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 agentmods add commands/jbwashington/ebay-mcp/ebay-draftgit clone --depth 1 https://github.com/jbwashington/ebay-mcpWrote 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/jbwashington/ebay-mcp/ebay-draft)<a href="https://agentmods.dev/commands/jbwashington/ebay-mcp/ebay-draft"><img src="https://agentmods.dev/badge/commands/jbwashington/ebay-mcp/ebay-draft.svg" alt="Measured on agentmods" 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 | $0.00009 | $0.00388 |
| Opus 5 | $0.00005 | $0.00194 |
| Sonnet 5 | $0.00002 | $0.00078 |
| Haiku 4.5 | $0.00001 | $0.00039 |
Grade A, and why
ebay-draft 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.
What it actually says
Create eBay Draft Listing
Create a draft eBay listing for an item.
Prerequisites
If the item hasn't been analyzed yet, run /ebay-analyze first.
Task
-
If folder path provided as
$1, use it. Otherwise ask the user for the item folder path. -
Get the item analysis (either from previous conversation or by analyzing now)
-
Generate a unique SKU in format:
SKU-YYYYMMDD-XXXwhere XXX is a sequential number -
Prepare listing data:
- Title: SEO-optimized, 80 chars max
- Description: Detailed HTML description including:
- Product details
- Condition description
- Measurements (if any)
- Flaws/defects (be transparent!)
- Shipping policy (free USPS Ground)
- Return policy (30-day)
- "From smoke-free, pet-free home"
- Category: Determine appropriate eBay category ID
- Price: Suggested competitive price
- Images: Upload to eBay or use hosted URLs
- Item Specifics: All relevant aspects (Brand, Size, Color, Condition, etc.)
-
Use eBay MCP tools to create the listing:
ebay_create_inventory_itemwith SKU and product detailsebay_create_offerto create the draft listing
-
Report back to user:
- SKU created
- Offer ID
- Draft listing preview
- Next steps: review and publish with
/ebay-publish
Important: This creates a DRAFT listing only. It won't be visible on eBay until published.
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.
- 4d ago First seen · 49 lines · 9 tokens per session scan A 23024247a350
ebay-draft is a command published in the GitHub repository jbwashington/ebay-mcp (13 stars, last pushed 5mo ago), licensed MIT. It adds 9 tokens to every session and 388 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.
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).
pipeline-undo
Undo a pipeline run's result. With worktree isolation (the current engine), this is clean and low-risk: a run never touches your checkout — its result lives only on a pipeline/ branch (and, for a --push run, on the remote). "Undo" therefore means deleting that branch and its worktree, not reverting your working tree.
rank-vertical
E-Commerce and Local Business SEO checks with auto-detection.
local-env
Point this machine at its claude-prove checkout — writes the per-machine env block into .claude/settings.local.json.
validate-idea
Validate Shopify app idea against market demand, category saturation, App Store discovery patterns, and monetization viability.
clean
Remove the git worktrees review checked PR code out into. Each one is a full checkout on disk; nothing else is touched.