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 New1Direction/korgex --skill data-pipelinesgit clone --depth 1 https://github.com/New1Direction/korgexWrote 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/new1direction/korgex/data-pipelines)<a href="https://agentmods.dev/skills/new1direction/korgex/data-pipelines"><img src="https://agentmods.dev/badge/skills/new1direction/korgex/data-pipelines/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/new1direction/korgex/data-pipelines"><img src="https://agentmods.dev/badge/skills/new1direction/korgex/data-pipelines.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 | $0.00017 | $0.00358 |
| Opus 5.5 | $0.00007 | $0.00143 |
| Sonnet 5.5 | $0.00003 | $0.00072 |
| Haiku 4.5 | $0.00002 | $0.00036 |
Grade A, and why
data-pipelines 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.
What it actually says
A data pipeline moves/transforms data between systems. The failure modes are about correctness and recovery, not just throughput.
- Idempotent + resumable. Pipelines fail partway. Design so re-running produces the same result (upsert by key, not blind insert) and can resume from a checkpoint rather than restarting from zero.
- Validate at the edges. Check schema/types/ranges on ingest; decide up front what to do with bad records — reject, quarantine, or repair — never silently drop.
- Idempotency keys + watermarks. Track what's been processed (a high-water mark or per-record key) so incremental runs don't double-count or miss late data.
- Batch sensibly. Process in chunks with bounded memory; don't load an entire dataset into RAM. Stream where you can.
- Make it observable. Record counts in/out/rejected per stage; a pipeline that silently processes 0 rows is a common, costly bug. Alert on anomalies.
- Schema evolution. Upstream schemas change — handle added/removed fields gracefully (defaults, versioning) rather than crashing the whole run.
- Separate extract / transform / load so each stage is testable in isolation, and keep raw inputs so you can reprocess after a transform bug.
Red flag: a non-resumable pipeline that must restart from scratch on any failure, or one with no record counts so you can't tell correct from silently-empty.
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 First seen · 29 lines · 17 tokens per session scan A 14366926ed4b
data-pipelines is a skill published in the GitHub repository New1Direction/korgex (5 stars, last pushed 15d ago), licensed MIT. It adds 17 tokens to every session and 358 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
app-ai-binding
Build AI features in generated apps using the platform-provided Workers AI binding. Load this skill for chatbots, summarization, classification, embeddings, semantic search, image understanding, transcription, translation, or other model inference.
mcp-builder
Guide the creation of high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when the user wants to build an MCP server to integrate an external API or service, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
code-review-pi
Review code for quality, run linters, check test coverage, fix issues, and enforce gates. Save the final report to ./specs/issues/003-code-review-pi/PROMPT.md. Use before committing changes.
adhd
Divergent ideation across model families — the same brainstorm, but each cognitive frame is handed to a different model (Claude sub-agent, OpenAI Codex, a cheap third via OpenCode) so the ideas diverge by frame and by model priors at once. Use for open design questions, architecture and API shape, naming, schema…
api-contract-reviewer
Conditional code-review persona, selected when the diff touches API routes, request/response types, serialization, versioning, or exported type signatures. Reviews code for breaking contract changes. Spawned by the ce:review-beta skill as part of a reviewer ensemble.
huggingface-community-evals
Run evaluations for Hugging Face Hub models using inspect-ai and lighteval on local hardware. Use for backend selection, local GPU evals, and choosing between vLLM / Transformers / accelerate. Not for HF Jobs orchestration, model-card PRs, .evalresults publication, or community-evals automation.