Product Search Helper

Product Search Helper is an agent for coding agents from obot-platform/nanobot. It costs 3 tokens per session (81 once invoked), scanned A, original, Apache-2.0.

A product-finding assistant for the shopify.supply catalogue, an online product shop. It uses a shopper’s needs and preferences to suggest relevant products.

In plain words
What is it for?
Finding products by requirements, preferences, or intended use and receiving product recommendations from the catalogue.
Why use it?
It reduces the need to search through the catalogue manually when the shopper knows what they want but not which item matches.

Agent

Install

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.

agentmods
npx agentmods add agents/obot-platform/nanobot/helper
Clone the repo
git clone --depth 1 https://github.com/obot-platform/nanobot

Wrote 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.

agentmods badge for Product Search Helper

README.md
[![agentmods](https://agentmods.dev/badge/agents/obot-platform/nanobot/helper.svg)](https://agentmods.dev/agents/obot-platform/nanobot/helper)
Your own site
<a href="https://agentmods.dev/agents/obot-platform/nanobot/helper"><img src="https://agentmods.dev/badge/agents/obot-platform/nanobot/helper.svg" alt="Measured on agentmods" height="20"></a>
Per session 3 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 81 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00003 $0.00081
Opus 5 $0.00002 $0.00041
Sonnet 5 $0.00001 $0.00016
Haiku 4.5 $0.00000 $0.00008

Measured 4d ago against content hash 6fe0c8f1ffd1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Product Search Helper 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.

examples/directory-config/agents/helper.md · 15 lines

What it actually says

You are a specialized product search assistant. Your role is to help users find specific products in the shopify.supply catalog based on their needs and preferences.

Focus on understanding what the user is looking for and providing relevant product recommendations.

Changes

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.

  1. 4d ago First seen · 15 lines · 3 tokens per session scan A 6fe0c8f1ffd1

Subscribe to this mod's changes

Product Search Helper is an agent published in the GitHub repository obot-platform/nanobot (1,336 stars, last pushed yesterday), licensed Apache-2.0. It adds 3 tokens to every session and 81 once invoked, about $0.0000 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 2026-08-30.

Related

Other agents, from other repositories

trellis-check

Code quality check expert. Reviews code changes against specs and self-fixes issues.

yuqie6/ProductFlow · 20 tokens

strategy-consultant

You are a management and startup consultant for Korean founders, small-business owners, and startup operators. You turn a goal (validate business idea X, size market Y, win grant program Z, assess this storefront location) into concrete, evidence-based deliverables: business plans, business model canvases, market…

modu-ai/moai-cowork · 106 tokens

woo-regression-reviewer

WooCommerce regression-invariant review — Action Scheduler traps, meta equality and sync-on-read loops, template/theme overrides, broken-until-JS defaults, filter return-type variance, PHP coercion, migration legacy state, heuristic proxy predicates vs. store-configuration variance, removed-markup selector contracts…

vladolaru/claude-code-plugins · 98 tokens

shopify-app-architect

Use when starting a new Shopify app or designing a major feature. Specializes in creating complete architecture plans including data models, API routes, webhooks, scopes, billing strategy, and deployment targets. Route here for architecture approval workflows.

khadinakbarlabs/shopify-app-builder · 52 tokens

business-architect

Senior business-domain architect for SaaS, ERP, e-commerce, and full-stack applications. Delegates here for designing business logic that survives real-world edge cases — billing, multi-tenancy, inventory, GL postings, refunds, RBAC, audit, idempotency. Knows how Stripe, Linear, NetSuite, Shopify, and similar solve…

viknesh20-20/claude-code-tool-kit · 76 tokens

comps-researcher

Least-privilege pricing-research subagent. Pulls live eBay sold comps (and optional FB Marketplace context) for one secondhand item and returns exactly two labeled Markdown blocks. Use when the listing orchestrator needs pricing without the browser-heavy page text polluting the main context. Scraper only — never…

hansohn/marketplace-skills · 74 tokens