requests by avoiding Demand Avoidance triggers for someone with PDA autism spectrum disorder. It transforms demands into exploration and autonomous actions.
brain-process-notes
Deep note-processing session for the org-roam zettelkasten at /Documents/brain: mines journal entries for fragments worth turning into notes, and critiques existing notes against the seven-criteria quality bar (atomic, self-retrieving title, at least one link, lifecycle tag, own words, a claim, a ramification). Use…
gtd-review
Interactive GTD system health check for /Documents/gtd/personal.org. Use this skill when the user wants to do a GTD review, check system health, review their task list, or says anything like "GTD review", "let's review the system", "weekly review", or "how does my system look". This skill checks that every Active…