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-newgit 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-new)<a href="https://agentmods.dev/skills/nwave-ai/nwave/nw-new"><img src="https://agentmods.dev/badge/skills/nwave-ai/nwave/nw-new.svg" alt="Measured on agentmods" 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 | $0.00030 | $0.01282 |
| Opus 5 | $0.00015 | $0.00641 |
| Sonnet 5 | $0.00006 | $0.00256 |
| Haiku 4.5 | $0.00003 | $0.00128 |
Grade A, and why
nw-new 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 4d 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NW-NEW: Start a New Feature
Wave: CROSS_WAVE (entry point)
Agent: Main Instance (self — wizard)
Command: /nw-new
Overview
Conversational wizard that asks the user to describe their feature|classifies it|recommends a starting wave|launches it. Eliminates need to understand the 6-wave pipeline before using nWave.
You (the main Claude instance) run this wizard directly. No subagent delegation.
Behavior Flow
Step 1: Feature Description Intake
Ask the user to describe what they want to build. If provided as argument, use that.
If vague (fewer than 3 meaningful words or unclassifiable):
- Ask: What system is being changed?
- Ask: What problem are you solving?
- Ask: Who benefits from this change?
- Provide example: "Add rate limiting to prevent API abuse"
Do NOT proceed until you have a clear, actionable description.
Step 2: Feature ID Derivation
Derive feature ID per rules in ~/.claude/nWave/skills/common/wizard-shared-rules.md (section: Feature ID Derivation).
Examples: "Add rate limiting to the API gateway" -> rate-limiting-api-gateway | "OAuth2 upgrade" -> oauth2-upgrade | "Implement a real-time notification system with WebSocket support for mobile and desktop clients" -> real-time-notification-system-websocket
Show derived ID via AskUserQuestion. Allow override with custom value.
Step 3: Name Conflict Check
Check if docs/feature/{feature-id}/ exists. If so, offer via AskUserQuestion:
- Continue that project — switch to
/nw-continue - Start fresh with different name — ask for distinguishing name
- Archive and restart — move to
docs/feature/{feature-id}-archived-{date}/
Step 4: Clarifying Questions
Use AskUserQuestion:
Q1: New or existing behavior?
- New functionality that doesn't exist yet
- Changing/improving existing functionality
- Fixing a bug or regression
Q2: Requirements readiness?
- Clear requirements in my head but nothing written
- Rough idea, need to explore further
- Haven't validated whether problem is worth solving
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.
- 4d ago First seen · 153 lines · 30 tokens per session scan A 823183224dd6
nw-new is a skill published in the GitHub repository nWave-ai/nWave (608 stars, last pushed 2d ago), licensed MIT. It adds 30 tokens to every session and 1,282 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.
Other skills, from other repositories
parallel-feature-development
Coordinate parallel feature development with file ownership strategies, conflict avoidance rules, and integration patterns for multi-agent implementation. Use this skill when decomposing a large feature into independent work streams, when two or more agents need to implement different layers of the same system…
bazel-build-optimization
Optimize Bazel builds for large-scale monorepos. Use when configuring Bazel, implementing remote execution, or optimizing build performance for enterprise codebases.
track-management
Use this skill when creating, managing, or working with Conductor tracks - the logical work units for features, bugs, and refactors. Applies to spec.md, plan.md, and track lifecycle operations.
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.
planning
Create structured plan documents and track work items using YAML frontmatter. Use when the user wants to plan a feature, track progress, log bugs/tasks/ideas, or organize project work.
organize-task-files
Lists, pairs, deduplicates, and moves task files across the Coworker task state machine (0draft → 6git-pushed). Use when asked to organize, clean up, or audit task files.