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-dr-review-criteriagit 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-dr-review-criteria)<a href="https://agentmods.dev/skills/nwave-ai/nwave/nw-dr-review-criteria"><img src="https://agentmods.dev/badge/skills/nwave-ai/nwave/nw-dr-review-criteria/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-dr-review-criteria"><img src="https://agentmods.dev/badge/skills/nwave-ai/nwave/nw-dr-review-criteria.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 | $0.00025 | $0.01242 |
| Opus 5 | $0.00013 | $0.00621 |
| Sonnet 5 | $0.00005 | $0.00248 |
| Haiku 4.5 | $0.00003 | $0.00124 |
Grade A, and why
nw-dr-review-criteria 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 9d 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Documentation Review Criteria
Critique Dimensions
1. Classification Accuracy
Verify type assignment against DIVIO decision tree.
Questions: Do cited signals support assigned type? | Contradicting signals ignored? | Confidence appropriate? | Decision tree leads to same classification?
Verification: 1) Run decision tree independently 2) Check positive signals present 3) Check for red flags 4) Verify confidence matches signal strength
Severity: if wrong classification leads to wrong verdict = blocking.
2. Validation Completeness
Verify all type-specific criteria checked. Questions: All items checked? | Pass/fail correct? | Issues properly located? | Any criteria missed?
Tutorial (required): completable without external refs | steps numbered/sequential | verifiable outcomes | no assumed knowledge | builds confidence
How-to (required): clear goal | assumes fundamentals | single task | completion indicator | no basics teaching
Reference (required): all params documented | return values | error conditions | examples | no narrative
Explanation (required): addresses "why" | context/reasoning | alternatives considered | no task steps | conceptual model
3. Collapse Detection Correctness
Verify all five anti-patterns checked with accurate findings.
- Tutorial creep: explanation >20% | How-to bloat: teaching basics | Reference narrative: prose in entries
- Explanation task drift: steps in explanation | Hybrid horror: 3+ quadrants
Verification: independently scan, count lines per quadrant, compare to documentarist's findings, flag discrepancies.
4. Recommendation Quality
Criteria: Specific (exact what/where) | Actionable (author knows next step) | Prioritized (important first) | Justified (why it matters) | Root cause (underlying issue)
Bad: "Improve the documentation", "Make it clearer" Good: "Move explanation in section 3.2 (lines 45-60) to separate doc", "Add return value docs for login()"
5. Quality Score Accuracy
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.
- 9d ago First seen · 138 lines · 25 tokens per session scan A 77c659f657a7
nw-dr-review-criteria is a skill published in the GitHub repository nWave-ai/nWave (610 stars, last pushed 6d ago), licensed MIT. It adds 25 tokens to every session and 1,242 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
tutorial
Interactive tutorial teaching Ouroboros hands-on.
animation
Author animated technical explainer diagrams as .anim.json files for Nimbalyst's Animation editor. Use when the user wants to animate a diagram, show how a system/protocol/algorithm behaves over time, build a motion explainer, or turn a static architecture diagram into something that plays.
exam-material-recommendation
A study-material recommendation tool for doctors preparing for professional exams or job-related training. It uses the person’s target, timeline, available study time, and specialty, while treating the official exam syllabus as the main reference.
moai-workflow-jit-docs
Enhanced Just-In-Time document loading system that discovers, loads, and caches relevant documentation based on user intent and project context. Use when users need specific documentation on demand.
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.