A pricing research process for secondhand items using completed eBay listings and active Facebook Marketplace listings. It compares similar items and produces a suggested listing price.

Use it to price a used item, prepare an eBay or Facebook Marketplace listing, or estimate what an item is worth. It is intended for specific items with known condition and location.

It replaces guesswork with evidence from comparable listings. This helps sellers choose a price that reflects the item's condition and local selling context.

comps — Skill for Claude Code by hansohn

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code

/plugin marketplace add hansohn/marketplace-skills

Claude Code

/plugin install marketplace

Made for: Claude Code.

Or install marketplace, the plugin that ships this one along with the rest of its 4 skills, 2 agents.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/hansohn/marketplace-skills/comps/github.svg)](https://agentmods.dev/skills/hansohn/marketplace-skills/comps)

Your own site

<a href="https://agentmods.dev/skills/hansohn/marketplace-skills/comps"><img src="https://agentmods.dev/badge/skills/hansohn/marketplace-skills/comps/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/hansohn/marketplace-skills/comps"><img src="https://agentmods.dev/badge/skills/hansohn/marketplace-skills/comps.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 113 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,639 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00113	$0.03639
Opus 5	$0.00056	$0.01819
Sonnet 5	$0.00023	$0.00728
Haiku 4.5	$0.00011	$0.00364

Measured 9d ago against content hash 8cc7bab9ddc9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

comps 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 9d 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.

skills/comps/SKILL.md · 192 lines

How it starts

The opening of the file, as written. The whole thing — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Marketplace Comps

Pull live pricing comparables for a secondhand item from eBay (sold/completed listings) and Facebook Marketplace (active listings), then synthesize a recommended list price.

When to use

Trigger automatically when:

The user names a specific used item and asks what it's worth, what it sold for, or how to price it
The /marketplace:listing orchestrator delegates pricing research
The user is preparing a Facebook Marketplace or eBay listing

Do not use for new-item retail pricing (use a regular web search) or for pricing services/labor.

Required inputs

Item name — Make + model, with model number if available (e.g., "Strider 12 Sport Balance Bike ST-S4RD")
Condition — New, Used (Like New / Good / Fair), Open Box
Location — User's city + state + zip, used for FB Marketplace search context (when not skipped) and to phrase the local-pickup pricing premium in the recommendation paragraph. The orchestrator resolves this from CLI flag / user memory / interactive prompt — this skill never hardcodes a default. If the orchestrator did not pass a location and one is genuinely needed (FB research is enabled), ask the user before proceeding.

If any are missing and not derivable from context (CSV row, prior conversation, item details file), ask before continuing — surface the gap with concrete options rather than guessing (see ${CLAUDE_PLUGIN_ROOT}/references/handling-ambiguity.md).

Process

1. eBay sold listings (primary signal)

First, confirm a browser MCP is available. This step's primary path uses Playwright browser tools (browser_navigate, browser_evaluate, etc.). If no such tool exists — the Playwright MCP isn't installed or configured — don't error out and don't fabricate prices. Skip straight to the WebSearch/WebFetch path (the same fallback described under failure mode 1) to gather sold-price data, and note in the output that pricing came from search results rather than a live DOM scrape, so the comp set is thinner and less precise. If neither browser nor web tools are available, emit the honest "no comparable data found" result (see Notes) — never invent prices. Everything below assumes the browser MCP exists.

Read the full file on GitHub · 192 lines

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.

9d ago First seen · 192 lines · 113 tokens per session scan A 8cc7bab9ddc9

Subscribe to this mod's changes

comps is a skill published in the GitHub repository hansohn/marketplace-skills (1 stars, last pushed 1mo ago), licensed MIT. It adds 113 tokens to every session and 3,639 once invoked, about $0.0006 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.

Claude Code E-commerce Research agent-skills anthropic claude claude-code-plugin claude-skills

ecommerce-seo

E-commerce SEO audit for online stores (WooCommerce, Shopify, Magento, custom). Covers the structural problems unique to commerce sites: category / product listing pages (PLP), product detail pages (PDP), faceted navigation and the crawl-budget / duplicate-content traps it creates, pagination, canonical handling for…

nowork-studio/notfair-plugin · 235 tokens

comps

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Marketplace Comps

When to use

Required inputs

Process

1. eBay sold listings (primary signal)

What this file has done since we first saw it

Other skills, from other repositories

ecommerce-seo

paid-ads-amazon

einbeziehung-online-clickwrap-browsewrap

kurzfristige-preiserhoehung-lieferfrist

plattform-online-gate-rollout-rangfolge

lieferfrist-teillieferung