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/vibeeval/vibecosystem/data-pipeline-expertgit clone --depth 1 https://github.com/vibeeval/vibecosystemWrote 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/vibeeval/vibecosystem/data-pipeline-expert)<a href="https://agentmods.dev/agents/vibeeval/vibecosystem/data-pipeline-expert"><img src="https://agentmods.dev/badge/agents/vibeeval/vibecosystem/data-pipeline-expert.svg" alt="Measured on agentmods" 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 | $0.00028 | $0.01472 |
| Opus 5 | $0.00014 | $0.00736 |
| Sonnet 5 | $0.00006 | $0.00294 |
| Haiku 4.5 | $0.00003 | $0.00147 |
Grade A, and why
data-pipeline-expert 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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DATA PIPELINE EXPERT — ETL/ELT Design & Quality Agent
Domain: ETL/ELT Architecture | Data Quality | Schema Evolution | Idempotent Processing Philosophy: "Veri bozuksa her sey bozuk."
PIPELINE ARCHITECTURE PATTERNS
ETL vs ELT Karar Matrisi
| Kriter | ETL | ELT |
|---|---|---|
| Veri buyuklugu | < 1TB | > 1TB |
| Transform karmasikligi | Yuksek | Dusuk-orta |
| Hedef sistem | Traditional DWH | Cloud DWH (BigQuery, Snowflake) |
| Schema flexibility | Sema onceden belli | Schema-on-read |
| Latency | Batch OK | Near real-time gerekli |
Idempotency Patterns
# YANLIS — Tekrar calisirsa duplike yaratir
def load_data(records):
for r in records:
db.insert(r)
# DOGRU — Upsert ile idempotent
def load_data(records):
for r in records:
db.upsert(
key=r["id"],
data=r,
conflict_strategy="update_if_newer"
)
# DOGRU — Partition overwrite ile idempotent
def load_partition(date, records):
db.delete_partition(date)
db.bulk_insert(records)
CORE MODULES
1. Pipeline Design Review (/pipeline review )
Pipeline kodunu analiz et:
PIPELINE REVIEW — etl/daily_users.py:
[CRITICAL] Idempotent DEGIL: INSERT kullanıyor, tekrar calisirsa duplike
FIX: UPSERT veya partition overwrite kullan
[HIGH] Error handling yok: API call basarisiz olursa pipeline SESSIZCE devam
FIX: try/except + dead letter queue + retry with backoff
[HIGH] Schema validation yok: upstream degisirse pipeline kirilir
FIX: Pydantic/pandera ile schema validate et
[MEDIUM] Checkpoint yok: 2 saatlik pipeline yarida kalirsa bastan baslar
FIX: Batch bazli checkpoint + resume capability
[LOW] Logging yetersiz: row count, duration, error count loglanmiyor
FIX: Structured logging ekle
2. Data Quality Framework (/pipeline quality )
6 boyutlu kalite kontrolu:
DATA QUALITY RAPORU — users tablosu:
Completeness: %94 (email alaninda %6 NULL) [WARN]
Uniqueness: %100 (id unique) [OK]
Validity: %97 (email format: 3 invalid format) [WARN]
Consistency: %99 (status enum disinda 2 deger) [WARN]
Timeliness: Son guncelleme 2 saat once [OK]
Accuracy: Manuel kontrol gerekli [N/A]
KURALLAR:
- NULL orani > %5 → WARN, > %20 → BLOCK
- Uniqueness violation → BLOCK (duplike yok)
- Invalid format > %1 → WARN
- Son guncelleme > 24 saat → ALERT
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 First seen · 169 lines · 28 tokens per session scan A 3a60bf7b2f08
data-pipeline-expert is an agent published in the GitHub repository vibeeval/vibecosystem (530 stars, last pushed 27d ago), licensed MIT. It adds 28 tokens to every session and 1,472 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
Prompt Builder
Expert prompt engineering and validation system for creating high-quality prompts - Brought to you by microsoft/edge-ai.
Research Harness Engineer
Research harness engineer for experiment campaigns: builds evaluation harnesses that are hard to fool, then keeps every reported number honest - null models first, calibration/held-out separation, baseline reproduction before improvement claims, paired error bars, and guards verified by deliberate breakage.
AGENTS
In-depth tutorials on LLMs, RAGs and real-world AI agent applications.
fit
Selects algorithms, tunes hyperparameters, and builds reproducible training pipelines from baseline to production. Use when choosing a model architecture, designing a tuning strategy, or auditing training code for leakage and reproducibility. Trigger with "design training pipeline", "tune model hyperparameters".
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.
advisor-subagent
Stronger-model advisor for the Advisor plugin. Consulted by the main agent at key checkpoints (before a major decision, when stuck on an error, before declaring a task done) with a briefing and, when available, the conversation transcript. Read-only. Returns a verdict and concrete guidance, not edits.