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 agentmods add commands/devkindhq/shopifyql-skill/shopifyql-setupgit clone --depth 1 https://github.com/devkindhq/shopifyql-skillWhat 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 | $0.00033 | $0.01168 |
| Opus 5 | $0.00016 | $0.00584 |
| Sonnet 5 | $0.00007 | $0.00234 |
| Haiku 4.5 | $0.00003 | $0.00117 |
Grade F, and why
shopifyql-setup scanned grade F with 4 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Harvests environment variableshighData exfiltration
Enumerating or grepping the environment for keys collects credentials unrelated to what the mod says it does.
You are running the ShopifyQL plugin setup wizard. Your job is to check Python, collect credentials, and configure them so the plugin works across any project. Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
> sudo apt update && sudo apt install -y python3.11 python3.11-venv python3-pip Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
> curl https://pyenv.run | bash Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
> brew --version 2>/dev/null || /bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/brew.sh/install/HEAD/install.sh)" How it starts
The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are running the ShopifyQL plugin setup wizard. Your job is to check Python, collect credentials, and configure them so the plugin works across any project.
Security note: You must NEVER read .env or display a full access token back to the user at any point during this wizard.
Step 0 — Check Python environment
Before anything else, run:
python3.11 --version 2>/dev/null || echo "NOT_FOUND"
If Python 3.11 is found: confirm to the user — "Python 3.11 detected. ✓" — and proceed.
If NOT_FOUND: tell the user Python 3.11 is required and show the install options:
macOS (Homebrew — recommended):
brew install [email protected]After install, verify:
python3.11 --versionmacOS (without Homebrew): Download the installer from python.org/downloads — select version 3.11.x.
Verify Homebrew is installed first (if using Homebrew):
brew --version 2>/dev/null || /bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/brew.sh/install/HEAD/install.sh)"Ubuntu / Debian:
sudo apt update && sudo apt install -y python3.11 python3.11-venv python3-pipFedora / RHEL / CentOS:
sudo dnf install -y python3.11Other Linux (pyenv — works on any distro):
curl https://pyenv.run | bash pyenv install 3.11 pyenv global 3.11
Then check if the required Python packages are installed:
python3.11 -c "import shopifyql, pandas, certifi" 2>&1 || echo "MISSING_DEPS"
If MISSING_DEPS: show the install command and run it with user approval:
pip3.11 install 'shopifyql[all]' pandas certifi
Do not proceed to credential collection until Python 3.11 is confirmed working.
Step 1 — Explain how credentials work for this plugin
Before collecting anything, explain:
This is a Claude Code plugin — credentials are set once as OS environment variables and work across every project automatically. You won't need to run this setup again per project.
The script reads
SHOPIFY_STORE_URLandSHOPIFY_ACCESS_TOKENdirectly from the OS environment. No.envfile is loaded automatically.
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.
- 2d ago First seen · 128 lines · 33 tokens per session scan F d2e378d1e354
shopifyql-setup is a command published in the GitHub repository devkindhq/shopifyql-skill (7 stars, last pushed 3mo ago), licensed MIT. It adds 33 tokens to every session and 1,168 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it F with 4 findings (harvests environment variables, asks for root, downloads and executes remote code). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
launch-pmax
Launch a Google Ads Performance Max campaign with a complete asset group, audience signals, and (for ecom) listing groups. Built paused for review. Use when the user wants a new PMax campaign.
payments
Шаг 11 — подключить приём платежей через Polar (продукт, кнопка, webhook, portal, prod).
bundle-suggest
You are a senior E-commerce & Retail specialist. The user needs help with bundle suggest in the context of product catalogue optimisation, conversion rate, customer journey and retail analytics.
cart-abandonment
You are a senior E-commerce & Retail specialist. The user needs help with cart abandonment in the context of product catalogue optimisation, conversion rate, customer journey and retail analytics.
cro-audit
You are a senior E-commerce & Retail specialist. The user needs help with cro audit in the context of product catalogue optimisation, conversion rate, customer journey and retail analytics.
customer-segment
You are a senior E-commerce & Retail specialist. The user needs help with customer segment in the context of product catalogue optimisation, conversion rate, customer journey and retail analytics.