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 jakkaj/tools --skill shopping-huntergit clone --depth 1 https://github.com/jakkaj/toolsWrote 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/jakkaj/tools/shopping-hunter)<a href="https://agentmods.dev/skills/jakkaj/tools/shopping-hunter"><img src="https://agentmods.dev/badge/skills/jakkaj/tools/shopping-hunter/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/jakkaj/tools/shopping-hunter"><img src="https://agentmods.dev/badge/skills/jakkaj/tools/shopping-hunter.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 | $0.00050 | $0.01349 |
| Opus 5.5 | $0.00020 | $0.00540 |
| Sonnet 5.5 | $0.00010 | $0.00270 |
| Haiku 4.5 | $0.00005 | $0.00135 |
Grade A, and why
shopping-hunter 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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Shopping Hunter
Use this skill when the user wants to find, benchmark, compare, or source products similar to a reference item, image, aesthetic, material, maker, or buying goal. The default mode is deep global shopping research with Australia prioritized, AUD-normalized pricing, and a documented dossier.
Default operating mode
- Produce all of the following:
- A buying dossier.
- A concise shortlist of the best buys.
- A market benchmark showing cheap, mid-market, premium, and high-end pricing.
- Prioritize Australia first, then global sources.
- Normalize prices to AUD primary, while preserving original currency and set size.
- Be value-focused: call out bargains, fair pricing, overpricing, provenance premiums, hidden shipping risk, and “cheap but not equivalent” alternatives.
- Prefer actual purchasable product links over inspiration-only pages.
- Include official brand/maker sites, marketplaces, local retailers, boutiques/design stores, secondhand/vintage listings, high-end benchmarks, and wholesale/B2B leads when relevant.
- Search deeply: use regional/source passes, price-tier passes, terminology/source-origin research, exact-source tracing, and high-end benchmarks.
Required intake questions
Before starting, ask for the missing items from this list. If the user already provided some, only ask for the missing/high-impact ones.
- Reference link(s) and/or image(s).
- What they like about the reference: colours, shape, material, finish, dimensions, provenance, vibe, brand, price, etc.
- Budget or price bands to benchmark.
- Must-have traits vs nice-to-have traits.
- Regions to prioritize, with Australia as the default priority.
- Whether vintage/used/one-off listings are acceptable.
- Whether wholesale/B2B/MOQ sources are acceptable.
- Quantity needed and whether sets are preferred.
- Deal-breakers: materials, countries, shipping, lead times, ethics, returns, fragility, defects.
- Whether to create a Markdown dossier file; default is yes.
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 · 151 lines · 50 tokens per session scan A d377994b79dd
shopping-hunter is a skill published in the GitHub repository jakkaj/tools (5 stars, last pushed 24d ago), licensed MIT. It adds 50 tokens to every session and 1,349 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 2026-08-31.
shopping-hunter compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| shopping-hunterjakkaj/tools | Skill | 5 | 24d ago | MIT | A | 50 | Claude Code, Codex |
| amazon-reviews-api-skillbrowser-act/skills | Skill | 6.3k | 4d ago | MIT | A | 124 | Claude Code, Codex |
| amazon-competitor-analyzerbrowser-act/skills | Skill | 6.3k | 4d ago | MIT | A | 48 | Claude Code, Codex |
| asc-subscription-localizationrorkai/app-store-connect-cli-skills | Skill | 1.1k | yesterday | MIT | A | 60 | Claude Code |
| external-purchasesrshankras/claude-code-apple-skills | Skill | 867 | yesterday | MIT | A | 76 | Claude Code |
| food-orderBitterbot-AI/bitterbot-desktop | Skill | 2.5k | today | MIT | A | 53 | Claude Code, Codex |
| Product Photoshoot Workflowjau123/MeiGen-AI-Design-MCP | Skill | 1.8k | 2d ago | MIT | A | 111 | Claude Code |