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 goodbarber/goodbarber-skills --skill shop-orphan-productsgit clone --depth 1 https://github.com/goodbarber/goodbarber-skillsWrote 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/goodbarber/goodbarber-skills/shop-orphan-products)<a href="https://agentmods.dev/skills/goodbarber/goodbarber-skills/shop-orphan-products"><img src="https://agentmods.dev/badge/skills/goodbarber/goodbarber-skills/shop-orphan-products/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/goodbarber/goodbarber-skills/shop-orphan-products"><img src="https://agentmods.dev/badge/skills/goodbarber/goodbarber-skills/shop-orphan-products.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 | $0.00102 | $0.01280 |
| Opus 5 | $0.00051 | $0.00640 |
| Sonnet 5 | $0.00020 | $0.00256 |
| Haiku 4.5 | $0.00010 | $0.00128 |
Grade A, and why
shop-orphan-products 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.
How it starts
The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an assistant that executes this skill workflow for the user.
You MUST execute the required tool workflow and return the output in the required format sections. Do not skip required steps and do not replace the required report/template with a short summary.
Goal
Detect every product not attached to a collection and provide actionable assignment suggestions so the user can clean catalog structure quickly.
Access contract
READ_ONLY.READ_WRITEonly if the user asks to apply collection assignments.
Input contract
- Optional
statusfilter:- default:
PUBLISHEDonly - supported overrides:
INVISIBLE,DRAFT,DEMO, or any explicit status combination requested by the user
- default:
- Optional
top_nto limit displayed rows (default: all orphan products) - Optional "strict mode":
- suggest only existing collections with strong similarity
- otherwise allow "create a new collection" recommendations
- Optional apply mode after report:
high_only: apply only High confidence recommendationsmedium_and_above: apply Medium + Highall: apply every recommendationmanual: user provides specific product + one or more collection targets
Required Tool Workflow (strict order)
Follow the sequence below exactly when those tools are available for the request context.
- Load catalog:
shop_list_productswith requested status scope.
- Load collection reference:
shop_list_collectionsto build candidate targets and known themes.
- Detect orphan products:
- Product is orphan if
collectionsis empty or missing.
- Product is orphan if
- Find assignment candidates for each orphan:
- Use title, tags, description keywords, and nearby product naming patterns.
- If obvious match to an existing collection exists, recommend that one.
- If no reliable match, recommend a new collection theme.
- Build direct back-office links:
- Resolve the shop root domain through the internal runtime domain resolver (repository-level guidance).
- Extract the domain label from the resolved shop root URL.
- Build each product edit link via the internal runtime URL resolver.
- Render a short localized clickable label in the conversation language
(examples:
link,lien,enlace).
- Render fixed-format report:
- orphan table + assignment plan table.
- If no explicit status filter was requested, add a short note that this
run only includes
PUBLISHEDproducts and mention that non-published statuses can be included on request.
- Prompt for assignment action:
- Ask the user whether to apply:
- assignment plan as
high_only,medium_and_above, orall - manual mapping (
product -> one or more collections)
- assignment plan as
- If user confirms an apply mode, switch to apply flow:
- Resolve collection names to IDs via
shop_list_collections. - Resolve product names to IDs from the orphan table.
- Show dry-run change list (product, current collections, target collections).
- Require explicit confirmation.
- Apply product updates with
shop_update_productone product at a time. - Verify each updated product with
shop_get_product.
- Resolve collection names to IDs via
- Ask the user whether to apply:
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 · 140 lines · 102 tokens per session scan A d357b16a23f4
shop-orphan-products is a skill published in the GitHub repository goodbarber/goodbarber-skills (2 stars, last pushed 2d ago), licensed Unlicense. It adds 102 tokens to every session and 1,280 once invoked, about $0.0005 per session on Opus 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 2026-09-08.
Other skills, from other repositories
shop
Shop catalog search, checkout, order tracking, returns.
shopify
Query Shopify Admin/Storefront GraphQL APIs via curl.
stripe-link-cli
Agent payments via Stripe Link — cards, SPT, approvals.
product-price-monitor
Watch product, flight, or listing prices; alert on target.
17-pricing-strategy
Dung khi can dat gia hoac sua gia san pham va dich vu — chon mo hinh gia, thiet ke bac goi, neo gia, chien thuat giam gia, so sanh gia voi doi thu va cach bay bang gia tren trang. Kich hoat khi user nhac 'dinh gia san pham', 'chien luoc gia', 'pricing', 'nen ban bao nhieu tien', 'chia goi dich vu', 'co nen giam gia…
11-thiet-lap-kenh
Dung khi can MO va thiet lap kenh marketing tu con so khong — TikTok Brand, Zalo OA, Fanpage, Instagram Business, Google Business Profile, TikTok Shop, tai khoan email: checklist setup 4 giai doan, thong so ky thuat, lien ket cheo va ke hoach 30 ngay dau. Kich hoat khi user nhac 'thiet lap kenh', 'tao fanpage moi'…