nw-document

nw-document is a skill for Claude Code from nWave-ai/nWave. It costs 31 tokens per session (1,406 once invoked), scanned A, original, MIT.

A workflow for creating documentation using the DIVIO/Diataxis model. It coordinates research, writing, and review for tutorials, how-to guides, reference pages, and explanations.

In plain words
What is it for?
It helps research a topic, write one of four kinds of documentation, and review the result for completeness and consistency.
Why use it?
It gives documentation work a defined process and checks that the result fits the chosen document type and its evidence.

Skill for Claude Code

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

Good fit It helps research a topic, write one of four kinds of documentation, and review the result for completeness and consistency.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/nwave-ai/nwave/nw-document"><img src="https://agentmods.dev/badge/skills/nwave-ai/nwave/nw-document.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,406 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 warn 7 Sept 2026
SkillSpector: 2 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Rogue Agent · line 15
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
  • low Excessive Agency · line 108
    Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.
    Fix: Limit the skill's scope to its documented purpose. Remove instructions that enable the agent to perform actions outside its stated functionality.
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 $0.00031 $0.01406
Opus 5 $0.00015 $0.00703
Sonnet 5 $0.00006 $0.00281
Haiku 4.5 $0.00003 $0.00141

Measured 6d ago against content hash fc3de2c1beb4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

nw-document 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-document/SKILL.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

NW-DOCUMENT: DIVIO Documentation Creation

Wave: CROSS_WAVE | Agent: Orchestrator (self) Agents: Nova (nw-researcher)|Scholar (nw-researcher-reviewer)|Quill (nw-documentarist)|nw-documentarist-reviewer

Overview

Create evidence-based, DIVIO-compliant documentation by orchestrating research and writing phases with peer review at each gate. Cross-wave capability for any nWave phase.

Context Files Required

  • .nwave/trusted-source-domains.yaml — Embed inline in researcher prompt
  • ~/.claude/agents/nw/nw-researcher.md — Extract research methodology
  • ~/.claude/agents/nw/nw-documentarist.md — Extract DIVIO framework and templates

Command Syntax

/nw-document [topic] [--type=tutorial|howto|reference|explanation] [--research-depth=overview|detailed|comprehensive|deep-dive]

If --type omitted, ask user. If --research-depth omitted, auto-select: tutorial->overview|howto->detailed|reference->comprehensive|explanation->deep-dive.

Orchestration Phases

Sub-agents have no Skill tool access. Embed all domain knowledge inline in each Task prompt. Read from agent files and config at orchestration time.

Phase 1: Research           @nw-researcher
Phase 1.5: Research Review  @nw-researcher-reviewer
Phase 2: Documentation      @nw-documentarist
Phase 2.5: Doc Review       @nw-documentarist-reviewer
Phase 3: Handoff

Phase 0: Pre-Flight

  1. Validate topic non-empty, type/depth valid if provided
  2. If type not specified, present DIVIO selection: TUTORIAL ("Teach me")|HOW-TO ("Help me do X")|REFERENCE ("What is X?")|EXPLANATION ("Why is X?")
  3. Determine output: docs/{tutorials|howto|reference|explanation}/{topic-kebab-case}.md
  4. Read and cache: .nwave/trusted-source-domains.yaml|nw-researcher.md|nw-documentarist.md

Phase 1: Research (@nw-researcher)

Invoke via Task tool. Prompt includes: topic|doc type|research depth|complete .nwave/trusted-source-domains.yaml (inline)|type-specific research focus (from nw-researcher.md)|quality gates: trusted sources only, 3+ sources/claim, citation coverage >95%, source reputation >=0.80. Output: docs/research/{topic-kebab-case}-for-{type}-doc.md

Read the full file on GitHub · 119 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 · 119 lines · 31 tokens per session scan A fc3de2c1beb4

Subscribe to this mod's changes

nw-document is a skill published in the GitHub repository nWave-ai/nWave (610 stars, last pushed 3d ago), licensed MIT. It adds 31 tokens to every session and 1,406 once invoked, about $0.0002 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.