cargo-analytics Skill for Claude Code: Download Results and Measure Runs in Cargo

Lets Claude pull data out of Cargo: download run and batch results, export a segment to CSV or JSON, and report success and error counts.

Installs: 10.5K; on skills.sh
Stars: 21; on GitHub
Files: 5; besides SKILL.md
Updated: Oct 2026; last repo commit

Claude uses cargo-ai commands to get run metrics and run counts for a workflow, run ad-hoc SQL over runs and batches, download a run's outputs or a batch's results, and export a segment or model. It also covers handling batches where some records failed.

SKILL.md scopes it to measuring and exporting, not explaining. Why a run failed or where credits went belongs to cargo-diagnostics, and plans and invoices to cargo-billing. It needs the Cargo CLI and a Cargo sign-in.

Good for

RevOps analysts who need results as a file
Operators watching error rates on a play
Anyone exporting an enriched list or a segment

Install cargo-analytics

Claude Code

Copy this prompt.

Install the cargo-analytics 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

Get data out of Cargo and measure what ran — download a run output, export a segment or model to CSV or JSON, and pull run and batch success and error counts. Triggers: "download the results", "export this to CSV", "give me the file", "how many succeeded", "what is my error rate", "send me the enriched list", "get the output of that run", "how many records did it write". Skip when: asking why something failed or where credits went — use cargo-diagnostics; asking about credits, plans, or invoices — use cargo-billing.

Sections in SKILL.md

Bootstrap
Scope — measure and export, not explain
Discover resources first
Quick reference
Workflow run metrics
Run count
Ad-hoc execution analytics (orchestration query)
Downloading run results
run download — one row per run, one column per node (gzipped CSV)
run download-outputs — per-run input + output (CSV/JSON via signed URL)
Getting the full runContext for several runs
Downloading batch results
Handling partial batch failures
Segment data export
Help

Key facts

Author: Cargo (frontmatter author: getcargo), in the vendor's own repo
License: MIT (LICENSE, README badge and plugin.json agree)
Version: 1.7.0
Installs on skills.sh: 10,535 (Nov 2, 2026)
GitHub stars: 21 (Nov 2, 2026)
Last commit: Oct 31, 2026
What installs: 6 files including SKILL.md: 4 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

Returns predefined success and error metrics for one workflow.
Runs code · run get-metrics
Counts runs for a workflow, optionally by status such as error.
Runs code · run count
Runs ad-hoc SQL over runs, batches, spans and records across the workspace.
Runs code · query execute
Downloads per-record run results, or just one output node, as a signed link.
Runs code · run download / download-outputs
Gets a signed link to a batch CSV with each output key as a cargo_ column.
Runs code · batch download
Steps for handling a batch where only some records failed.
Runs code · Partial batch failures
Exports a filtered segment or model to a file.
Runs code · segment download

From the official docs

Permissions

Medium risk

It downloads run results and segment exports that can hold contact data. Export only what you need and store the files carefully.

What it can do

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

Watch out for

Exports can contain contact data
Segment and run exports return lead and contact records as CSV or JSON. Store them like any contact list. 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
Downloads return links to files
download-outputs and batch download return a signed URL. Do not paste these links into shared channels. 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	Reads run results and segment data and downloads them to files Cargo workspace sign-in (saved in ~/.config/cargo-ai/credentials.json)

Questions

What does cargo-analytics do?

It gets data out of Cargo and measures what ran. Claude downloads run outputs, exports segments, and reports how many runs succeeded or failed.

How do I download the results of a run?

SKILL.md points to run download-outputs for one output node's data and run download for per-record results. Batches use batch download. Each returns a link to a file.

Can it tell me why a run failed?

That is explicitly out of scope. SKILL.md sends why-it-failed and where-credits-went questions to cargo-diagnostics.

Does it cost credits?

SKILL.md describes these as measuring and exporting commands, and does not give a credit price for them. Use cargo-billing to check your balance.

What do I do if half a batch failed?

SKILL.md has a section on handling partial batch failures, and hands off to cargo-diagnostics for the root cause once you know the error count.

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 moves Cargo data onto your machine. Downloads and segment exports can hold lead and contact records, and they return links to files. Our advice: export only the segments you need, keep the files out of shared folders and delete them when done.

Information

updated Nov 2, 2026

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

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-analytics 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