cargo-storage Skill for Claude Code: Models, Columns, Records and SQL in Cargo

Lets Claude work with the data in a Cargo workspace: list models, add columns, link tables, write records and run SQL over Companies and Contacts.

Installs: 10.5K; on skills.sh
Stars: 21; on GitHub
Files: 8; besides SKILL.md
Updated: Oct 2026; last repo commit

Claude uses cargo-ai storage commands to list models and their DDL, create or remove columns, set relationships between models, create and remove records, and run SQL such as a count of companies by size. It also covers webhook-fed models, previews of what a model would pull, and unification, which merges records from several models into one account or contact.

Run telemetry (runs, batches, spans) belongs to cargo-orchestration, and named saved audiences to cargo-segmentation. It needs the Cargo CLI and a Cargo sign-in.

Good for

GTM engineers shaping the Companies, Contacts and Deals models
Analysts running SQL over workspace storage
Teams merging duplicate accounts or linking contacts to companies

Install cargo-storage

Claude Code

Copy this prompt.

Install the cargo-storage skill in Claude Code. Run this command:

/plugin marketplace add getcargohq/cargo-skills
/plugin install cargo@cargo-skills

Then check that it loaded and tell me how to use it.

2
Paste it into Claude Code. It shows the change and asks before running it.

Every Cargo skill drives the cargo-ai CLI, so install it and sign in first. A new account starts with 100 free credits and no card (README). Pick one channel, not two: the plugin and skills add both register the skills, so using both duplicates them. The whole bundle is the route the README documents; this skill's own files point to files in sibling skills such as ../cargo/references/prerequisites.md. The plugin needs Claude Code 2.1.154 or newer and adds hooks and two subagents; see the safety section.

From the project README. Source.

What's in the skill

When it loads

Work with the data inside a Cargo workspace — models (Companies, Contacts, Deals…), datasets, columns, relationships, records, and SQL over workspace storage. Triggers: "what models do I have", "show me the schema", "add a column for", "how many contacts do I have", "SELECT … FROM", "query my companies table", "join contacts to companies", "what is the DDL", "set up a webhook-fed model", "where does this field live", "import this into a model", "unify these models", "merge duplicate accounts", "link contacts to companies", "set up a relationship between". Skip when: querying run or batch telemetry rather than business data — use cargo-orchestration; naming a reusable filtered audience — use cargo-segmentation.

Sections in SKILL.md

Bootstrap
Discover resources first
Quick reference
Models
A model that is a SQL query over other models
Dry-run an extractor config before creating the model
Ingest models (webhook-fed)
Datasets
Columns
Preview what you built
Relationships
Unification
Records
Query with SQL
Help

Key facts

Author: Cargo (frontmatter author: getcargo), in the vendor's own repo
License: MIT (LICENSE, README badge and plugin.json agree)
Version: 1.5.0
Installs on skills.sh: 10,538 (Nov 2, 2026)
GitHub stars: 21 (Nov 2, 2026)
Last commit: Oct 31, 2026
What installs: 9 files including SKILL.md: 7 reference and example files and skill-metadata.json
Needs: The cargo-ai CLI (npm) and a Cargo sign-in; a new account starts with 100 free credits
Cargo CLI license: UNLICENSED on npm; the skills bundle itself is MIT
Bundle size: README and plugin manifests say 19 skills, the skills.sh badge says 18, and the repo has 20 skill folders including a redirect stub
Works in: Claude Code, Codex, Cursor, Windsurf, GitHub Copilot, Hermes Agent and other skills.sh agents

What it includes

Lists models and shows one with its DDL so SQL uses the exact table name.
Runs code · model list / get / get-ddl
Removes a model.
Delete · model remove
Webhook-fed models filled by pushing records; the feed URL carries an API token.
Runs code · Ingest models
Lists datasets, the groups that hold models.
Runs code · dataset list
Reads, adds and removes columns on a model.
Delete · column list / create / remove
Previews what an extractor would pull before you build the model.
Runs code · model preview
Links models; sending a partial list deletes relationships not in it.
Delete · relationship list / set
Merges records from several models into one canonical account or contact.
Runs code · Unification
Writes records in bulk and removes one or many by id.
Delete · record create-bulk / remove
Runs SQL over workspace storage, or downloads the results.
Runs code · query execute / download

From the official docs

Permissions

High risk

It can delete models, columns and records in your Cargo workspace. Start with list and SELECT commands and confirm the workspace before any write.

What it can do

Read your data
Create and change things
Delete things
Read-only mode

Watch out for

It can remove models, columns and records
model remove, column remove, record remove and remove-bulk delete workspace data. Confirm the workspace and the ids before you approve. github.com
Setting relationships replaces the full list
SKILL.md says a relationship whose uuid is absent from the payload is deleted. List the current ones first and send them all back. github.com
The webhook feed URL contains an API token
SKILL.md assembles it as a URL with a token query parameter. Treat the URL as a secret. github.com
Claude runs the cargo-ai CLI as you
The skill drives the cargo-ai CLI. Sign-in is saved to ~/.config/cargo-ai/credentials.json, and the docs say to confirm the workspace with cargo-ai whoami before any write. github.com
The plugin route adds hooks that run shell commands
The plugin wires a PreToolUse hook on Bash that auto-approves safe cargo-ai calls, and a SessionStart hook that runs npm install -g @cargo-ai/cli at the pinned version. Login, token creation, report creation, project deploy and any remove or delete still prompt. github.com
The plugin sends a session summary to your Cargo workspace
The SessionEnd hook passes the last 60,000 bytes of the transcript to claude -p to write a title and summary, then stores them in your Cargo workspace session record. Use the skills CLI route if you do not want that. github.com
Some extractors bill credits
SKILL.md notes that an extractor on a credits connector bills for what it pulls, including a preview page. Keep limits strict. github.com
The plugin also adds two subagents
cargo-execution-planner and cargo-list-builder run on the haiku model with Read, Grep, Glob and Bash tools. The planner is described as read-only and the list builder as executing only pre-approved slices. github.com

Security advisories

No published security advisories as of Nov 2, 2026.

Technical details

Talks to	api.getcargo.io (Cargo API). registry.npmjs.org (CLI install). app.getcargo.io (token creation)
Sign-in and keys	Sign-in by emailed code, browser (OAuth) or an API token. Browser and email sign-in save a session to ~/.config/cargo-ai/credentials.json; API tokens are workspace-scoped and the README says to store them in a secrets manager.
Scopes	Creates, edits and removes models, columns, relationships and records Cargo workspace sign-in (saved in ~/.config/cargo-ai/credentials.json)

Questions

What does cargo-storage do?

It lets Claude work with the business data inside Cargo: models such as Companies and Contacts, their columns and relationships, individual records, and SQL queries.

Can it run SQL?

Yes, with storage query execute, or storage query download for the results as a file. SKILL.md says to get the model's DDL first so the query uses the exact table name.

Can it delete data?

Yes. The SKILL.md quick reference includes model remove, column remove and record remove and remove-bulk. It also warns that setting relationships replaces the full list, so a payload with one relationship removes the others.

What is the webhook URL for a model?

For ingest models, SKILL.md says the URL is built from your base URL, the model UUID and an API token. It says not to hand the URL out when the extractor registers its own hook (autoIngest), and not to use it inside Cargo workflows.

Storage or cargo-segmentation?

SKILL.md points to cargo-segmentation for naming a reusable filtered audience and to cargo-orchestration for run and batch telemetry. This skill covers the business data itself.

How do I install it?

Use the install box above. Install the whole Cargo bundle, then the Cargo CLI and sign in. The README says to pick one channel, plugin or skills add, not both.

Is it official?

Yes. It sits in Cargo's own repo (getcargohq/cargo-skills), the LICENSE names Cargo as the copyright holder and the plugin manifest lists Cargo as the author.

Does it work in the Claude app, Codex or Cursor?

The README names Claude Code, Codex, Cursor, Windsurf, GitHub Copilot and Hermes Agent. For Claude Desktop it documents a Claude Cowork plugin route with network egress turned on. The skill drives a local CLI, so there is no plain Claude app skill upload here.

Is it safe to use?

It can change and delete the data your GTM runs on. Model, column and record removal is available, relationship updates replace the whole list, and the webhook feed URL contains a token. Our advice: run SELECT queries and list commands first, and confirm the workspace before any write.

Information

updated Nov 2, 2026

Repository: getcargohq/cargo-skills
Folder: cargo-storage

getcargohq/cargo-skills skills.sh

Sources

Docs, issue trackers and discussions this page is built from.

Show all 7

cargo-skills README · github.com
cargo prerequisites.md · github.com
cargo-storage SKILL.md · github.com
cargo-skills LICENSE · github.com
cargo-skills plugin.json · github.com
session-end.sh · github.com
session-start.sh · github.com