diverge

diverge is a command for Claude Code from nWave-ai/nWave. It costs 26 tokens per session (1,918 once invoked), scanned A, original, MIT.

Generates 3-5 divergent design directions through JTBD analysis, competitive research, structured brainstorming, and taste evaluation before convergence.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: reads .claude/ paths; mentions subagents.

Part of the nw plugin — 12 commands shipped together

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 commands/nwave-ai/nwave/diverge
Clone the repo
git clone --depth 1 https://github.com/nWave-ai/nWave

Made for: Claude Code.

Or install nw, the plugin that ships this one along with the rest of its 12 commands.

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 diverge

README.md
[![agentmods](https://agentmods.dev/badge/commands/nwave-ai/nwave/diverge.svg)](https://agentmods.dev/commands/nwave-ai/nwave/diverge)
Your own site
<a href="https://agentmods.dev/commands/nwave-ai/nwave/diverge"><img src="https://agentmods.dev/badge/commands/nwave-ai/nwave/diverge.svg" alt="Measured on agentmods" height="20"></a>
Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,918 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.00026 $0.01918
Opus 5 $0.00013 $0.00959
Sonnet 5 $0.00005 $0.00384
Haiku 4.5 $0.00003 $0.00192

Measured today against content hash c384361923d1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

diverge 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 today.

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.

plugins/nw/commands/diverge.md · 173 lines

How it starts

The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.

NW-DIVERGER: Structured Divergent Thinking Before Convergence

Wave: DIVERGE (between DISCOVER and DISCUSS, optional) | Agent: Flux (nw-diverger) | Command: /nw-diverger

Overview

Execute DIVERGE wave through Flux's 4-phase workflow: JTBD analysis|competitive research|structured brainstorming|taste-filtered evaluation. Transforms a validated problem into 3-5 concrete, taste-scored design directions so DISCUSS can converge on one with confidence.

DIVERGE is optional. Brownfield features with a clear direction may skip it (see skip checklist in design spec). New products and pivot decisions benefit most from structured divergence.

Interactive Decision Points

Decision 1: Work Type

Question: What type of work is this? Options:

  1. New product -- no prior solution exists, full divergence needed
  2. Brownfield feature -- existing product, exploring approach alternatives
  3. Pivot / redesign -- existing feature being reconsidered from scratch
  4. Other -- user provides custom context

Decision 2: Research Depth

Question: How deep should competitive research go? Options:

  1. Lightweight -- 3 competitors, known market
  2. Comprehensive -- 5+ competitors including non-obvious alternatives
  3. Deep-dive -- cross-category research, adjacent markets, academic references

Prior Wave Consultation

Before beginning DIVERGE work, read SSOT and prior wave artifacts:

  1. SSOT (if docs/product/ exists):
    • docs/product/jobs.yaml -- validated jobs and opportunity scores
    • docs/product/vision.md -- product vision and strategic context
  2. Project context: docs/project-brief.md | docs/stakeholders.yaml (if available)
  3. DISCOVER artifacts: Read docs/feature/{feature-id}/discover/ (if present)
    • wave-decisions.md -- validated assumptions and key decisions
    • problem-validation.md -- customer evidence grounding the problem

If docs/product/ does not exist, this is the first wave using the SSOT model. DIVERGE will create it (bootstrap docs/product/jobs.yaml with the validated job).

Read the full file on GitHub · 173 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. today First seen · 173 lines · 26 tokens per session scan A c384361923d1

Subscribe to this mod's changes

diverge is a command published in the GitHub repository nWave-ai/nWave (605 stars, last pushed today), licensed MIT. It adds 26 tokens to every session and 1,918 once invoked, about $0.0001 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 2026-09-06.