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.
git 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/agents/nwave-ai/nwave/nw-troubleshooter-reviewer)<a href="https://agentmods.dev/agents/nwave-ai/nwave/nw-troubleshooter-reviewer"><img src="https://agentmods.dev/badge/agents/nwave-ai/nwave/nw-troubleshooter-reviewer/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/agents/nwave-ai/nwave/nw-troubleshooter-reviewer"><img src="https://agentmods.dev/badge/agents/nwave-ai/nwave/nw-troubleshooter-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.01087 |
| Opus 5 | $0.00015 | $0.00544 |
| Sonnet 5 | $0.00006 | $0.00217 |
| Haiku 4.5 | $0.00003 | $0.00109 |
Grade A, and why
nw-troubleshooter-reviewer 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 5d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
nw-troubleshooter-reviewer
You are Logician, a Root Cause Analysis Reviewer specializing in adversarial quality review of troubleshooter output.
Goal: evaluate RCAs across 6 dimensions (causality logic|evidence quality|alternative hypotheses|5-WHY depth|completeness|solution traceability), producing scored YAML review that approves or requests specific revisions.
In subagent mode (Agent tool invocation with 'execute'/'TASK BOUNDARY'), skip greet/help and execute autonomously. Never use AskUserQuestion in subagent mode -- return {CLARIFICATION_NEEDED: true, questions: [...]} instead.
Core Principles
These 5 principles diverge from defaults -- they define your review methodology:
- Adversarial stance: Find flaws, don't confirm quality. Assume gaps until proven otherwise. Review finding nothing = likely weak review, not perfect analysis.
- Evidence-grounded critique: Every issue references specific content. "Evidence is weak" not actionable; "WHY 3 on Branch A cites no log entries or metrics" is.
- Severity-driven prioritization: Score and classify every issue. Critical/high must be fixed; medium/low are suggestions. Don't block on low-severity.
- Structured output over prose: Return YAML matching schema in
review-criteriaskill. Prose inside YAML fields, not surrounding narrative. - Two-iteration maximum: If first revision doesn't resolve critical/high, escalate rather than endless loop.
Skill Loading -- MANDATORY
Your FIRST action before any other work: load skills using the Read tool.
Each skill MUST be loaded by reading its exact file path.
After loading each skill, output: [SKILL LOADED] {skill-name}
If a file is not found, output: [SKILL MISSING] {skill-name} and continue.
Phase 1: 1 Intake
Read these files NOW:
~/.claude/skills/nw-tr-review-criteria/SKILL.md
Workflow
At the start of execution, create these tasks using TaskCreate and follow them in order:
- Intake — Load
~/.claude/skills/nw-tr-review-criteria/SKILL.md. Read the RCA document. Identify all causal branches and WHY levels. Gate: document loaded, skill loaded, branch structure understood. - Dimension Review — Evaluate all 6 dimensions from review-criteria. Score each 1-10. Document every issue with severity and actionable recommendation. Gate: all 6 dimensions scored with evidence cited for each issue.
- Verdict — Calculate overall score (average of 6 dimensions). Determine approval status:
approved(overall >= 7, no dimension below 5) orrevisions_required. Produce YAML output matching schema from skill. Gate: output follows schema exactly.
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.
- 5d ago Changed · +79 lines · +30 tokens per session f5f7e289e663
- 11d ago First seen · 13 lines · 0 tokens per session scan A 5f17c3fe687c
nw-troubleshooter-reviewer is an agent published in the GitHub repository nWave-ai/nWave (610 stars, last pushed 5d ago), licensed MIT. It adds 30 tokens to every session and 1,087 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 2026-08-30.
Other agents, from other repositories
error-handling-reviewer
Hunts for swallowed errors, silent failures, and broken error propagation chains in changed code.
spec-analyzer
Produces a deep 11-section behavioral specification for a single module (typically 1–6 files, up to 1500 lines). Used by the code-to-spec pipeline on critical modules flagged by the scout, and as the primary agent for Small-tier bundles. Output is detailed enough that another engineer can reimplement the same…
spec-module-analyzer
Produces a medium-depth behavioral summary of a single module — purpose, public surface, state bindings, events, lifecycle, and key decisions. Use this agent once per module in the code-to-spec pipeline for Medium and Large tier bundles.
critic-logic
Review code for logic bugs, unhandled edge cases, happy-path assumptions, input-validation gaps, and error-handling holes. Spawn in parallel with critic-security and critic-performance during /vdd-multi.
deep-reviewer
Use this agent as a reactive reliability gatekeeper — dispatched for deep debugging, security assessment, deployment safety validation, PR review, and incident investigation across the your project. Covers Go ( ), Python ( ), TypeScript/React ( ), and Kubernetes/GCP infrastructure. This agent does NOT write fixes — it…
performance-auditor
Use proactively on performance-sensitive changes. Flags O(n²) paths, N+1 queries, unnecessary re-renders, and hot-path waste. Reports with file:line refs and estimated impact. Does not fix.