agentmods.dev

rp-source-csv

rp-source-csv is a skill for Claude Code from wix/skills. It costs 61 tokens per session (6,658 once invoked), scanned A, original, MIT.

A reference guide for importing product data from CSV files, which are plain-text tables commonly used for exports. It covers reading files, identifying ecommerce vendors, grouping rows into entities, and handling sets of files.

In plain words
What is it for?
Use it during discovery to profile CSV files and identify vendors, or during code generation to create readers that group and extract product data correctly.
Why use it?
It keeps CSV-specific import rules separate from the rest of a migration system. This helps generated readers interpret vendor exports consistently, including differences between empty and missing data.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is bash tests/run-all.sh source-csv.

Part of the wix plugin — 42 skills, 1 MCP server shipped together

not rated 36repo +2 changed 4d ago A scan SkillSpector: pass 61 tokens original MIT

Good fit Use it during discovery to profile CSV files and identify vendors, or during code generation to create readers that group and extract product data correctly.

Compare 6 skills from other repositories ↓
View source ↗ wix/skills
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/wix/skills
agentmods
npx agentmods add skills/wix/skills/rp-source-csv

Made for: Claude Code.

Or install wix, the plugin that ships this one along with the rest of its 42 skills, 1 MCP server.

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 rp-source-csv

README.md
[![agentmods](https://agentmods.dev/badge/skills/wix/skills/rp-source-csv/github.svg)](https://agentmods.dev/skills/wix/skills/rp-source-csv)
Your own site
<a href="https://agentmods.dev/skills/wix/skills/rp-source-csv"><img src="https://agentmods.dev/badge/skills/wix/skills/rp-source-csv/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 rp-source-csv

Your own site · 80×15
<a href="https://agentmods.dev/skills/wix/skills/rp-source-csv"><img src="https://agentmods.dev/badge/skills/wix/skills/rp-source-csv.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,658 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00061 $0.06658
Opus 5.5 $0.00024 $0.02663
Sonnet 5.5 $0.00012 $0.01332
Haiku 4.5 $0.00006 $0.00666

Measured 4d ago against content hash 7d51593114cc, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

rp-source-csv 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 4d ago.

The scan reads SKILL.md. This mod also ships 6 executable files (lib/canonical-record.js, lib/csv-fileset.js, lib/csv-fingerprint.js, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/wix-replatform/resources/rp-source-csv/SKILL.md · 482 lines

How it starts

The opening of the file, as written. The whole thing — 482 lines — stays where its author put it; the contents beside it link to each section on GitHub.

rp-source-csv

CSV source adapter. Owns every CSV-specific detail the platform-agnostic skills must not hardcode: how to parse a file, how to identify which vendor produced it, how its rows group into entities, how a set of files resolves into entity streams, and what a generated reader must get right.

When this skill is used

This is not a stage in the migration flow — it is a reference consulted by two stages:

  • rp-discovery consults the Capture section to sample the files and produce the canonical source-profile.md + source-schema.json.
  • rp-import-codegen consults the Read contract section to generate a reader that extracts CSV data correctly (grouping, derived entities, empty-vs-absent) into durable project-local files for the later import step.

rp-execute-import never consults this skill — by the time execution runs, the CSV-specific knowledge is already baked into the generated reader.

Platform identity

  • Source platform: csv — a file-provided flow, not a URL probe.
  • Set "platform": "csv" in the emitted source-schema.json, and record the detected vendor per file in sourceMeta.vendor / sourceMeta.sourceFiles[].
  • Record sourcePlatform=csv, sourceMode=files_only, and every input file in fileInputPaths in orchestration/decisions.json. Preflight requires no source env keys for csv; the files_only branch enforces a non-empty fileInputPaths instead.

Three layers

  1. A generic core — lib/csv-parse.js (parse, dialect detection, type sniffing) and lib/csv-layout.js (layout inference, derived entities). Knows nothing about commerce and handles any CSV, including hand-rolled ones.
  2. Per-vendor overlays — declarative JSON profiles under vendors/ that specialize the core with a vendor's fingerprint anchors, known layout, column→Wix pre-map, and quirks. v1 ships shopify, woocommerce, magento, bigcommerce.
  3. A fingerprint detector — lib/csv-fingerprint.js picks the overlay from the header set, or honors a user-stated vendor, and falls back to custom below the threshold.

Read the full file on GitHub · 482 lines

Files

What ships with it

11 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 4d ago Changed · +3 lines 7d51593114cc
  2. 1mo ago First seen · 479 lines · 61 tokens per session scan A c3fad0f7e691

Subscribe to this mod's changes

rp-source-csv is a skill published in the GitHub repository wix/skills (36 stars, last pushed yesterday), licensed MIT. It adds 61 tokens to every session and 6,658 once invoked, about $0.0002 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 2026-08-30.

Data and AIE-commerce
Related

Other skills, from other repositories

apify-product-data-setup

Wire an AI agent to live e-commerce product data using Apify's E-commerce Scraping Tool over MCP, either as runtime tool calls or as a scheduled refresh into a vector store. Trigger on "give my agent live product data", "my agent quotes stale prices", "connect Apify MCP to Claude or Cursor or n8n", "add product data…

apify/awesome-skills · 132 tokens

predictive-personalization

Use machine learning models to predict customer preferences and deliver personalized product recommendations, content, and offers based on behavioral signals.

finsilabs/awesome-ecommerce-skills · 28 tokens

linkfox-multimodal-extract-attributes

A product-image analysis tool that turns what appears in main listing photos into structured attributes, such as colour, shape, material, or style. It can also produce prompts describing the visual content.

linkfox-ai/linkfox-skills · 162 tokens

evo-taxonomy-merger

Merge product category taxonomies from multiple e-commerce platforms (Amazon, Facebook, Google Shopping) into a unified 5-level hierarchy. Use when you need to unify category systems across platforms with text normalization, embedding-based clustering, and constraint-validated naming.

Zhang-Henry/CoEvoSkills · 57 tokens

ai-api-gateway-migration-guide-ai-hive

A migration guide for teams comparing an AI API gateway, which connects software to multiple AI providers, with AI-HIVE.

wubin1836/ai-hive-agent-skills · 161 tokens

ai-api-task-ledger-ai-hive

An audit ledger for AI generation jobs, recording each input, model setup, price snapshot, task ID, status, result, and failure reason.

wubin1836/ai-hive-agent-skills · 161 tokens