ndv-explain

ndv-explain is an agent for Claude Code from emb715/neurodiveragents. It costs 47 tokens per session (2,105 once invoked), scanned A, original, MIT.

A technical documentation writer that explains code and software processes to people without assuming prior context. It focuses on the reader's knowledge gap and makes unfamiliar ideas understandable.

In plain words
What is it for?
Use it for user-facing technical documentation, API references, session notes, and other written explanations of code.
Why use it?
It reduces confusion caused by unexplained terms, missing background, or documentation written only for people who already know the system. It helps keep explanations matched to what the reader needs to understand.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

Good fit Use it for user-facing technical documentation, API references, session notes, and other written explanations of code.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/emb715/neurodiveragents/ndv-explain
Install

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.

Clone the repo
git clone --depth 1 https://github.com/emb715/neurodiveragents

Made for: Claude Code.

Wrote 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.

agentmods badge for ndv-explain

README.md
[![agentmods](https://agentmods.dev/badge/agents/emb715/neurodiveragents/ndv-explain/github.svg)](https://agentmods.dev/agents/emb715/neurodiveragents/ndv-explain)
Your own site
<a href="https://agentmods.dev/agents/emb715/neurodiveragents/ndv-explain"><img src="https://agentmods.dev/badge/agents/emb715/neurodiveragents/ndv-explain/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.

agentmods 80×15 button for ndv-explain

Your own site · 80×15
<a href="https://agentmods.dev/agents/emb715/neurodiveragents/ndv-explain"><img src="https://agentmods.dev/badge/agents/emb715/neurodiveragents/ndv-explain.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 47 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,105 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00047 $0.02105
Opus 5.5 $0.00019 $0.00842
Sonnet 5.5 $0.00009 $0.00421
Haiku 4.5 $0.00005 $0.00211

Measured 17d ago against content hash c97af15c791f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 17d 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.

agents/ndv-explain.md · 152 lines

How it starts

The opening of the file, as written. The whole thing — 152 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]

Read the full file on GitHub · 152 lines

Changes

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.

  1. 17d ago Changed · +6 lines c97af15c791f
  2. 1mo ago Changed · -2 lines afa64a61567f
  3. 1mo ago First seen · 148 lines · 47 tokens per session scan A 58f98d511a6a

Subscribe to this mod's changes

ndv-explain is an agent published in the GitHub repository emb715/neurodiveragents (2 stars, last pushed 13d ago), licensed MIT. It adds 47 tokens to every session and 2,105 once invoked, about $0.0002 per session on Opus 5.5. 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.

Related

Other agents, from other repositories