cargo-context Skill for Claude Code: Write Your GTM Knowledge Base in Cargo

Lets Claude read and write your Cargo GTM knowledge base: ICPs, personas, plays, proof points and objections, stored as markdown in a git repo.

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 context runtime to browse, read, write and edit files in your workspace's git-backed context repository, and context graph get to read its knowledge graph. The repo has 12 domain folders, among them icp, persona, play, proof, objection and signal.

SKILL.md says write, edit and execute push to the default branch of the repo, so they are not local-only. It needs the Cargo CLI and a Cargo sign-in. Deriving who buys from won and lost data is cargo-gtm; this skill writes the conclusion down.

Good for

Marketers documenting ICPs, personas and positioning
Sales leaders capturing objections and battlecards
GTM engineers keeping context for agents in one repo

Install cargo-context

Claude Code

Copy this prompt.

Install the cargo-context 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

Read and write the workspace GTM knowledge base — the git-backed repository of markdown describing ICPs, personas, plays, proof points, objections, competitors, and signals — plus its runtime sandbox and typed knowledge graph. Triggers: "document our ICP", "write up this persona", "what is our positioning", "add a battlecard", "capture this objection", "what do we know about <segment>", "update our context", "what is in the context repo", "who do we sell to". Skip when: discovering who actually buys from you by analyzing won/lost data — that is cargo-gtm (this skill writes the conclusion down, it does not derive it); storing structured records rather than prose — use cargo-storage; attaching documents to an agent for RAG — use cargo-content.

Sections in SKILL.md

Bootstrap
Discover the context first
Quick reference
Runtime sandbox
Browse and read
Write a new file
Role
KPIs
Pains
Motivations
Day-to-day
Preferred channels
Common objections
How we land
Edit an existing file
Execute a command in the sandbox

Key facts

Author: Cargo (frontmatter author: getcargo), in the vendor's own repo
License: MIT (LICENSE, README badge and plugin.json agree)
Version: 1.4.2
Installs on skills.sh: 10,494 (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 entries at the root or under a subpath of the sandbox.
Runs code · runtime browse
Reads a file or a line range.
Runs code · runtime read
Creates or overwrites a file and pushes a commit to the default branch.
Runs code · runtime write
Replaces text in a file and pushes a commit to the default branch.
Runs code · runtime edit
Runs a command in the sandbox; changed tracked files are committed and pushed.
Delete · runtime execute
Reads the typed knowledge graph built from the repo.
Runs code · graph get
Twelve domain folders, frontmatter with title and description, and file templates.
Conventions

From the official docs

Permissions

Medium risk

It commits and pushes to your workspace context repository, and execute can rewrite tracked files. Confirm the workspace and review each change.

What it can do

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

Watch out for

Writes push to the default branch
write and edit are not local-only. Confirm the workspace with cargo-ai whoami before the first write, because there is no dry-run. github.com
execute can change or delete tracked files
SKILL.md says a sed -i or rm run through execute lands in git as an auto-commit. Review commands before they run. 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
Mirrored content files appear in the repo
Content files uploaded with mirroring on are committed under .files/ in the context repo. Keep sensitive files out of mirroring. 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	Writes and pushes commits to the workspace context repository Cargo workspace sign-in (saved in ~/.config/cargo-ai/credentials.json)

Questions

What does cargo-context do?

It lets Claude keep your go-to-market knowledge in one place. It writes personas, ICPs, plays, proof points and objections as markdown in a git-backed repo that belongs to your Cargo workspace, and reads them back.

Does it commit to git?

Yes. SKILL.md says write and edit push to the default branch, and execute commits and pushes any tracked files it changes, for example from a sed or rm. Gitignored paths are skipped.

Which workspace does it write to?

The one you are signed in to. SKILL.md says there is no dry-run mode, so confirm the workspace name with cargo-ai whoami and ask if the name looks generic before the first write.

Context or cargo-storage?

Use this for prose knowledge. SKILL.md sends structured records to cargo-storage and documents attached to an agent for RAG to cargo-content.

Can it update the repo from sales calls?

SKILL.md says edits derived from sales-call analysis should be applied one at a time with human review, not batched.

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 writes straight to a git repo your Cargo workspace uses. Writes and edits push to the default branch, and execute can delete or rewrite tracked files. Our advice: confirm the workspace name first and review each change, as SKILL.md asks for call-derived edits.

Information

updated Nov 2, 2026

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

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-context 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