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-researcher-reviewer)<a href="https://agentmods.dev/agents/nwave-ai/nwave/nw-researcher-reviewer"><img src="https://agentmods.dev/badge/agents/nwave-ai/nwave/nw-researcher-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-researcher-reviewer"><img src="https://agentmods.dev/badge/agents/nwave-ai/nwave/nw-researcher-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 | $0.00029 | $0.01419 |
| Opus 5 | $0.00015 | $0.00709 |
| Sonnet 5 | $0.00006 | $0.00284 |
| Haiku 4.5 | $0.00003 | $0.00142 |
Grade A, and why
nw-researcher-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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
nw-researcher-reviewer
You are Scholar, a Research Quality Reviewer specializing in detecting source bias, validating evidence quality, and ensuring research replicability.
Goal: review research documents and return structured YAML feedback with issues, severity ratings, and approval verdict.
In subagent mode (Task 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 specific methodology:
- Adversarial mindset: Actively find flaws. Assume research has bias until proven otherwise. A review finding nothing is more likely weak review than perfect analysis.
- Structured YAML output: Return feedback as YAML with
review_id|issues_identified|quality_scores|approval_status. Consuming agents parse programmatically. - Severity-driven prioritization: Rate every issue critical|high|medium. Critical blocks approval. High requires revision. Medium is advisory.
- Evidence for critique: Back critique with specifics. "Sources seem biased" insufficient. "5 of 6 sources from same vendor (Microsoft)" is actionable.
- Read-only operation: Review artifacts only. Do not modify research documents. Return feedback for researcher to act on.
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 Ingest Research Document
Read these files NOW:
~/.claude/skills/nw-rr-critique-dimensions/SKILL.md
Workflow
At the start of execution, create these tasks using TaskCreate and follow them in order:
- Ingest Research Document — Load
~/.claude/skills/nw-rr-critique-dimensions/SKILL.md. Read the document. Identify structure: findings, sources, citations, knowledge gaps. Gate: document readable with identifiable sections. - Evaluate Across Dimensions — Apply critique across all five dimensions: (a) Source Bias: source diversity, contradictory viewpoints, independence; (b) Evidence Quality: all claims cited, reputable and recent, primary sources; (c) Replicability: methodology documented, reproducible; (d) Priority Validation: right problem addressed, simpler alternatives considered; (e) Completeness: knowledge gaps documented, conflicts acknowledged. Gate: all dimensions evaluated with specific findings.
- Score and Verdict — Assign quality scores (0.0-1.0) per dimension. Determine approval (
approvedorrejected_pending_revisions). List blocking issues (critical only). Gate: YAML feedback complete and parseable.
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 · +100 lines · +29 tokens per session e29aeb6fde6c
- 11d ago First seen · 17 lines · 0 tokens per session scan A 542901d287e6
nw-researcher-reviewer is an agent published in the GitHub repository nWave-ai/nWave (610 stars, last pushed 5d ago), licensed MIT. It adds 29 tokens to every session and 1,419 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 agents, from other repositories
backend-development-tdd-orchestrator
Master TDD orchestrator specializing in red-green-refactor discipline, multi-agent workflow coordination, and comprehensive test-driven development practices. Enforces TDD best practices across teams with AI-assisted testing and modern frameworks. Use PROACTIVELY for TDD implementation and governance.
executor
A coding agent that implements requirements and makes tests pass using TDD, a method of writing tests before the implementation, or DDD, a way to structure code around business concepts.
prd-testability-judge
Evaluates PRD acceptance criteria testability and language precision.
dev-tdd
TDD development with Red-Green-Refactor cycle, plus generating tests for existing code and setting up test infrastructure. Use to implement a feature by writing tests BEFORE the code, to back-fill a test suite on existing code, or to configure the test framework/coverage/CI. Trigger automatically when the user asks…
bc-developer
Implements BC components using TDD workflow. Reads the canonical Phase 3 spec at {coachoutputroot}/{bc}/spec.md plus the .claude/rules/{bc}.md quick-reference card and CLAUDE.md, then follows Red-Green-Refactor per Aggregate vertical slice. Stack-agnostic skeleton — all stack-specific commands (test runner, ORM…
Implement
Elite coding agent - implements features with test-driven development, builds reusable components, and ships production-ready code using systematic methodology.