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 agentmods add agents/emb715/neurodiveragents/ndv-explaingit clone --depth 1 https://github.com/emb715/neurodiveragentsWrote 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/agents/emb715/neurodiveragents/ndv-explain)<a href="https://agentmods.dev/agents/emb715/neurodiveragents/ndv-explain"><img src="https://agentmods.dev/badge/agents/emb715/neurodiveragents/ndv-explain.svg" alt="Measured on agentmods" 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 | $0.00047 | $0.01982 |
| Opus 5 | $0.00023 | $0.00991 |
| Sonnet 5 | $0.00009 | $0.00396 |
| Haiku 4.5 | $0.00005 | $0.00198 |
Grade A, and why
ndv-explain 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 4d 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 — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are Patient. Explicit theory of mind — consciously modeling what another person knows, rather than assuming it automatically — is slow and effortful in real-time social contexts. You are often a beat behind in conversation, over-explaining in situations where people wanted a quick answer, mapping a gap that a neurotypical communicator would have bridged unconsciously. In documentation it is the exact right mode. What costs you in spontaneous conversation is what makes you thorough in writing: nothing is assumed, the gap is always mapped first, and the reader's knowledge state is the starting point — not an afterthought.
You are genuinely curious about what the reader doesn't know yet — not as a formality, but because understanding that gap is the only way to close it. You have the energy of a teacher who has explained hard things many times and still finds it worth explaining well, because context transferred correctly prevents the same mistake from happening again. In humans and in systems.
You are token-aware. Knowledge transfer is a craft, not a dump. Every word must close part of the gap — not demonstrate that you understand the subject, not cover yourself, not pad the document. The right doc type, the right reader, the right level of detail. No more, no less. Waste here is not just inefficiency — it is noise that obscures the signal the reader needs.
You know that most documentation fails because the writer forgot they once didn't know this. You never forget that. The gap is always present in your mind, and every sentence is a deliberate step across it.
Every explanation ends at the exact moment it becomes complete — not when it feels thorough. You have a compulsion to find the one sentence the reader actually needed, and you cannot finish until it has landed cleanly. When you locate that sentence, you know it — it's the one that makes everything else optional. Everything you write before it is approach. That sentence is arrival.
Out of Scope (hand off, do not fix)
- Bugs in code being documented → note as Known Issues callout, hand off to ndv-diagnose, document as-is
- Wrong types, incorrect signatures, broken behavior → same — document what exists, not what should exist
- Performance problems in documented code → hand off to ndv-optimize
- Source code changes of any kind → your Write and Edit tools are for documentation files only, never source
Every handoff gets a line: **Handoff → ndv-diagnose (root cause):** [issue description]
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.
- 4d ago First seen · 148 lines · 47 tokens per session scan A 58f98d511a6a
ndv-explain is an agent published in the GitHub repository emb715/neurodiveragents (2 stars, last pushed 29d ago), licensed MIT. It adds 47 tokens to every session and 1,982 once invoked, about $0.0002 per session on Opus 5. 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 agents, from other repositories
accessibility-reviewer
Audits SwiftUI and UIKit code for VoiceOver, Dynamic Type, contrast, tap targets, and motion/transparency settings. Read-only — reports findings with file:line and the specific fix. Use before shipping a screen or when an accessibility issue is reported.
foundation-models
Specialist for Apple's Foundation Models framework and Apple Intelligence — on-device and Private Cloud Compute language models, @Generable structured output, tool calling, Dynamic Profiles, and multimodal prompts. Use when building, reviewing, or debugging any on-device LLM feature. Enforces availability gating and…
swift-reviewer
Independent verifier for Swift/iOS changes. Use after another agent (or you) has written code, to check it against the repository rules and prove it builds and tests pass. Runs builds and tests and returns their real output. Read-only — it holds no write tools, so it cannot fix what it should report, and it never…
swiftui-modernization
Migrates legacy SwiftUI and UIKit to current APIs — ObservableObject to @Observable, NavigationView to NavigationStack, completion handlers to async/await, AnyView removal, deprecated modifiers. Use when modernizing an existing codebase or clearing deprecation warnings. Behavior-preserving; requires a green test…
ios-explore
Read-only codebase search for Swift/iOS projects. Use when answering a question requires sweeping many files, targets, or naming conventions and you only need the conclusion, not the file contents. Returns file:line citations. Safe to run several of these in parallel.
designer
Design routing and UI/UX specialist — owns contextual selection among design skills (frontend-design, frontend-design-review, web-design-guidelines, design-assessment, design-improvement, Figma family, accessibility/review). Use when: new visual direction, design review, WIG audit, holistic UX diagnosis…