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 skills add TeamDijon/shopify-rules --skill discover-rule-topicsgit clone --depth 1 https://github.com/TeamDijon/shopify-rulesWrote 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/skills/teamdijon/shopify-rules/discover-rule-topics)<a href="https://agentmods.dev/skills/teamdijon/shopify-rules/discover-rule-topics"><img src="https://agentmods.dev/badge/skills/teamdijon/shopify-rules/discover-rule-topics/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.
<a href="https://agentmods.dev/skills/teamdijon/shopify-rules/discover-rule-topics"><img src="https://agentmods.dev/badge/skills/teamdijon/shopify-rules/discover-rule-topics.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00055 | $0.01651 |
| Opus 5.5 | $0.00022 | $0.00660 |
| Sonnet 5.5 | $0.00011 | $0.00330 |
| Haiku 4.5 | $0.00006 | $0.00165 |
Grade A, and why
discover-rule-topics 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 2mo 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.
How it starts
The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Discover rule topics from Shopify themes
You are exploring Shopify themes to discover patterns, techniques, and conventions that could become AI-consumable rules. Your goal is to enrich the topic backlog, NOT to write rules.
The search focus is: $ARGUMENTS
If $ARGUMENTS is empty or very broad (e.g., "general", "explore"), perform a wide exploration across multiple categories. If it names a specific area (e.g., "CSS patterns", "cart AJAX API", "metafield traversal"), focus your search on that domain.
Read these files before starting:
- references/category-definitions.md -- extended category taxonomy with search hints
- references/existing-coverage.md -- what Shopify's Horizon cursor rules already cover (avoid re-discovering these)
rules/BACKLOG.md-- existing topic backlog (don't re-discover these)rules/INDEX.md-- completed rules (don't suggest already-covered topics)
Phase 1 -- Orient
- Parse
$ARGUMENTSto determine the search scope:- Focused: a specific technology area, pattern type, or Shopify feature
- Broad: no arguments, or a high-level term like "explore" or "general"
- Read
rules/BACKLOG.mdto load existing topics. - Read
rules/INDEX.mdto load completed rules. - Check for Horizon cursor rule coverage using the three-level approach:
- If
shopify-themes/horizon/is present, list files inshopify-themes/horizon/.cursor/rules/for the latest coverage. - If Horizon is not present, consult
references/existing-coverage.mdfor a summary of what Shopify's cursor rules cover. - Either way, also check
references/existing-coverage.mdfor the "What is NOT covered" section -- these are prime opportunities for new rules.
- If
- Build an exclusion set from all sources -- these are topics you must NOT re-discover.
Phase 2 -- Search
Search across all themes in shopify-themes/. Use Explore agents to parallelize searches.
If shopify-themes/ is empty or contains no themes, lean on web research instead. Suggest the user adds themes to shopify-themes/ for richer discovery -- see the project README for recommended themes (Dawn and Horizon as starting points).
What ships with it
2 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.
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.
- 2mo ago First seen · 143 lines · 55 tokens per session scan A b1bb4eb06b5a
discover-rule-topics is a skill published in the GitHub repository TeamDijon/shopify-rules (12 stars, last pushed 9mo ago), licensed MIT. It adds 55 tokens to every session and 1,651 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.
discover-rule-topics compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| discover-rule-topicsTeamDijon/shopify-rules | Skill | 12 | 9mo ago | MIT | A | 55 | Claude Code |
| amazon-reviews-api-skillbrowser-act/skills | Skill | 6.3k | 3d ago | MIT | A | 124 | Claude Code, Codex |
| amazon-competitor-analyzerbrowser-act/skills | Skill | 6.3k | 3d ago | MIT | A | 48 | Claude Code, Codex |
| asc-subscription-localizationrorkai/app-store-connect-cli-skills | Skill | 1.1k | today | MIT | A | 60 | Claude Code |
| food-orderBitterbot-AI/bitterbot-desktop | Skill | 2.5k | today | MIT | A | 53 | Claude Code, Codex |
| external-purchasesrshankras/claude-code-apple-skills | Skill | 867 | today | MIT | A | 76 | Claude Code |
| Product Photoshoot Workflowjau123/MeiGen-AI-Design-MCP | Skill | 1.8k | yesterday | MIT | A | 111 | Claude Code |