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.
git clone --depth 1 https://github.com/danielrosehill/Claude-Israel-Shopping-PluginWrote 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/danielrosehill/claude-israel-shopping-plugin/search-zap)<a href="https://agentmods.dev/commands/danielrosehill/claude-israel-shopping-plugin/search-zap"><img src="https://agentmods.dev/badge/commands/danielrosehill/claude-israel-shopping-plugin/search-zap/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/commands/danielrosehill/claude-israel-shopping-plugin/search-zap"><img src="https://agentmods.dev/badge/commands/danielrosehill/claude-israel-shopping-plugin/search-zap.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 | $0.00078 | $0.01047 |
| Opus 5 | $0.00039 | $0.00524 |
| Sonnet 5 | $0.00016 | $0.00209 |
| Haiku 4.5 | $0.00008 | $0.00105 |
Grade A, and why
search-zap 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 11d 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Search Zap
Zap is the canonical Israeli price-comparison aggregator. One Zap search returns a ranked table of all vendors carrying the product, with prices, so it's materially more efficient than hitting each retailer's search endpoint independently.
Make this the default first-pass for any cross-retailer price comparison. Only fall through to /tech-product-search or /general-search when Zap misses (new SKU, niche specialist product, or Zap search returns nothing).
See
docs/search-strategies.md§ Zap for full URL patterns and workflow, § Hebrew-term resolution for the preflight, and § store-metadata merge convention for the merged-list rule used when flagging vendors.
Backend
Playwright MCP. Zap has bot detection; Tavily's indexed snapshots are often stale and miss the price table.
Preflight — Hebrew term resolution
Zap search is dramatically better with Hebrew queries. Build: <hebrew term> <brand> <model> — brand + model stay Latin.
Example: עמדת טעינה Anker Prime A2343, not "Anker Prime A2343 desktop charging station".
Full resolution procedure (including reverse-lookup from listings when the term is unknown) is in docs/search-strategies.md § Hebrew-term resolution.
URL patterns
Keyword search (start here)
https://www.zap.co.il/search.aspx?keyword=<encoded query>
Returns a list of matching products and/or model pages.
Model page (comparison table)
Once you've identified the model, Zap has a dedicated page with the full vendor price table:
https://www.zap.co.il/model.aspx?modelid=<id>
The modelid is visible in the search results URL. This is the page you actually want — it has all vendors side-by-side.
Category browse (fallback)
If keyword search is unhelpful, browse by category:
https://www.zap.co.il/models.aspx?sog=<category>
Less precise but useful when you don't know the exact product name.
Workflow
- Resolve Hebrew term (preflight above).
- Navigate to Zap keyword search with the Hebrew query.
- Find the right model. Zap groups by SKU — pick the result that matches the specific model the user asked about. If unsure, list the top 3 model pages and confirm with user.
- Open the model page (
model.aspx?modelid=...). This has the price-comparison table. - Extract the vendor table. Each row has:
- Vendor name
- Price (ILS, usually VAT-inclusive — verify)
- Delivery info
- Link through to the vendor listing
- Check for Eilat / ex-VAT pricing. Apply rules from
data/shopping-rules.md— if a vendor shows an unusually low price, check for an ex-VAT or Eilat badge and use the higher regular price. - Rank low-to-high by VAT-inclusive price.
- Note vendors not in
data/israeli-stores.json— Zap often surfaces small specialists worth adding.
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.
- 11d ago First seen · 104 lines · 78 tokens per session scan A ce61960491ea
search-zap is a command published in the GitHub repository danielrosehill/Claude-Israel-Shopping-Plugin (3 stars, last pushed 4mo ago), licensed MIT. It adds 78 tokens to every session and 1,047 once invoked, about $0.0004 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 2026-08-31.
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).
start
Runs a project that has already been compiled with vendure build.
validate-idea
Validate Shopify app idea against market demand, category saturation, App Store discovery patterns, and monetization viability.
intake
You are running the intake for this purchase. The goal is to populate spec.md at the repo root with the per-purchase brief.
price-strategy
You are a senior E-commerce & Retail specialist. The user needs help with price strategy in the context of product catalogue optimisation, conversion rate, customer journey and retail analytics.
price-strategy
You are a senior E-commerce & Retail specialist. The user needs help with price strategy in the context of product catalogue optimisation, conversion rate, customer journey and retail analytics.