explore-feature

explore-feature is a command for coding agents from mentilead/shopify-app-skill. It costs 0 tokens per session (431 once invoked), scanned A, original, MIT.

An eight-step planning review for a new Shopify feature before implementation. It covers Shopify's documented constraints, architecture choices, security, code integration points, billing access, monitoring, testing, and breaking-change risks.

In plain words
What is it for?
Use it to explore features such as order webhooks, Shopify Flow connectors, or billing for a paid tier.
Why use it?
It exposes technical, security, billing, and operational issues before they become expensive changes in the codebase.

Command

Part of the shopify-app-skill plugin — 1 skill, 10 commands shipped together

Install

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.

agentmods
npx agentmods add commands/mentilead/shopify-app-skill/explore-feature
Clone the repo
git clone --depth 1 https://github.com/mentilead/shopify-app-skill

Or install shopify-app-skill, the plugin that ships this one along with the rest of its 1 skill, 10 commands.

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 explore-feature

README.md
[![agentmods](https://agentmods.dev/badge/commands/mentilead/shopify-app-skill/explore-feature.svg)](https://agentmods.dev/commands/mentilead/shopify-app-skill/explore-feature)
Your own site
<a href="https://agentmods.dev/commands/mentilead/shopify-app-skill/explore-feature"><img src="https://agentmods.dev/badge/commands/mentilead/shopify-app-skill/explore-feature.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 431 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.00431
Opus 5 $0.00000 $0.00216
Sonnet 5 $0.00000 $0.00086
Haiku 4.5 $0.00000 $0.00043

Measured 4d ago against content hash 95c98ee73f16, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

explore-feature 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.

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.

commands/explore-feature.md · 27 lines

What it actually says

Explore Feature

Run the 8-step feature exploration framework before implementing a new Shopify feature.

Arguments

$ARGUMENTS = description of the feature to explore (e.g., "order webhooks", "Flow connectors", "billing for pro tier")

Instructions

  1. Read the feature exploration framework from .claude/skills/shopify-app/references/feature-exploration.md.
  2. Parse the feature description from $ARGUMENTS. If empty, ask the user what feature they want to explore.
  3. Run through each of the 8 steps for the described feature:
    • Step 1: Shopify Docs Research — identify hard constraints from Shopify docs
    • Step 2: Architecture Decision Analysis — document key decisions and trade-offs
    • Step 3: Security Hardening Checklist — review security concerns
    • Step 4: Code Path Injection Mapping — trace integration points in existing code
    • Step 5: Plan Gating Analysis — determine billing tier access
    • Step 6: Monitoring & Observability — define metrics and alarms
    • Step 7: Testing Strategy by Environment — plan tests per environment
    • Step 8: Breaking Change Risk Assessment — identify non-changeable contracts
  4. Use the "When to Use" table at the bottom of the framework to determine which steps are relevant. Skip steps that don't apply and explain why.
  5. For each relevant step, fill in the templates and checklists with specifics for the described feature.
  6. Cross-reference other skill references as needed (security-patterns.md, billing-patterns.md, testing-patterns.md, cdk-infrastructure.md).
  7. Summarize findings and flag any blockers or open questions before implementation begins.
  8. After presenting the summary, ask the user: "Do you want me to update the relevant feature in roadmap.md?" If yes, read roadmap.md, find the matching feature section, and update it with the constraints, decisions, and risks discovered during exploration.
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 First seen · 27 lines · 0 tokens per session scan A 95c98ee73f16

Subscribe to this mod's changes

explore-feature is a command published in the GitHub repository mentilead/shopify-app-skill (5 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 431 tokens. 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.