agentspec: Command for Claude Code

.claude/commands/data-engineering/ai-pipeline.md

ai-pipeline is a command for Claude Code from luanmorenommaciel/agentspec. It costs 19 tokens per session (366 once invoked), scanned A, original, MIT.

A command for scaffolding data and AI pipelines, including RAG, embeddings, feature stores, and text-to-SQL. RAG retrieves relevant documents before an AI model generates an answer.

In plain words
What is it for?
Use it to plan document-embedding pipelines, vector database indexes, feature stores, or AI tools that turn natural-language questions into SQL.
Why use it?
It provides a starting structure for moving data into search, machine-learning, or AI workflows instead of designing each pipeline from scratch.

Command for Claude Code

Written for Claude Code: installed under .claude/.

This is luanmorenommaciel/agentspec's own configuration. It tells Claude Code how to work on agentspec itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything agentspec configures →

Reuse

Borrowing it

Nothing to install: this file belongs to luanmorenommaciel/agentspec. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/luanmorenommaciel/agentspec/main/.claude/commands/data-engineering/ai-pipeline.md
Clone the repo
git clone --depth 1 https://github.com/luanmorenommaciel/agentspec

Made for: Claude Code.

Wrote 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.

agentmods badge for ai-pipeline

README.md
[![agentmods](https://agentmods.dev/badge/commands/luanmorenommaciel/agentspec/ai-pipeline/github.svg)](https://agentmods.dev/commands/luanmorenommaciel/agentspec/ai-pipeline)
Your own site
<a href="https://agentmods.dev/commands/luanmorenommaciel/agentspec/ai-pipeline"><img src="https://agentmods.dev/badge/commands/luanmorenommaciel/agentspec/ai-pipeline/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.

agentmods 80×15 button for ai-pipeline

Your own site · 80×15
<a href="https://agentmods.dev/commands/luanmorenommaciel/agentspec/ai-pipeline"><img src="https://agentmods.dev/badge/commands/luanmorenommaciel/agentspec/ai-pipeline.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 366 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00019 $0.00366
Opus 5 $0.00010 $0.00183
Sonnet 5 $0.00004 $0.00073
Haiku 4.5 $0.00002 $0.00037

Measured 8d ago against content hash 250257840df8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

ai-pipeline 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.

.claude/commands/data-engineering/ai-pipeline.md · 56 lines

What it actually says

AI Pipeline Command

Scaffold RAG pipelines, embedding workflows, feature stores, and text-to-SQL

Usage

/ai-pipeline <description-or-file>

Examples

/ai-pipeline "RAG pipeline for internal docs with pgvector"
/ai-pipeline "Embedding pipeline from S3 PDFs to Pinecone"
/ai-pipeline "Feature store setup with Feast for ML models"
/ai-pipeline "Text-to-SQL agent for analytics queries"

What This Command Does

  1. Invokes the ai-data-engineer agent
  2. Analyzes your AI/ML data requirements
  3. Loads KB patterns from ai-data-engineering and streaming domains
  4. Generates:
    • RAG pipeline architecture and code
    • Embedding pipeline with chunking strategies
    • Vector database setup and indexing
    • Feature store definitions
    • Text-to-SQL prompt templates

Agent Delegation

Agent Role
ai-data-engineer Primary — RAG, embeddings, vector DBs, features
streaming-engineer Escalation — real-time embedding pipelines
data-quality-analyst Escalation — embedding quality metrics

KB Domains Used

  • ai-data-engineering — RAG pipelines, vector databases, feature stores, LLMOps
  • streaming — real-time embedding ingestion
  • data-quality — embedding quality, drift detection

Output

The agent generates pipeline code, configuration, and architecture documentation for your AI data workflow.

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. 8d ago First seen · 56 lines · 19 tokens per session scan A 250257840df8

Subscribe to this mod's changes

ai-pipeline is a command published in the GitHub repository luanmorenommaciel/agentspec (246 stars, last pushed today), licensed MIT. It adds 19 tokens to every session and 366 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 2026-09-01.