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 okuegow/agent-skills --skill ebay-sellergit clone --depth 1 https://github.com/okuegow/agent-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/okuegow/agent-skills/ebay-seller)<a href="https://agentmods.dev/skills/okuegow/agent-skills/ebay-seller"><img src="https://agentmods.dev/badge/skills/okuegow/agent-skills/ebay-seller/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/okuegow/agent-skills/ebay-seller"><img src="https://agentmods.dev/badge/skills/okuegow/agent-skills/ebay-seller.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 | $0.00112 | $0.01642 |
| Opus 5 | $0.00056 | $0.00821 |
| Sonnet 5 | $0.00022 | $0.00328 |
| Haiku 4.5 | $0.00011 | $0.00164 |
Grade A, and why
ebay-seller 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
eBay-Seller
Guides each item through fixed phases. Per-item state lives in <workspace>/ebay/items/<YYYY-MM-DD-slug>/state.json. Seller defaults in <workspace>/ebay/config.json. Usually one new item per day; several items can run in parallel across different phases.
The listing text and item content are produced in German (target marketplace eBay.de), even though this guide is written in English.
<workspace> = the user's current project directory (fallback: ask). On Windows the .claude directory is under %USERPROFILE%\.claude\. References and templates live relative to this SKILL.md under references/ and templates/.
Requirements
- Required: Claude Code + the "Claude in Chrome" extension, and a Chrome where the user is logged in to eBay.de. Nothing else — runs on macOS and Windows.
- Optional (convenience only): Python 3 +
Pillowfor automatic photo enhancement (scripts/enhance_photo.py). Without Python/Pillow the skill still works — photos are used unedited (the user uploads them manually anyway). - No installation needed: manage
state.jsondirectly (read/write JSON), no Python helper required.
Safety gates (non-negotiable)
- Never publish without explicit approval. Fill the listing, then stop before the final click.
- Live price changes and counter-offers only after approval.
- Never retouch defects out of photos (see
references/compliance.md).
First run
If <workspace>/ebay/config.json does not exist, this is the first run: first show a short quick-start (3 sentences: drag in a photo + "sell on eBay"; you upload the photos yourself; nothing is published without your approval). Then create it from templates/config-template.json and ask the user for the fields (location/ZIP, shipping method+cost, returns, handling time, default sale format, tone). ebay_benutzername is optional. Login is manual: the user logs in to eBay in Chrome themselves — no password in chat, no Keychain setup needed.
Every run
- Scan
<workspace>/ebay/items/. Show an overview: item × phase × today's task. - New photo(s) on the message? (one or more) — derive a rough name from the first photo, then search
items/for an item with a similar name (dedupe). Match → ask whether it is the same item; if yes, add the new photos to the existing item. Otherwise create a new item (phaseneu). - For items in
beobachtenandlive: daily update — but only ifletzter_lauf≠ today (idempotency). Otherwise skip and report "already captured today". - The user drives the phase transitions.
What ships with it
18 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- .gitignore 40 B
- README.de.md 1.9 KB
- README.md 1.8 KB
- references/compliance.md 672 B
- references/item-identification.md 979 B
- references/listing-guide.md 1.4 KB
- references/login.md 1.1 KB
- references/optimization.md 2.2 KB
- references/price-research.md 1.4 KB
- scripts/__init__.py 0 B runs code
- scripts/enhance_photo.py 3.3 KB runs code
- scripts/state.py 2.5 KB runs code
- scripts/tests/__init__.py 0 B runs code
- scripts/tests/test_enhance_photo.py 1.6 KB runs code
- scripts/tests/test_state.py 2.3 KB runs code
- templates/config-template.json 270 B
- templates/listing-template.md 250 B
- templates/state-template.json 399 B
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 · 79 lines · 112 tokens per session scan A 4bfb78b926ef
ebay-seller is a skill published in the GitHub repository okuegow/agent-skills (4 stars, last pushed 1mo ago), licensed MIT. It adds 112 tokens to every session and 1,642 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.
Other skills, from other repositories
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…
paid-ads-amazon
Plan and review Amazon Ads with margin-aware ACoS, product, and search-term guardrails. Use for Amazon advertising, Sponsored Products, Sponsored Brands, Sponsored Display, ASIN targeting, Amazon ACoS, or Amazon Ads performance exports.
skill-monitor
Analyze skill effectiveness across sessions. Computes per-skill metrics (action rate, friction, outcomes), identifies degrading skills, and generates improvement recommendations. Requires session-scan data in metrics.jsonl.
deps-audit
Audit Hex deps for supply-chain security risk — bidi chars, compile-time exec, maintainer changes, typosquats, CVEs. Use after mix deps.update, when checking if a package upgrade is safe, or reviewing mix.lock PR diffs.
review
Review code with parallel agents — tests, security, Ecto, LiveView, Oban. Use after implementation to catch bugs and anti-patterns before committing.
phx-deps-audit
Audit Hex deps for supply-chain security risk — bidi chars, compile-time exec, maintainer changes, typosquats, CVEs. Use after mix deps.update, when checking if a package upgrade is safe, or reviewing mix.lock PR diffs.