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.
npx skills add nWave-ai/nWave --skill nw-mikadogit clone --depth 1 https://github.com/nWave-ai/nWaveWrote 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.
[](https://agentmods.dev/skills/nwave-ai/nwave/nw-mikado)<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.
<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>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once 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 |
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.
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.
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.
- 6d ago First seen · 70 lines · 19 tokens per session scan A 029e3316f02b
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.
Other skills, from other repositories
workflow-patterns
Use this skill when implementing tasks according to Conductor's TDD workflow, handling phase checkpoints, managing git commits for tasks, or understanding the verification protocol.
strict-tdd
Strict RED->GREEN->REFACTOR test-driven development with enforcement. Never write production code before a failing test. Atomic commits per TDD cycle.
sup-coding
Coding workflow recipe (brainstorm → design → spec → plan → implement → review → verify → finish).
workflow-patterns
Use this skill when implementing tasks according to Conductor's TDD workflow, handling phase checkpoints, managing git commits for tasks, or understanding the verification protocol.
git-advanced-workflows
Master advanced Git workflows including rebasing, cherry-picking, bisect, worktrees, and reflog to maintain clean history and recover from any situation. Use when managing complex Git histories, collaborating on feature branches, or troubleshooting repository issues.
mcore-split-pr
Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.