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-tr-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-tr-review-criteria)<a href="https://agentmods.dev/skills/nwave-ai/nwave/nw-tr-review-criteria"><img src="https://agentmods.dev/badge/skills/nwave-ai/nwave/nw-tr-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-tr-review-criteria"><img src="https://agentmods.dev/badge/skills/nwave-ai/nwave/nw-tr-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 | $0.00016 | $0.00814 |
| Opus 5.5 | $0.00006 | $0.00326 |
| Sonnet 5.5 | $0.00003 | $0.00163 |
| Haiku 4.5 | $0.00002 | $0.00081 |
Grade A, and why
nw-tr-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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Troubleshooter Review Criteria
Review dimensions and scoring for root cause analysis quality assessment.
Dimension 1: Causality Logic
Check each WHY-to-WHY link.
Pass: logical mechanism (not just correlation) | no skipped steps | alternatives considered/eliminated | chain reads coherently both directions
Failures: correlation assumed as causation | causal chain gaps | single-path tunnel vision (first plausible cause accepted)
Severity: Critical -- wrong root cause = ineffective fixes.
Dimension 2: Evidence Quality
Verify findings grounded in observable data.
Pass: each WHY cites specific evidence (logs, metrics, config, repro steps) | evidence verifiable by third party | timeline supports causality | hypotheses marked unverified
Failures: "Probably because..." without data | vague references ("logs show issues") | mixing facts with speculation unlabeled
Severity: High -- unreliable analysis undermines trust.
Dimension 3: Alternative Hypotheses
Verify competing explanations explored.
Pass: 2+ alternatives at WHY 1-3 | each pursued or eliminated with evidence | "why not" reasoning documented
Failures: stops at first plausible cause | alternatives mentioned but unevaluated | confirmation bias
Severity: High -- may miss actual root cause.
Dimension 4: Five-WHY Depth
Verify analysis reaches fundamental causes.
Pass: each branch reaches WHY 5 (or justifies stopping with evidence) | final causes are actionable | causes explain symptoms when traced forward
Failures: stopping at WHY 2-3 | WHY 5 vague/philosophical not actionable | branches abandoned
Severity: High -- shallow analysis = band-aid fixes that recur.
Dimension 5: Completeness and Coverage
Verify all symptoms accounted for.
Pass: all symptoms have causal branch | root causes collectively explain all | no orphan symptoms | cross-cause validation (no contradictions)
Failures: symptoms ignored | root causes explain primary but not secondary | contradictory causes without reconciliation
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 · 112 lines · 16 tokens per session scan A 07c54b0f0426
nw-tr-review-criteria is a skill published in the GitHub repository nWave-ai/nWave (620 stars, last pushed 1mo ago), licensed MIT. It adds 16 tokens to every session and 814 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 2026-09-06.
Other skills, from other repositories
behavior-contract
Bug condition/postcondition formalization as testable Behavior Contracts. Defines invariants that must be preserved across fixes.
debugging
A structured method for finding and fixing software bugs. It starts by writing a test that reproduces the failure, then investigates its underlying cause before making a small fix.
hk-rca
Interactive Root Cause Analysis enforcer. Guides you through the 7-step RCA protocol: Reproduce, Locate, Hypothesis, Failing Test, Fix, Verify Live, Document. Use when debugging a bug, investigating a failure, or when something unexpected happened. This skill gates each step — it won't let you skip to a fix without…
debug-flow
Systematic debugging workflow. Reproduce the issue, isolate root cause, write a failing test, fix, verify. Use when diagnosing bugs or unexpected behavior.
team-fix
Use for the full bug-fix pipeline only on explicit request. Never infer from an ordinary bug fix. Runs the compressed pipeline.
investigate
Root-cause a bug, test failure, CI failure, or unexpected behavior before changing code. Reproduce, compare against working code, test one hypothesis at a time, then fix with a failing regression test first. Stops after three failed fixes to question the design, and requires fresh evidence before any "fixed" claim.…