nw-mikado

nw-mikado is a skill for Claude Code from nWave-ai/nWave. It costs 19 tokens per session (572 once invoked), scanned A, original, MIT.

A command and workflow for using the Mikado Method on complex refactoring work. It records discovered dependencies, builds a tree or graph, and guides bottom-up implementation.

In plain words
What is it for?
Use it when a refactoring goal spans multiple classes and a direct change causes cascading failures.
Why use it?
Architectural refactors often reveal hidden prerequisites only after code or tests fail. This workflow helps preserve those discoveries and order the work safely.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

Good fit Use it when a refactoring goal spans multiple classes and a direct change causes cascading failures.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/nwave-ai/nwave/nw-mikado
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.

Any agent
npx skills add nWave-ai/nWave --skill nw-mikado
Clone the repo
git clone --depth 1 https://github.com/nWave-ai/nWave

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 nw-mikado

README.md
[![agentmods](https://agentmods.dev/badge/skills/nwave-ai/nwave/nw-mikado/github.svg)](https://agentmods.dev/skills/nwave-ai/nwave/nw-mikado)
Your own site
<a href="https://agentmods.dev/skills/nwave-ai/nwave/nw-mikado"><img src="https://agentmods.dev/badge/skills/nwave-ai/nwave/nw-mikado/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 nw-mikado

Your own site · 80×15
<a href="https://agentmods.dev/skills/nwave-ai/nwave/nw-mikado"><img src="https://agentmods.dev/badge/skills/nwave-ai/nwave/nw-mikado.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 572 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00019 $0.00572
Opus 5 $0.00010 $0.00286
Sonnet 5 $0.00004 $0.00114
Haiku 4.5 $0.00002 $0.00057

Measured 6d ago against content hash 029e3316f02b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

nw-mikado 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 6d 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.

nWave/skills/nw-mikado/SKILL.md · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

NW-MIKADO: Complex Refactoring with Mikado Method

EXPERIMENTAL: Under active development. Behavior and output format may change between versions.

Wave: CROSS_WAVE Agent: Crafty (nw-software-crafter) Command: *mikado

Overview

Plan and execute complex refactoring using the Mikado Method. Builds dependency {visualization} through iterative exploration|tracks discoveries via commits|executes leaf-to-goal bottom-up. For architectural changes spanning multiple classes where simple refactoring is insufficient.

Context Files Required

  • src/* - Codebase to refactor
  • docs/product/architecture/brief.md - Target architecture (if available)

Agent Invocation

@nw-software-crafter

Execute *mikado for {refactoring-goal}.

Context Files:

  • src/*
  • docs/product/architecture/brief.md

Configuration:

  • refactoring_goal: "{goal description with business value}"
  • complexity: complex # simple/moderate/complex
  • visualization: {tree|graph} # tree = indented markdown checklist, graph = Mermaid dependency diagram

Success Criteria

  • Mikado {visualization} persisted at docs/mikado/{goal-name}.mikado.md
  • Discovery commits capture each exploration attempt
  • All leaf nodes implemented bottom-up
  • Goal node achieved with all tests passing
  • {visualization_label} stable (no new dependencies emerging)

Visualization labels: tree → "Tree", graph → "Graph". Use the selected visualization type in all output messages (e.g., "Wrote the Mikado tree" or "Wrote the Mikado graph").

Next Wave

Handoff To: {invoking-agent-returns-to-workflow} Deliverables: Refactored codebase + Mikado {visualization} documentation

Examples

Example 1: Extract shared domain model

/nw-mikado "Extract shared domain model from monolithic service layer"

Crafty builds Mikado dependency {visualization} through iterative exploration, discovers 12 leaf nodes across 4 modules, executes bottom-up from leaves to goal with discovery commits at each step.

Read the full file on GitHub · 70 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. 6d ago First seen · 70 lines · 19 tokens per session scan A 029e3316f02b

Subscribe to this mod's changes

nw-mikado is a skill published in the GitHub repository nWave-ai/nWave (610 stars, last pushed 3d ago), licensed MIT. It adds 19 tokens to every session and 572 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 2026-09-03.