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 goshippo/ai --skill shippogit clone --depth 1 https://github.com/goshippo/aiWrote 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/goshippo/ai/shippo)<a href="https://agentmods.dev/skills/goshippo/ai/shippo"><img src="https://agentmods.dev/badge/skills/goshippo/ai/shippo.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 5.1 | $0.00098 | $0.13014 |
| Opus 5 | $0.00049 | $0.06507 |
| Sonnet 5 | $0.00020 | $0.02603 |
| Haiku 4.5 | $0.00010 | $0.01301 |
Grade A, and why
shippo 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 7d 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 — 1,047 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Shippo Shipping Skill
Setup
MCP server: Shippo's hosted MCP at https://mcp.shippo.com, with per-user Shippo OAuth. You authorize once through Shippo on first use, with nothing to copy or configure, and the client refreshes the token automatically.
Point your MCP client at the hosted server:
{
"mcpServers": {
"shippo": {
"type": "http",
"url": "https://mcp.shippo.com"
}
}
}
On first use, your client runs the Shippo OAuth sign-in (in OpenClaw, openclaw mcp login shippo; in Claude Code, /mcp). No local Node process and nothing to store.
Prerequisites: A Shippo account and at least one carrier account (Shippo provides managed accounts for USPS, UPS, FedEx, DHL Express by default). See references/tool-reference.md for the full tool catalog.
Purchases are live: label purchases charge the authorized Shippo account for real. Confirm carrier, service, and cost with the user before any purchase.
Response envelope: The MCP wraps most API responses in a Speakeasy envelope shaped like {"ContentType": "application/json", "StatusCode": <code>, "RawResponse": {}, "<PayloadName>": {...actual response...}}. The payload field is named after the response schema on success (e.g. ParsedAddress, AddressPaginatedList, AddressValidationResultV2, AddressWithMetadataResponse, Shipment, CarrierAccountPaginatedList) and after the HTTP status code on some errors (e.g. fourHundredAndNineApplicationJsonObject for a 409, the body may be {}). To extract the payload, find the field whose key is not ContentType, StatusCode, or RawResponse, and branch on StatusCode for success vs error.
Non-envelope errors: Some failures bypass the envelope entirely and surface as an MCP-level error instead, the tool response has isError: true with a single text block containing a plaintext message like Unexpected API response status or content-type: Status 404 Content-Type application/json Body: {"detail":"Not found."}. Argument-validation failures come back as JSON-RPC error code -32602. Handle both paths when reporting errors to the user.
What ships with it
6 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.
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.
- 7d ago First seen · 1,047 lines · 98 tokens per session scan A 3df5d3f2077d
shippo is a skill published in the GitHub repository goshippo/ai (2 stars, last pushed 2d ago), licensed MIT. It adds 98 tokens to every session and 13,014 once invoked, about $0.0005 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 skills, from other repositories
shop
Use when the user wants Axon-backed product research, product comparisons, review synthesis, budget-aware recommendations, or cart preparation without checkout.
product-price-monitor
Watch product, flight, or listing prices; alert on target.
refunds
Check refund eligibility and use the refund-order tool safely.
snack-batching
Weekly snack-request batching for {{officechannel}}. Collects Slack shortcut submissions since the last order, consolidates duplicates and standing staples, builds a cart against {{preferredvendor}} within {{weeklybudget}}, and posts it for the office manager to approve before anything is placed.
logistics-ops
Use when an order is paid and packed and the box now has to move, go sideways, or come back — picking a carrier and service and cutting a label, reacting to a delivery exception, getting ahead of where-is-my-order tickets, running a return, exchange or refund with its reverse label, filing a carrier claim before the…
blast-radius
Trace ServiceNow configuration dependencies — what artifacts touch a given field, what calls a script include, table/app-level config inventory. Use before deletes, renames, or refactors.