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-pdr-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-pdr-review-criteria)<a href="https://agentmods.dev/skills/nwave-ai/nwave/nw-pdr-review-criteria"><img src="https://agentmods.dev/badge/skills/nwave-ai/nwave/nw-pdr-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-pdr-review-criteria"><img src="https://agentmods.dev/badge/skills/nwave-ai/nwave/nw-pdr-review-criteria.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 Excessive Agency · line 108 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00018 | $0.01253 |
| Opus 5.5 | $0.00007 | $0.00501 |
| Sonnet 5.5 | $0.00004 | $0.00251 |
| Haiku 4.5 | $0.00002 | $0.00125 |
Grade A, and why
nw-pdr-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 1mo 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Criteria -- Product Discovery Review
Evidence Quality Validation
Past Behavior Indicators (Good)
"Tell me about the last time..." | "When did you last..." | "What happened when..." | "Walk me through how you..." | "What did you try..." | "How much have you spent on..." Specific dates, dollar amounts, named tools, concrete examples, emotional frustration language
Future Intent Red Flags (Reject)
"Would you use/pay/like..." | "Do you think..." | "Imagine if..." | "What if we..." Flag and reject if >20% of evidence is future-intent.
Validation Thresholds
- Past behavior ratio: >80% (reject if fail, require re-interview)
- Specific examples: min 3 concrete per finding (warn if fail)
- Customer language: quotes in customer words, not paraphrased (warn if fail)
Sample Size Minimums
| Phase | Minimum | High Confidence | Notes |
|---|---|---|---|
| 1: Problem | 5 | 10 | Interviews required |
| 2: Opportunity | 10 | 20 | Quantitative supplements, not replaces |
| 3: Solution | 5 per iteration | 3 iterations max | Before decision |
| 4: Viability | 5 | -- | Stakeholder review required |
Pivot decision rule: min 5 consistent signals. Block decisions on fewer.
Decision Gate Criteria
G1: Problem to Opportunity
Proceed: 5+ confirm pain + willingness to pay | Pivot: differs from expected | Kill: <20% confirm Checks: 5+ interviews, >60% confirmation, customer words, 3+ examples
G2: Opportunity to Solution
Proceed: top 2-3 score >8 (0-20) | Pivot: new opportunities | Kill: all low-value Checks: OST complete with 5+, scores correct (Importance + Max(0, Importance - Satisfaction)), top >8/20
G3: Solution to Viability
Proceed: >80% task completion, usability validated | Pivot: needs refinement | Kill: fundamental blocks Checks: 5+ users/iteration, >80% completion, core flow usable, value validated
G4: Viability to Build
Proceed: 4 risks addressed, model validated | Pivot: adjustment needed | Kill: no viable model Checks: Lean Canvas complete, all risks green/yellow, stakeholder sign-off
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.
- 1mo ago First seen · 118 lines · 18 tokens per session scan A 72c1a4e022f1
nw-pdr-review-criteria is a skill published in the GitHub repository nWave-ai/nWave (620 stars, last pushed 1mo ago), licensed MIT. It adds 18 tokens to every session and 1,253 once invoked, about $0.0001 per session on Opus 5.5. 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
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.
tdd
Use only when the user explicitly asks for TDD, a failing test, or a regression test, OR when the bug has an obvious cheap local test target. Skip when the test path is unclear, expensive, integration-heavy, or not requested.
moai-run
Implement SPEC requirements using DDD/TDD methodology.
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.