cargo-orchestration Skill for Claude Code: Run Actions, Workflows and Batches in Cargo

Makes Claude run Cargo actions, build workflows, trigger batches over a segment, message AI agents and query run history with SQL.

Installs: 10.5K; on skills.sh
Stars: 21; on GitHub
Files: 15; besides SKILL.md
Updated: Oct 2026; last repo commit

Claude uses cargo-ai orchestration to find an action, run it on one record, run a multi-step workflow, or fan a workflow across a segment, model or file as a batch. It can build or edit a node graph, draw a workflow as a diagram, message an AI agent, and query the runtime tables (runs, batches, spans, records) with SQL.

SKILL.md says every node execution costs 0.01 credits on top of the provider cost, and that batches must start with a 10 to 20 record sample and your approval. It needs the Cargo CLI and a Cargo sign-in.

Good for

GTM engineers building and scheduling Cargo workflows and plays
Operators running an action over a whole segment or model
Analysts querying runs, batches and spans in SQL

Install cargo-orchestration

Claude Code

Copy this prompt.

Install the cargo-orchestration 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

Make Cargo actually run something, or show what it would run — execute one connector action, run a multi-step workflow, trigger a batch across a whole segment or model, message an AI agent, build or edit a node graph, draw a workflow, tool or play as a diagram, and query the runtime tables (runs, batches, spans, records) with SQL. Triggers: "run this on all my contacts", "execute the action", "kick off a batch", "build a workflow", "schedule a play", "make it run every morning", "ask the agent", "show me the workflow", "what does this tool do", "visualize this play", "draw the graph", "explain this workflow", "how many runs failed today", "what is the output schema for this action", "add a step that". Skip when: explaining why a run misbehaved — use cargo-diagnostics; downloading result files — use cargo-analytics; committing the workflow as code — use cargo-project.

Sections in SKILL.md

Bootstrap
Discover resources first
Quick reference
Polling async operations
Execute actions
Find it first — action list
Resolve an action's output schema (without executing)
Dry run — check inputs and price, free, no account
Create a run
Create a batch
The sample gate
Send a message to an AI agent
Inspect records
Query orchestration history (orchestration query)
Fetch segment data
Use a workflow template

Key facts

Author: Cargo (frontmatter author: getcargo), in the vendor's own repo
License: MIT (LICENSE, README badge and plugin.json agree)
Version: 1.18.0
Installs on skills.sh: 10,543 (Nov 2, 2026)
GitHub stars: 21 (Nov 2, 2026)
Last commit: Oct 31, 2026
What installs: 16 files including SKILL.md: 14 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

Finds an action by keywords, free, with its credit costs and a pasteable action object.
Runs code · action list
Runs one connector, tool or agent action; --dry-run prices it without calling a provider.
Runs code · action execute
Runs one action over many records and bills per record.
Runs code · action execute-batch
Starts a workflow run, or runs an inline node graph.
Runs code · run create
Counts the audience for free, then fans a workflow over a segment, model, file or records.
Runs code · batch preview / create
Updates a play, disables it, sets health alerts, or removes a play or tool.
Delete · play and tool management
Sends a message to an agent chat and polls for the reply.
Runs code · Message an AI agent
Reads run, batch and record details and polls async operations.
Runs code · Inspect records
Runs ClickHouse SQL over runs, batches, spans and records.
Runs code · query execute
Lists traces and node executions by time, status or batch without SQL.
Runs code · trace and span list
Fetches records for a segment filter with a fetching limit.
Runs code · Fetch segment data
Starts from a template and validates and tests nodes before a run.
Runs code · Workflow templates and validation

From the official docs

Permissions

High risk

It runs paid actions and batches that can write to your CRM and workspace. Approve the sample first, then the full run, with the credit estimate in view.

What it can do

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

Watch out for

Batches fan out across every record and bill for each
A batch applies one workflow to a whole segment, model or file. SKILL.md says to preview the count for free, sample 10 to 20 records, then ask you to approve the full record count and credit estimate. github.com
Workflow nodes can write to outside systems
Actions include CRM syncs and messages. Check what a play writes and where before you run or schedule it. github.com
Plays and tools can be disabled or removed
play update --is-disabled, play remove and tool remove change automation that may be running. The plugin hook still prompts for remove and delete. 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
Every node execution costs 0.01 credits
SKILL.md says the charge applies whatever the node is, on top of provider costs. Step-heavy graphs add up. 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	Runs paid actions, workflows and batches Updates and removes plays and tools Cargo workspace sign-in (saved in ~/.config/cargo-ai/credentials.json)

Questions

What does cargo-orchestration do?

It makes Claude run things in Cargo. That means one action on one record, a workflow, a batch over a whole segment, a message to an AI agent, or an SQL query over run history.

What does a batch cost?

SKILL.md says cost has two terms: the provider cost times records, plus 0.01 credits per node execution. It requires a free count first, then a 10 to 20 record sample, then your approval with the record count and credit estimate before enrolling everything.

Can I see what an action would do before paying?

Yes. action list is free and shows credit costs, and action execute --dry-run validates your input and shows sample output and the price without calling a provider. batch preview counts a batch audience without creating it.

Can it delete things?

Yes. The quick reference includes play remove and tool remove. It can also disable a play with play update --is-disabled.

When should I use cargo-diagnostics or cargo-analytics instead?

SKILL.md says to use cargo-diagnostics to explain why a run misbehaved and cargo-analytics to download result files.

Does it need a Cargo account to try?

Browsing the action catalog and the dry-run work signed out. Anything that creates a run, a batch or a message needs a signed-in workspace.

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 runs real actions that spend credits and can write to your CRM and workspace. SKILL.md blocks full batches until you approve a record count and credit estimate after a sample, and its quick reference includes play and tool removal. Our advice: read the batch approval message, and run the free preview first.

Information

updated Nov 2, 2026

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

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-orchestration 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