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/mentilead/shopify-app-skill/explore-featuregit clone --depth 1 https://github.com/mentilead/shopify-app-skillWrote 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.
[](https://agentmods.dev/commands/mentilead/shopify-app-skill/explore-feature)<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>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.
| Model | Per session | Once 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 |
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.
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
- Read the feature exploration framework from
.claude/skills/shopify-app/references/feature-exploration.md. - Parse the feature description from
$ARGUMENTS. If empty, ask the user what feature they want to explore. - 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
- 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.
- For each relevant step, fill in the templates and checklists with specifics for the described feature.
- Cross-reference other skill references as needed (security-patterns.md, billing-patterns.md, testing-patterns.md, cdk-infrastructure.md).
- Summarize findings and flag any blockers or open questions before implementation begins.
- After presenting the summary, ask the user: "Do you want me to update the relevant feature in
roadmap.md?" If yes, readroadmap.md, find the matching feature section, and update it with the constraints, decisions, and risks discovered during exploration.
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.
- 4d ago First seen · 27 lines · 0 tokens per session scan A 95c98ee73f16
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.
Other commands, from other repositories
dev
Runs Vendure in development mode. By default it starts three processes: the GraphQL server (ts-node ./src/index.ts), the worker (ts-node ./src/index-worker.ts), and the dashboard (a Vite dev server).
eval-merge
Use the Read tool to load .skill-compass/{skill-name}/manifest.json. Verify.
cti-report
Render case deliverables — relationship graph (PNG/SVG/Mermaid) and a polished PDF/DOCX assessment. Usage: /cti-report [--graph|--pdf].
reskin
Extract a measured design signature (type ramp, accent + its budget, grid unit, radius, layout) from a reference image or site, write it to signature.json, and drive the build to match it — "steal this vibe" as a spec, not pixels.
local-env
Point this machine at its claude-prove checkout — writes the per-machine env block into .claude/settings.local.json.
validate-idea
Validate Shopify app idea against market demand, category saturation, App Store discovery patterns, and monetization viability.