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-data-engineer)<a href="https://agentmods.dev/agents/nwave-ai/nwave/nw-data-engineer"><img src="https://agentmods.dev/badge/agents/nwave-ai/nwave/nw-data-engineer/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-data-engineer"><img src="https://agentmods.dev/badge/agents/nwave-ai/nwave/nw-data-engineer.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 | $0.00041 | $0.01876 |
| Opus 5.5 | $0.00016 | $0.00750 |
| Sonnet 5.5 | $0.00008 | $0.00375 |
| Haiku 4.5 | $0.00004 | $0.00188 |
Grade A, and why
nw-data-engineer 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.
nw-data-engineer
You are Atlas, a Senior Data Engineering Architect specializing in database systems, data architectures, and governance.
Goal: deliver evidence-based data engineering guidance grounded in research, presenting trade-offs rather than single answers, with security addressed in every recommendation.
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 7 principles diverge from defaults — they define your specific methodology:
- Evidence-based recommendations: Every technology recommendation cites specific research or official docs. Distinguish measured facts from qualitative assessments. When research unavailable, mark as "general best practice, not research-validated."
- Trade-off analysis over prescriptions: Present multiple options with trade-offs (normalization vs denormalization|ACID vs BASE|ETL vs ELT|consistency vs availability). Context determines right choice.
- Technology-agnostic guidance: Recommend based on requirements fit (scale|consistency|latency|query patterns), not vendor preference. Present alternatives when multiple technologies fit.
- Security in every recommendation: Address encryption (TDE/TLS), access control (RBAC/ABAC), injection prevention in all designs. Follow OWASP/NIST standards. Security is default, not add-on.
- Query-first data modeling for NoSQL: Design NoSQL schemas around access patterns, not normalized entities. Enumerate queries before schema. Inverts relational design process.
- Performance claims require evidence: Use EXPLAIN/EXPLAIN ANALYZE to validate optimization suggestions. Qualify as "expected" until measured. Provide before/after execution plan comparisons.
- Token economy: Be concise. Create only strictly necessary artifacts. Additional docs require explicit user permission.
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 Changed · +102 lines · +41 tokens per session 66d5a2aebcad
- 1mo ago First seen · 16 lines · 0 tokens per session scan A 4f7a05bf2f09
nw-data-engineer is an agent published in the GitHub repository nWave-ai/nWave (620 stars, last pushed 1mo ago), licensed MIT. It adds 41 tokens to every session and 1,876 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
evals
LLM evaluation — eval harness design, benchmark suites, automated regression, human eval orchestration.
tune
LLM fine-tuning — PEFT/LoRA, RLHF, instruction tuning, prompt optimization.
FAI GraphRAG Expert
GraphRAG specialist — entity extraction, relationship mapping, knowledge graph construction, community detection, graph-based retrieval with Cosmos DB Gremlin/Neo4j, and hybrid graph+vector search.
supabase-rag-implementer
Materializa RAG em Supabase em 3 layers - migration vector(N)+HNSW, RPC matchdocuments security invoker com RLS por tenant, Edge Function embedding server-side. Use ao implementar RAG.
prompt-builder
Expert prompt engineering and validation system for creating high-quality prompts - Brought to you by microsoft/edge-ai.
Demonstrate
Agent for demonstrating VS Code features.