AutoRAG-Research: Command for Claude Code

.claude/commands/implement-pipeline.md

implement-pipeline is a command for Claude Code from NomaDamas/AutoRAG-Research. It costs 27 tokens per session (1,316 once invoked), scanned A, original, Apache-2.0.

A guided workflow for turning a research paper into a working retrieval or generation data pipeline.

In plain words
What is it for?
It extracts the algorithm from a paper, creates a design, writes tests, implements the pipeline, and checks the finished code.
Why use it?
It breaks a research implementation into separate analysis, design, testing, coding, and validation stages with review points.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions subagents; names the AskUserQuestion tool.

This is NomaDamas/AutoRAG-Research's own configuration. It tells Claude Code how to work on AutoRAG-Research 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 AutoRAG-Research configures →

Reuse

Borrowing it

Nothing to install: this file belongs to NomaDamas/AutoRAG-Research. 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/NomaDamas/AutoRAG-Research/main/.claude/commands/implement-pipeline.md
Clone the repo
git clone --depth 1 https://github.com/NomaDamas/AutoRAG-Research

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 implement-pipeline

README.md
[![agentmods](https://agentmods.dev/badge/commands/nomadamas/autorag-research/implement-pipeline.svg)](https://agentmods.dev/commands/nomadamas/autorag-research/implement-pipeline)
Your own site
<a href="https://agentmods.dev/commands/nomadamas/autorag-research/implement-pipeline"><img src="https://agentmods.dev/badge/commands/nomadamas/autorag-research/implement-pipeline.svg" alt="Measured on agentmods" height="20"></a>
Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,316 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 $0.00027 $0.01316
Opus 5 $0.00014 $0.00658
Sonnet 5 $0.00005 $0.00263
Haiku 4.5 $0.00003 $0.00132

Measured 7d ago against content hash b393a16aa612, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

implement-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 7d 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/implement-pipeline.md · 180 lines

How it starts

The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pipeline Implementation Workflow Orchestrator

This skill orchestrates the complete pipeline implementation workflow using specialized sub-agents with mandatory human checkpoints.

Arguments

  • $ARGUMENTS: Paper URL (arxiv, PDF path, or web URL) or algorithm name if paper already analyzed

Prerequisites

  • Research paper accessible (URL, arxiv link, or local PDF)
  • Docker PostgreSQL running for test validation (make docker-up)

Workflow Overview

Phase 1: Paper Analysis      → Pipeline_Analysis.json
Phase 2: Architecture Design → Pipeline_Design.md (HUMAN CHECKPOINT)
Phase 3: Test Writing        → test_[name]_pipeline.py (HUMAN CHECKPOINT)
Phase 4: Implementation      → [name].py
Phase 5: Validation          → All checks pass (HUMAN CHECKPOINT)

Phase 1: Paper Analysis

Agent: pipeline-paper-analyst

Task(subagent_type="pipeline-paper-analyst", prompt="Analyze paper: $ARGUMENTS. Extract algorithm details and create Pipeline_Analysis.json")

Output: Pipeline_Analysis.json in project root

After Phase 1:

  • Present summary of extracted algorithm
  • Confirm pipeline type (retrieval/generation)
  • Ask if user wants to proceed to design phase

Phase 2: Architecture Design (HUMAN CHECKPOINT)

Agent: pipeline-architecture-mapper

Prerequisites: Pipeline_Analysis.json exists

Task(subagent_type="pipeline-architecture-mapper", prompt="Design architecture for [algorithm_name] based on Pipeline_Analysis.json")

Output: Pipeline_Design.md in project root

MANDATORY Human Review:

AskUserQuestion:
  question: "Review the Pipeline_Design.md. How would you like to proceed?"
  header: "Design Review"
  options:
    - label: "Approve Design"
      description: "Design looks good. Proceed to test writing (TDD Phase)."
    - label: "Request Changes"
      description: "I have feedback. Revise the design."
    - label: "Reject"
      description: "Stop workflow. Design needs major rework."

Handle Response:

  • Approve: Proceed to Phase 3
  • Request Changes: Get feedback, re-invoke agent, repeat until approved
  • Reject: Stop workflow, acknowledge rejection

Read the full file on GitHub · 180 lines

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. 7d ago First seen · 180 lines · 27 tokens per session scan A b393a16aa612

Subscribe to this mod's changes

implement-pipeline is a command published in the GitHub repository NomaDamas/AutoRAG-Research (148 stars, last pushed 29d ago), licensed Apache-2.0. It adds 27 tokens to every session and 1,316 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.