shippo-support-ticket

shippo-support-ticket is a skill for Claude Code from goshippo/ai. It costs 141 tokens per session (5,077 once invoked), scanned A, original, MIT.

A tool for preparing a complete Shippo support request from one shipment or shipping-label identifier. Shippo is a shipping service that handles labels, rates, tracking, and carrier integrations; the tool classifies the problem and produces both a copy-ready message and structured routing data.

In plain words
What is it for?
Use it to escalate lost or delayed packages, unused-label refunds, billing or rate issues, address exceptions, customs holds, carrier-account problems, or tracking-webhook issues.
Why use it?
It gathers issue-specific shipment facts and organizes them for Shippo support, reducing missing information and repeated questions. It also labels the request for the appropriate support queue.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the shippo plugin — 9 skills, 1 MCP server shipped together

Good fit Use it to escalate lost or delayed packages, unused-label refunds, billing or rate issues, address exceptions, customs holds, carrier-account problems, or tracking-webhook issues.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/goshippo/ai/shippo-support-ticket
View source ↗ goshippo/ai
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.

Any agent
npx skills add goshippo/ai --skill shippo-support-ticket
Clone the repo
git clone --depth 1 https://github.com/goshippo/ai

Made for: Claude Code.

Or install shippo, the plugin that ships this one along with the rest of its 9 skills, 1 MCP server.

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 shippo-support-ticket

README.md
[![agentmods](https://agentmods.dev/badge/skills/goshippo/ai/shippo-support-ticket/github.svg)](https://agentmods.dev/skills/goshippo/ai/shippo-support-ticket)
Your own site
<a href="https://agentmods.dev/skills/goshippo/ai/shippo-support-ticket"><img src="https://agentmods.dev/badge/skills/goshippo/ai/shippo-support-ticket/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.

agentmods 80×15 button for shippo-support-ticket

Your own site · 80×15
<a href="https://agentmods.dev/skills/goshippo/ai/shippo-support-ticket"><img src="https://agentmods.dev/badge/skills/goshippo/ai/shippo-support-ticket.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 141 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,077 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00141 $0.05077
Opus 5 $0.00071 $0.02538
Sonnet 5 $0.00028 $0.01015
Haiku 4.5 $0.00014 $0.00508

Measured 10d ago against content hash 56ba452dcd6e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

shippo-support-ticket 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 10d 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.

providers/claude/plugin/skills/shippo-support-ticket/SKILL.md · 378 lines

How it starts

The opening of the file, as written. The whole thing — 378 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Shippo Support Ticket Builder

Turn a single shipment identifier into a complete, classified, well-structured support package for the Shippo support team. The agent classifies the issue, gathers every relevant fact from the Shippo MCP (running issue-type-specific lookups, not just the lost-package set), computes the triage timeline, and emits two things:

  1. A human copy-paste block for the ticket body.
  2. A structured JSON block tagged with a routing queue, so the ticket can be piped into the ticketing system and land in the right pipeline without a human re-classifying it.

This dual output is the point: completeness and correct routing are what kill the back-and-forth.

Audience: Shippo support agents. Output uses Shippo terminology, object IDs, and an internal routing tag. It is not customer-facing copy.

When to use

Use this skill when someone wants to escalate or document a shipping problem and asks for a support ticket / message to Shippo support, e.g. "package is stuck," "label was charged but never shipped," "why was I charged more than the rate I saw," "refund this label I never used," "where is this delivery," "the address looks wrong," "tracking updates aren't coming through," "can't get rates from this carrier." It produces text + JSON to copy and paste; it does not open a Jira ticket or send Slack/email itself.

Step 1: Classify the issue (do this first)

Pick exactly one canonical issue type from the customer's description. The issue type drives both the routing tag and which extra lookups you run in Step 4. If the wording is ambiguous, ask one clarifying question before building.

Issue type (canonical) Triggers / signals Routing tag
lost_or_delayed stuck, late, no movement, "where is my package", lost queue:tracking-ops
unused_label_refund "never shipped", "refund this label", bought-but-unused queue:billing-refunds
billing_adjustment "charged more than the rate", surcharge, reweigh, dim-weight, address-correction fee queue:billing-adjustments
address_exception undeliverable, returned to sender, bad/invalid address, address correction queue:address-exceptions
customs_international customs hold, duties/taxes, missing HS code, commercial invoice, international queue:customs-intl
carrier_account "can't get rates from ", connection failed, registration pending queue:carrier-onboarding
tracking_webhook "tracking updates aren't coming through", webhook not firing queue:integrations
other anything that doesn't fit above queue:general-triage

Read the full file on GitHub · 378 lines

Files

What ships with it

1 file 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.

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. 10d ago First seen · 378 lines · 141 tokens per session scan A 56ba452dcd6e

Subscribe to this mod's changes

shippo-support-ticket is a skill published in the GitHub repository goshippo/ai (2 stars, last pushed 6d ago), licensed MIT. It adds 141 tokens to every session and 5,077 once invoked, about $0.0007 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.