review-data-eng

A review guide for checking data pipelines, which move data through sources, transformations, and outputs. It examines whether the flow is traceable, repeatable, recoverable, and able to handle changed formats.

In plain words
What is it for?
Use it to review pipeline plans and specifications, including data lineage, safe reruns, failure recovery, stage contracts, audit-file compatibility, replay, and backfills.
Why use it?
It helps find silent record loss, duplicate results, unclear ownership of files, and failures that cannot be resumed or replayed.

Agent for Claude Code

Install

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.

agentmods
npx agentmods add agents/pinecone-io/rings/review-data-eng
Clone the repo
git clone --depth 1 https://github.com/pinecone-io/rings

Made for: Claude Code.

Per session 46 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 396 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00046 $0.00396
Opus 5 $0.00023 $0.00198
Sonnet 5 $0.00009 $0.00079
Haiku 4.5 $0.00005 $0.00040

Measured 3d ago against content hash 65f38a569169, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

review-data-eng 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 3d 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.

.claude/agents/review-data-eng.md · 25 lines

What it actually says

You build and maintain data pipelines for a living. You think in terms of sources, transforms, sinks, lineage, and idempotency. You have been burned by pipelines that silently drop records, produce duplicate outputs, or can't be replayed after a failure. You care deeply about being able to answer "what produced this file and when?" You are skeptical of tools that don't make their data flow explicit.

You have been given a task by the replan process. Read the materials specified in your task, then review them through your lens.

What to look for

  • Data lineage — can I tell which run produced which file? Is every output's provenance traceable?
  • Idempotency — re-running from a checkpoint produces the same result? Outputs overwritten predictably?
  • Failure recovery — when a run fails mid-pipeline, is partial output clearly marked? Can I resume without reprocessing?
  • Phase contracts — are declared inputs/outputs enforced or validated? What happens when a stage produces nothing?
  • Format stability — are audit log formats (costs.jsonl, state.json, run.toml) versioned? Can I parse old files after an upgrade?
  • Replay and backfill — can I re-run a specific cycle or phase in isolation?
  • Silent failures — does anything appear to succeed but produce wrong or empty output without raising an error?
  • Cost accounting — can I track cost per pipeline stage over time for capacity planning?

Output format

One-paragraph overall impression, then numbered findings each with severity (nit / concern / blocker) and a concrete fix.

Changes

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.

  1. 3d ago First seen · 25 lines · 46 tokens per session scan A 65f38a569169

Subscribe to this mod's changes

review-data-eng is an agent published in the GitHub repository pinecone-io/rings (5 stars, last pushed 17d ago), licensed Apache-2.0. It adds 46 tokens to every session and 396 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 2026-08-31.

Related

Other agents, from other repositories

AGENTS

In-depth tutorials on LLMs, RAGs and real-world AI agent applications.

patchy631/ai-engineering-hub · 0 tokens

streaming

Stream responses from AI providers in real-time using callbacks that execute at different points in the streaming lifecycle.

activeagents/activeagent · 20 tokens

algorithm-expert

RL algorithm expert. Fire when working on GRPO/PPO/DAPO/GSPO/SAPO algorithms, reward functions, advantage normalization, loss computation, or training loop implementation.

redai-infra/Relax · 37 tokens

mlops-reviewer

MLOps / model lifecycle pre-implementation reviewer. Specialises in dataset versioning (DVC / LakeFS), distributed training cost budgets, model registry (MLflow / W&B), drift detection (Evidently / WhyLabs), bias / fairness audit (Fairlearn / AIF360), shadow + A/B model serving, and EU AI Act high-risk classification.…

avelikiy/great_cto · 105 tokens

by-epitope

Deep epitope analysis agent. Maps binding interfaces from PDB structures, classifies epitope type, assesses druggability, identifies cryptic sites, cross-references SAbDab, and generates hotspot arrays in BoltzGen entities YAML format.

001TMF/blatant-why · 58 tokens

prompt_engineer

Prompt engineering specialist for LLM prompt design, few-shot and chain-of-thought structuring, eval harnesses, and RAG retrieval quality. Use when the task requires writing or reviewing prompts, building evaluation datasets, tuning retrieval for a RAG system, or diagnosing regressions in LLM outputs. For example…

josstei/maestro-orchestrate · 98 tokens