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 agentmods add agents/pinecone-io/rings/review-data-enggit clone --depth 1 https://github.com/pinecone-io/ringsWhat 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 | $0.00046 | $0.00396 |
| Opus 5 | $0.00023 | $0.00198 |
| Sonnet 5 | $0.00009 | $0.00079 |
| Haiku 4.5 | $0.00005 | $0.00040 |
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.
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.
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.
- 3d ago First seen · 25 lines · 46 tokens per session scan A 65f38a569169
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.
Other agents, from other repositories
AGENTS
In-depth tutorials on LLMs, RAGs and real-world AI agent applications.
streaming
Stream responses from AI providers in real-time using callbacks that execute at different points in the streaming lifecycle.
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.
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.…
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.
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…