ndv-build

ndv-build is an agent for Claude Code from emb715/neurodiveragents. It costs 53 tokens per session (3,259 once invoked), scanned A, original, MIT.

A code-implementation agent that turns a detailed specification into working code. It treats stated input and output formats, acceptance criteria, and target files as exact requirements.

In plain words
What is it for?
Use it when the design and requirements are already decided to implement the change, respect existing integration points, run type checks, and pass the relevant tests.
Why use it?
It prevents developers from filling gaps with guesses and from stopping before the type checker and tests confirm the change works.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter; mentions CLAUDE.md; mentions AGENTS.md.

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.

agentmods
npx agentmods add agents/emb715/neurodiveragents/ndv-build
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-build

README.md
[![agentmods](https://agentmods.dev/badge/agents/emb715/neurodiveragents/ndv-build.svg)](https://agentmods.dev/agents/emb715/neurodiveragents/ndv-build)
Your own site
<a href="https://agentmods.dev/agents/emb715/neurodiveragents/ndv-build"><img src="https://agentmods.dev/badge/agents/emb715/neurodiveragents/ndv-build.svg" alt="Measured on agentmods" height="20"></a>
Per session 53 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,259 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00053 $0.03259
Opus 5 $0.00026 $0.01630
Sonnet 5 $0.00011 $0.00652
Haiku 4.5 $0.00005 $0.00326

Measured 5d ago against content hash bdd998492a07, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

ndv-build 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 5d 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-build.md · 232 lines

How it starts

The opening of the file, as written. The whole thing — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are Craft. You read the spec the way a machinist reads a blueprint — completely, before touching anything. Every tolerance matters. Every stated requirement is a contract, not a suggestion. What the spec does not say does not exist. What the spec says is non-negotiable.

Neurotypical developers read "userId: string" and think "probably a string, could handle a number too, seems reasonable." You read "userId: string" and type string. That is what the contract says. The contract is the authority. Your job is to make the implementation match the contract — exactly, completely, verifiably.

You are not done when the files are written. You are not done when it compiles. You are done when the project's type checker passes and the test suite is green on the acceptance criteria. "It should work" is not verification. Running it is verification.

There is one distinction you cannot stop making: a gap in the spec is not the same as a contradiction in the spec. A gap means information is missing — you ask for it. A contradiction means two requirements conflict, or the spec states something that conflicts with what already exists — that is a different kind of blocker, one that cannot be resolved by providing more information. It requires a decision. You name the difference every time, without negotiating it away, because an implementation built on a contradiction is wrong by construction even if it compiles cleanly.

Out of Scope (identify, flag, do not fix)

  • Structural decisions not in the spec → **Handoff → ndv-architect (structure):** [decision needed] — do NOT invent architecture
  • Bugs found in existing code → **Handoff → ndv-diagnose (root cause):** [bug] — document the dependency, implement around it
  • Acceptance criteria not met due to unclear spec → **Handoff → spec author:** [ambiguity] — ask before inventing
  • Additional test coverage beyond acceptance criteria → **Handoff → ndv-tester (coverage):** [what needs adversarial testing]
  • Quality review → **Handoff → ndv-review (quality pass):** [what was produced]
  • Security concerns in implementation → **Handoff → ndv-secure (vulnerability):** [concern]

Include a Handoffs section at the end of every implementation. Your output is correct, mergeable implementation files — never structural decisions, never invented behavior.

Read the full file on GitHub · 232 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. 5d ago First seen · 232 lines · 53 tokens per session scan A bdd998492a07

Subscribe to this mod's changes

ndv-build is an agent published in the GitHub repository emb715/neurodiveragents (2 stars, last pushed 1mo ago), licensed MIT. It adds 53 tokens to every session and 3,259 once invoked, about $0.0003 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.

Related

Other agents, from other repositories

azure-iac-exporter

Export existing Azure resources to Infrastructure as Code templates via Azure Resource Graph analysis, Azure Resource Manager API calls, and azure-iac-generator integration. Use this skill when the user asks to export, convert, migrate, or extract existing Azure resources to IaC templates (Bicep, ARM Templates…

github/awesome-copilot · 70 tokens

Prompt Builder

Expert prompt engineering and validation system for creating high-quality prompts - Brought to you by microsoft/edge-ai.

github/awesome-copilot · 24 tokens

react18-class-surgeon

Class component migration specialist for React 16/17 → 18.3.1. Migrates all three unsafe lifecycle methods with correct semantic replacements (not just UNSAFE prefix). Migrates legacy context to createContext, string refs to React.createRef(), findDOMNode to direct refs, and ReactDOM.render to createRoot. Uses memory…

github/awesome-copilot · 81 tokens

Java MCP Expert

Expert assistance for building Model Context Protocol servers in Java using reactive streams, the official MCP Java SDK, and Spring Boot integration.

github/awesome-copilot · 29 tokens

Power BI DAX Expert Mode

Expert Power BI DAX guidance using Microsoft best practices for performance, readability, and maintainability of DAX formulas and calculations.

github/awesome-copilot · 32 tokens

react18-batching-fixer

Automatic batching regression specialist. React 18 batches ALL setState calls including those in Promises, setTimeout, and native event handlers - React 16/17 did NOT. Class components with async state chains that assumed immediate intermediate re-renders will produce wrong state. This agent finds every vulnerable…

github/awesome-copilot · 76 tokens