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 skills add vaquarkhan/data-engineering-agent-skills --skill safe-backfill-and-replay-orchestrationgit clone --depth 1 https://github.com/vaquarkhan/data-engineering-agent-skillsWrote 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/skills/vaquarkhan/data-engineering-agent-skills/safe-backfill-and-replay-orchestration)<a href="https://agentmods.dev/skills/vaquarkhan/data-engineering-agent-skills/safe-backfill-and-replay-orchestration"><img src="https://agentmods.dev/badge/skills/vaquarkhan/data-engineering-agent-skills/safe-backfill-and-replay-orchestration/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/skills/vaquarkhan/data-engineering-agent-skills/safe-backfill-and-replay-orchestration"><img src="https://agentmods.dev/badge/skills/vaquarkhan/data-engineering-agent-skills/safe-backfill-and-replay-orchestration.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 | $0.00061 | $0.01005 |
| Opus 5 | $0.00030 | $0.00502 |
| Sonnet 5 | $0.00012 | $0.00201 |
| Haiku 4.5 | $0.00006 | $0.00101 |
Grade A, and why
safe-backfill-and-replay-orchestration 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 8d 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Safe Backfill And Replay Orchestration
Overview
Backfills are among the highest-risk data engineering operations. Agents that rerun jobs without bounded windows, publish gates, or reconciliation checks routinely cause double-counting, corrupted metrics, and downstream trust loss. This skill blocks execution until a written replay plan, rollback path, and validation gates exist.
When to Use
- running
/backfillor any historical reprocessing request - repairing a failed or partial publish window
- replaying events or partitions after an incident
- changing transformation logic that requires recomputation
- cutting over to new pipeline behavior with overlapping data windows
Always load this skill before orchestration-and-backfills execution steps. Treat plan approval as a hard gate, not a suggestion.
Workflow
-
Stop before execution. Do not trigger reruns, delete partitions, or open publish paths until the replay plan is drafted and reviewed.
-
Run the backfill guard hook when available. Execute
hooks/backfill-guard.shorhooks/backfill-guard.ps1before planning destructive or wide-impact replay work. -
Draft the replay plan from
templates/backfill-plan.yaml. Require explicit values for:- affected time window and partitions
- source of truth and downstream targets
- execution mode (
replay,merge,overwrite) and idempotency proof - publish pause state and downstream notifications
- rollback strategy in plain language
- validation checks with thresholds
- required approvals
-
Separate incremental from backfill semantics. Confirm:
- concurrency limits differ from daily runs when needed
- watermark or cursor behavior will not skip or duplicate late data
- metric definitions remain comparable across the replay window
- downstream consumers know publish is paused
-
Define reconciliation gates before reopening publish. Load
data-reconciliation-and-financial-controlswhen correctness must be proven. Minimum gates:- row count or volume parity within threshold
- duplicate check on business keys
- metric reconciliation for business-critical aggregates
- contract checks on schema and nullability
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.
- 8d ago First seen · 110 lines · 61 tokens per session scan A 756cfd872322
safe-backfill-and-replay-orchestration is a skill published in the GitHub repository vaquarkhan/data-engineering-agent-skills (45 stars, last pushed 3mo ago), licensed MIT. It adds 61 tokens to every session and 1,005 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
kafka-shadowtraffic
Generate a ShadowTraffic configuration to populate a Kafka topic with realistic synthetic data. Discovers the target topic, its key and value schemas, and the correct serializers from the live cluster via any attached Kafka MCP server, then writes a ready-to-run shadowtraffic-config.json and Docker command. Use when…
spark-training-gotchas
Preflight and diagnose the ten known failure modes for ML training on NVIDIA DGX Spark. Use when a training run on DGX Spark fails to start, OOMs below the 128GB limit, slows down mid-run, or before any multi-hour training job on GB10.
9router
Entry point for 9Router — local/remote AI gateway with OpenAI-compatible REST for chat, image, TTS, embeddings, web search, web fetch. Use when the user mentions 9Router, NINEROUTERURL, or wants AI without writing provider boilerplate. This skill covers setup + indexes capability skills; fetch the relevant capability…
aeon
This skill should be used for time series machine learning tasks including classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search. Use when working with temporal data, sequential patterns, or time-indexed observations requiring specialized algorithms beyond standard…
lookml_ingest
Map a LookML view/model/explore into ktx semantic layer sources. Covers the LookML to ktx primitive table, provenance tagging, and three worked examples (overlay, standalone from derivedtable, standalone with sqlalwayswhere). Load when the turn contains .lkml content.
markitdown
Convert files and office documents to Markdown. Supports PDF, DOCX, PPTX, XLSX, images (with OCR), audio (with transcription), HTML, CSV, JSON, XML, ZIP, YouTube URLs, EPubs and more.