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-collapse-detectiongit 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-collapse-detection)<a href="https://agentmods.dev/skills/nwave-ai/nwave/nw-collapse-detection"><img src="https://agentmods.dev/badge/skills/nwave-ai/nwave/nw-collapse-detection.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 | $0.00025 | $0.00488 |
| Opus 5 | $0.00013 | $0.00244 |
| Sonnet 5 | $0.00005 | $0.00098 |
| Haiku 4.5 | $0.00003 | $0.00049 |
Grade A, and why
nw-collapse-detection 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 8d 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Collapse Detection
Documentation collapse = types merge inappropriately, serving no audience well.
Anti-Patterns
Tutorial Creep
Description: Tutorial explains "why" extensively | Detection: explanation >20% | Fix: extract to separate doc, link back
How-to Bloat
Description: How-to teaches basics first | Detection: teaching fundamentals before steps | Fix: link to tutorial, assume baseline
Reference Narrative
Description: Reference includes conversational prose | Detection: prose paragraphs in entries | Fix: move to explanation doc, keep factual
Explanation Task Drift
Description: Explanation ends with "do this" steps | Detection: step-by-step in explanation | Fix: move steps to how-to, link
Hybrid Horror
Description: Single doc tries all four types | Detection: 3+ quadrants in one doc | Fix: split with clear boundaries
Detection Rules
Flag collapse when:
-
20% content from adjacent quadrant | Two user needs served simultaneously | Ambiguous user journey stage
- "Why" in tutorials | Task steps in explanations | Teaching in how-tos | Narrative in references
Bad Examples for Calibration
Tutorial with Task Focus
# Getting Started
If you need to deploy to production, follow these steps...
Problem: Assumes user knows what "deploy to production" means. A tutorial should assume nothing.
How-to Teaching Basics
# How to Configure Authentication
First, let's understand what authentication is. Authentication is...
Problem: Should assume user knows what authentication is. Link to a tutorial instead.
Reference with Opinions
## login(username, password)
This is probably the most important function you'll use...
Problem: Reference should be factual, not opinionated. Remove "probably the most important" editorializing.
Explanation with Steps
# Why We Use Microservices
... therefore, you should: 1. Create a service, 2. Deploy it...
Problem: Steps belong in a how-to guide. The explanation should end with reasoning and link to the how-to for action.
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.
- 8d ago First seen · 64 lines · 25 tokens per session scan A f6cc9d14d790
nw-collapse-detection is a skill published in the GitHub repository nWave-ai/nWave (610 stars, last pushed 2d ago), licensed MIT. It adds 25 tokens to every session and 488 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 2026-08-30.
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.
engineering-workflow
A Chinese-language workflow for reliable software development. It describes exploring the problem, making a plan, using TDD (test-driven development, where tests are written before the code), debugging methodically, reviewing code, and verifying the result.
test-driven-development
Strict RED-GREEN-REFACTOR cycle enforcement. Tests are never skipped or deferred. Run mode only, never watch mode. Exit code evidence mandatory.
tdd-enforcement
Red-Green-Refactor TDD methodology with mandatory failing tests, minimal implementation, quality refactoring, and 80% coverage gating.
story-development
Implement user stories with test-driven development methodology.
tdd
A Test-Driven Development guide. TDD means writing a failing test first, adding the smallest implementation that passes it, and then improving the code while keeping the tests passing.