The eighteen neurodiveragents — specialist AI agents each grounded in a distinct cognitive style: Flow, Honest, Patient, Pierce, Acute, Just, Bound, Ward, Lean, Signal, Pulse, Arc, Craft, Datum, Edge, Pixel, Scout, and Lux

neurodiveragents

Eighteen specialist AI agents, each grounded in a real cognitive style, not a list of rules.

Designed for Claude models and OpenCode. Works with Cursor and GitHub Copilot.

npx neurodiveragents install

One command installs everything. Detects your tools automatically.

Meet the Agents

Each agent is a different way of thinking. Pick the one whose posture matches the problem.

Agents are one layer

Each agent thinks clearly within its domain. But specialists are only as effective as the context, memory, and tooling you wire around them. Without that infrastructure, the agent reasons precisely about whatever lands in the prompt — and nothing else.

Agents don't know all the details of your project's conventions, architecture decisions, or domain rules unless you surface that context explicitly. They don't carry memory across sessions unless something feeds prior state in. They don't automatically adapt to your stack — you decide what gets wired in and how.

That infrastructure is your responsibility to build. The topics worth researching: harness layer design, context engineering, AGENTS.md and CLAUDE.md setup, and project-specific skills tailored to your codebase and workflow. neurodiveragents gives you the specialists. The harness is yours to configure.

How to use

The question before every session: "how much context do I have, and is it enough to act precisely?" Describe your situation below.

Pick a situation above or type what you're working on

Cognitive Scaffolding

Agents route tasks to the right specialist. But how any step thinks — the cognitive orientation it brings — is a separate variable. Your AI scaffold tells the model what to do. Cognitive modules tell it how to think while doing it.

A review step that says "check for issues" and one that loads ndv-total-perception produce different results — not because the instructions changed, but because the cognitive frame did. Same scaffold, different thinking. These raise the ceiling. They don't raise the floor.

See the difference

Without
# your-skill / step-review.md

instructions: |
  Review this code for issues.
  Report what you find.
With modules
ndv-total-perception + ndv-adversarial
# your-skill / step-review.md

instructions: |
  Review this code for issues.
  Report what you find.

ndv-total-perception — registers everything simultaneously before sorting by severity. Self-censoring a finding as "too minor to mention" is a perception failure, not a judgment call. ndv-adversarial — assumes the code is lying until proven otherwise.

Compose by phase

2–3 modules per phase. More dilutes the signal — the model balances competing frames instead of fully adopting one.

Requirements
ndv-skeptical ndv-bounded

Probe intent. Scope is a wall.

Implement
ndv-precise ndv-incremental ndv-efficient

Follow the pattern. Build on verified ground.

Review
ndv-total-perception ndv-adversarial

Everything registers. Code is guilty until proven innocent.

Present
ndv-contextual ndv-direct

Model the reader. Every word earns its place.

Module Cognitive posture
ndv-skepticalassumption-hostile
ndv-structuraldependency-aware
ndv-preciseminimal-change
ndv-total-perceptioneverything registers
ndv-directzero filler
ndv-adversarialassumes failure
ndv-vigilantthreat-detection on
ndv-efficientwaste is intolerable
ndv-contextualmodels the reader
ndv-boundedscope as a wall
ndv-incrementalbuild on verified ground
ndv-parallel-safeadversarial toward assumed parallelism
ndv-temporaltrajectory over snapshot
ndv-map-firstcomplete before reporting
ndv-perceptualreads code as rendered output

Install modules

npx neurodiveragents install-skills claude
npx neurodiveragents install-skills opencode --global

Full guide: docs/ndv-skills.md

Claude Code and OpenCode only. Cursor and GitHub Copilot do not implement the Agent Skills spec.

Install

One command auto-detects your AI coding assistants and configures all agent prompts. No global state — pure local configuration.

Recommended

All Tools (Auto-detect)

npx neurodiveragents install

Or install for a specific tool

Claude Code

npx neurodiveragents install claude

OpenCode

npx neurodiveragents install opencode

Cursor

npx neurodiveragents install cursor

GitHub Copilot

npx neurodiveragents install copilot