Agent skill

Medusa Cloud Local Build

by medusajs in medusajs/medusa-agent-skills

Reproduces a Medusa Cloud build on your machine with mcloud local build, to debug build-failed deployments without pushing or waiting on Cloud.

No licenceAuto-check: notesDevOps & Cloud

Install Medusa Cloud Local Build

skills CLI
$ npx skills add medusajs/medusa-agent-skills --skill mcloud-local -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install medusajs/medusa-agent-skills mcloud-local --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/medusajs/medusa-agent-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/medusa-cloud/skills/mcloud-local .claude/skills/mcloud-local && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
mcloud-local
GitHub stars
227
Token cost
~1k tokens
SKILL.md length
347 words
Files
1
Skills in repo
15
Repo updated
First seen
Licence
None found

At a glance

Reproduces a Medusa Cloud build on your machine with mcloud local build, to debug build-failed deployments without pushing or waiting on Cloud.

  • Debugging a Cloud deployment that ended in build-failed
  • SKILL.md covers Constraints, Command, Reproduce a Build Failure and Examples
  • Calls jq and git
  • Iterating on a build fix without pushing to the tracked branch

What it does

This skill runs `mcloud local build` to reproduce a Medusa Cloud build on your own machine, so you can debug a deployment in the build-failed state without pushing to the tracked branch and waiting for Cloud. It infers the root path and build variables from the linked Cloud project and environment, builds the backend by default and builds the storefront with `--type storefront`.

It has clear limits. Docker must be installed and running, the command must run inside the project's Git repository, and it reproduces build failures only, not runtime deployment failures, which are handled with `mcloud logs`. There is no JSON output: build output streams as plain text and exit code 0 signals success. The Docker cache is off by default so variable changes always take effect, `--docker-cache` turns it on, and `--env-file` or repeated `--var` flags override build variables.

On success the backend image is tagged with the repository name and commit hash, and a storefront build writes its output directory and prints the path. To reproduce a failure, the agent checks out the same commit the failed deployment built, then branches on the exit code. The command needs mcloud CLI version 0.1.10 or later.

When your agent uses it

  • Debugging a Cloud deployment that ended in build-failed
  • Iterating on a build fix without pushing to the tracked branch
  • Testing changed build variables locally before updating the environment

Example prompts

  • “Our last Cloud deployment failed at build. Reproduce it locally and tell me which step breaks.”
  • “Run a local storefront build using the variables from my local .env file.”
  • “Try the backend build with API_URL overridden to the staging address and keep the Docker cache on.”

Requirements

  • Docker installed and running
  • The mcloud CLI, version 0.1.10 or later
  • A shell inside the project's Git repository
  • Pre-approved tools (allowed-tools): Bash(mcloud local*), Bash(mcloud deployments*), Bash(mcloud use*), Bash(git*), Bash(jq*)

What it can do on your machine

Read from SKILL.md and the folder at commit 066132d. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Bash(mcloud local*)
    • Bash(mcloud deployments*)
    • Bash(mcloud use*)
    • Bash(git*)
    • Bash(jq*)

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • jq
    • git

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Medusa Cloud Local Build loads about 1k tokens when it runs. Until then it costs about 75 tokens; SKILL.md has 347 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~75
When it runs · the whole SKILL.md, loaded when a task matches
~1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NoteMentions a .env fileSKILL.md:39
    - `--env-file <path>` — Use a local `.env` file instead of the Cloud environment's variables
  • NoteMentions a .env fileSKILL.md:82
    # Build against a local .env file
  • NoteMentions a .env fileSKILL.md:83
    mcloud local build --env-file .env

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

Without a licence we can't republish the file, so here is its outline and opening line. It has 347 words (~1,003 tokens).

“Execute mcloud local build to run a Cloud build on the local machine, mirroring how Cloud builds the project. Use it to debug build-failed deployments without pushing changes and waiting for a full Cloud build.”

— opening of SKILL.md by medusajs
name
mcloud-local
allowed-tools
Bash(mcloud local*), Bash(mcloud deployments*), Bash(mcloud use*), Bash(git*), Bash(jq*)

Read the full SKILL.md on GitHub

Files

Just SKILL.md in plugins/medusa-cloud/skills/mcloud-local of medusajs/medusa-agent-skills.

Open the folder on GitHubat commit 066132d

Compare with similar skills

Medusa Cloud Local Build next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Medusa Cloud Local Build compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Medusa Cloud Local Build this skillmedusajs/medusa-agent-skills227—~1kAutomated safety check: NotesNone
Releasear-io/ar-io-node127—~4.2kAutomated safety check: NotesAGPL-3.0
Demo Local Rolloutcarverauto/serviceradar921—~4.2kAutomated safety check: PassApache-2.0
Buzz Self Hostingtonbistudio/buzz-skills274—~2.2kAutomated safety check: NotesMIT
Deploying To Azuremicrosoft-foundry/foundry-agent-webapp127—~2.2kAutomated safety check: WarnMIT
Deploy To Tempsgotempsh/temps826—~1.3kAutomated safety check: NotesApache-2.0

Similar skills

  • Release

    ar-io/ar-io-node

    Drive the AR.IO Node release process end-to-end — preflight checks, prepare commit, finalize with image SHAs, test docker compose profiles, tag & publish, and post-release cleanup.

    127 GitHub stars~4.2k tokensUpdated yesterday
    DevOps & CloudAuto-check: notes
  • Demo Local Rollout

    carverauto/serviceradar

    Build unpublished sha-... An agent skill from carverauto/serviceradar.

    921 GitHub stars~4.2k tokensUpdated yesterday
    DevOps & CloudAuto-check passed
  • Buzz Self Hosting

    tonbistudio/buzz-skills

    A skill your agent uses when helping a user set up, debug, or operate a self-hosted Buzz relay through Docker Compose.

    274 GitHub stars~2.2k tokensUpdated 2 mo ago
    DevOps & CloudAuto-check: notes
  • Deploying To Azure

    microsoft-foundry/foundry-agent-webapp

    Provides deployment commands and troubleshooting for Azure Container Apps.

    127 GitHub stars~2.2k tokensUpdated 5 mo ago
    DevOps & CloudAuto-check: warnings
  • Deploy To Temps

    gotempsh/temps

    Deploy applications to the Temps platform with automatic framework detection, Dockerfile generation, and container orchestration.

    826 GitHub stars~1.3k tokensUpdated yesterday
    DevOps & CloudAuto-check: notes
  • Perplexity Server Deploy

    escapeWu/perplexity-ai

    Deploys the perplexity-ai project to its production server by pushing main, fast-forwarding the server checkout, rebuilding the image there and verifying health.

    169 GitHub stars~662 tokensUpdated 11 days ago
    DevOps & CloudAuto-check: notes

More from medusajs/medusa-agent-skills

All 15 skills in this repo
  • Medusa Internal Admin Agents

    medusajs/medusa-agent-skills

    Walks through adding an AI agent for store operators to a Medusa project: data models, module service, agent runtime, streaming API route and admin chat UI.

    227 GitHub stars~1.9k tokensUpdated 3 days ago
    Auto-check passed
  • Learning Medusa

    medusajs/medusa-agent-skills

    Interactive tutorial where the agent teaches Medusa development by guiding you through building a brands feature, with lessons and verification checkpoints.

    227 GitHub stars~4.1k tokensUpdated 3 days ago
    Auto-check passed
  • Medusa Cloud CLI Authentication

    medusajs/medusa-agent-skills

    Runs the mcloud commands for logging in, checking who is authenticated, and choosing the active organization, project and environment.

    227 GitHub stars~1.1k tokensUpdated 3 days ago
    Auto-check passed
  • Medusa Cloud Deployments CLI

    medusajs/medusa-agent-skills

    Lists Medusa Cloud deployments, fetches one deployment's details and reads backend or storefront build logs through the mcloud CLI to debug failed builds.

    227 GitHub stars~883 tokensUpdated 3 days ago
    Auto-check passed
  • mcloud Environments

    medusajs/medusa-agent-skills

    Runs mcloud environments commands to list, inspect, create, delete, redeploy or rebuild environments in Medusa Cloud projects.

    227 GitHub stars~1.2k tokensUpdated 3 days ago
    Auto-check passed
  • Mcloud Logs

    medusajs/medusa-agent-skills

    Execute mcloud logs to fetch and stream runtime logs for Cloud environments.

    227 GitHub stars~811 tokensUpdated 3 days ago
    Auto-check passed

Works with

Questions about Medusa Cloud Local Build

What does Medusa Cloud Local Build do?

Reproduces a Medusa Cloud build on your machine with mcloud local build, to debug build-failed deployments without pushing or waiting on Cloud. This skill runs `mcloud local build` to reproduce a Medusa Cloud build on your own machine, so you can debug a deployment in the build-failed state without pushing to the tracked branch and waiting for Cloud. It infers the root path and build variables from the linked Cloud project and environment, builds the backend by default and builds the storefront with `--type storefront`.

When should I use Medusa Cloud Local Build?

Medusa Cloud Local Build fits situations like: debugging a Cloud deployment that ended in build-failed; iterating on a build fix without pushing to the tracked branch; testing changed build variables locally before updating the environment.

How do I install Medusa Cloud Local Build in Claude Code?

Run `npx skills add medusajs/medusa-agent-skills --skill mcloud-local -a claude-code`. Or copy the skill folder (plugins/medusa-cloud/skills/mcloud-local in medusajs/medusa-agent-skills) into .claude/skills/mcloud-local in your project. Claude Code loads it when a task matches its description.

How do I install Medusa Cloud Local Build in Codex?

Run `npx skills add medusajs/medusa-agent-skills --skill mcloud-local -a codex`. Or copy the skill folder (plugins/medusa-cloud/skills/mcloud-local in medusajs/medusa-agent-skills) into .agents/skills/mcloud-local in your project. Codex loads it when a task matches its description.

Can I use Medusa Cloud Local Build in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add medusajs/medusa-agent-skills --skill mcloud-local -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/mcloud-local, .gemini/skills/mcloud-local, .github/skills/mcloud-local and .opencode/skills/mcloud-local in your project.

What does Medusa Cloud Local Build need to run?

Going by SKILL.md and its folder, Medusa Cloud Local Build needs the command-line tools its instructions call (jq and git). Our summary lists: Docker installed and running; The mcloud CLI, version 0.1.10 or later; A shell inside the project's Git repository. Its frontmatter pre-approves these tools: Bash(mcloud local*), Bash(mcloud deployments*), Bash(mcloud use*), Bash(git*), Bash(jq*).

Does Medusa Cloud Local Build access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Medusa Cloud Local Build safe to install?

Our automated static check of SKILL.md found notes only (mentions a .env file), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Medusa Cloud Local Build use?

No licence was found for Medusa Cloud Local Build or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Medusa Cloud Local Build use?

About 1k tokens (SKILL.md is roughly 4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Medusa Cloud Local Build?

Skills that share tags, products or a category with Medusa Cloud Local Build: Release (ar-io/ar-io-node, 127 stars), Demo Local Rollout (carverauto/serviceradar, 921 stars), Buzz Self Hosting (tonbistudio/buzz-skills, 274 stars) and Deploying To Azure (microsoft-foundry/foundry-agent-webapp, 127 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Medusa Cloud Local Build?

medusajs (a GitHub organization) maintains it in medusajs/medusa-agent-skills, which has 227 GitHub stars. The repository holds 15 skills in this directory. The repository was last updated on October 5, 2026.

Source: medusajs/medusa-agent-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.