New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Medusa Internal Admin Agents

by medusajs in 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.

No licenceAuto-check passedBackend & APIs

Install Medusa Internal Admin Agents

skills CLI
$ npx skills add medusajs/medusa-agent-skills --skill creating-internal-agents -a claude-code

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

GitHub CLI
$ gh skill install medusajs/medusa-agent-skills creating-internal-agents --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-dev/skills/creating-internal-agents .claude/skills/creating-internal-agents && 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
creating-internal-agents
GitHub stars
228
Token cost
~1.9k tokens
SKILL.md length
642 words
Files
8
Skills in repo
16
Repo updated
First seen
Licence
None found

At a glance

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.

  • Works in 6 steps: Start the Medusa dev server (npx medusa… → Open the admin dashboard and navigate to… → Type a simple read-only prompt — e.g.… → …
  • Building a store operations assistant inside the Medusa admin dashboard
  • SKILL.md covers Constraints, CRITICAL: Load Reference Files…, Related Skills and Architecture Overview, plus 3 more sections
  • Calls npx

What it does

The target is an internal, admin-facing agent used by merchants and store operators through the Medusa admin dashboard, not a storefront chatbot for customers. The agent writes TypeScript and runs it with MedusaExec for data operations, with custom tools reserved for things code cannot express, such as an external API call with a secret key. Conversation history sits in shared AgentSession and AgentMessage models told apart by an agent_type field.

Security rules are explicit: every agent route must live under src/api/admin and use authenticated requests, because MedusaExec has full database access and an open endpoint would allow remote code execution. Responses stream as NDJSON, the MedusaContainer is passed through experimental_context rather than imported, and migrations run after model changes. Seven reference files cover data models, service, agent setup, the API route, streaming, the admin extension and MedusaExec, and the right one is loaded before any code is written.

When your agent uses it

  • Building a store operations assistant inside the Medusa admin dashboard
  • Adding a product audit or cohort analysis agent for merchants
  • Streaming agent replies to an admin chat panel

Example prompts

  • “Add an internal agent to our Medusa admin that helps staff audit product listings.”
  • “Set up the AgentSession and AgentMessage models and the streaming chat route for an operations assistant.”
  • “Check my agent route for auth problems. It must live under src/api/admin.”

Requirements

  • A Medusa project with its admin dashboard

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. Start the Medusa dev server (npx medusa develop)
  2. Open the admin dashboard and navigate to the agent's page in the sidebar (the label set in defineRouteConfig)
  3. Type a simple read-only prompt — e.g. "How many products are in the store?" — and submit
  4. Verify the response streams in and a new session appears in the sidebar
  5. Send a follow-up message in the same session to confirm conversation history is preserved
  6. Reload the page, select the session from the sidebar, and confirm the message history is restored from the database

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 nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • npx

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

  • Network

    No URLs in SKILL.md. Its commands use npx, 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 Internal Admin Agents loads about 1.9k tokens when it runs. Until then it costs about 137 tokens; SKILL.md has 642 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~137
When it runs · the whole SKILL.md, loaded when a task matches
~1.9k

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 passed

The automated check found no risky patterns in SKILL.md.

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 642 words (~1,866 tokens).

“This skill covers the full stack for adding an internal, admin-facing AI agent to a Medusa project. These agents are used by merchants and store operators through the Medusa admin dashboard — not by customers on a storefront. For customer-facing…”

— opening of SKILL.md by medusajs
name
creating-internal-agents

Read the full SKILL.md on GitHub

Files

SKILL.md and 7 other files in plugins/medusa-dev/skills/creating-internal-agents of medusajs/medusa-agent-skills.

  • SKILL.md
  • reference/admin-extension.md
  • reference/agent-setup.md
  • reference/api-route.md
  • reference/data-models.md
  • reference/medusa-exec.md
  • reference/service.md
  • reference/streaming.md

Open the folder on GitHubat commit 066132d

Compare with similar skills

Medusa Internal Admin Agents 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 Internal Admin Agents compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Medusa Internal Admin Agents this skillmedusajs/medusa-agent-skills228—~1.9kAutomated safety check: PassNone
Posthog DesktopPostHog/posthog40k—~1.6kAutomated safety check: PassCustom licence
AWS Harnesshoodini/ai-agents-skills282—~4.2kAutomated safety check: NotesNone
Node Backend Development Guidelinesdiet103/claude-code-infrastructure-showcase10k2 repos~2kAutomated safety check: PassMIT
cmux Backend Rulesmanaflow-ai/cmux28k1 repos~682Automated safety check: PassCustom licence
Trigger.dev Agent Patternspapermark/papermark9.2k—~2kAutomated safety check: PassCustom licence

Similar skills

  • Posthog Desktop

    PostHog/posthog

    Official

    Scopes work to the desktop app at products/desktop — a nested standalone pnpm/turbo/Biome workspace imported from the now-archived PostHog/code repo, with posthog/posthog the only source of truth…

    40k GitHub stars~1.6k tokensUpdated today
    Backend & APIsAuto-check passed

  • AWS Harness

    hoodini/ai-agents-skills

    Build a new AI agent on AWS and deploy it easily, OR wrap and deploy an agent you already have, using the Amazon Bedrock AgentCore harness.

    282 GitHub stars~4.2k tokensUpdated 2 mo ago
    Backend & APIsAuto-check: notes

  • Node Backend Development Guidelines

    diet103/claude-code-infrastructure-showcase

    Sets layered architecture and coding rules for Node.js, Express and TypeScript microservices, covering routes, controllers, services, repositories, Prisma, Sentry and Zod.

    10k GitHub starsUsed in 2 repos~2k tokens
    Backend & APIsAuto-check passed

  • cmux Backend Rules

    manaflow-ai/cmux

    Sets the backend TypeScript and Cloud VM rules for cmux: Effect-based services, thin route handlers, Postgres as source of truth, migrations and provider secrets.

    28k GitHub starsUsed in 1 repo~682 tokens
    Backend & APIsAuto-check passed

  • Trigger.dev Agent Patterns

    papermark/papermark

    Patterns for building LLM agents on Trigger.dev tasks: prompt chaining, routing, parallel workers, orchestrator-workers, evaluator loops and human approval gates.

    9.2k GitHub stars~2k tokensUpdated 1 mo ago
    AI & LLM EngineeringAuto-check passed

  • Twenty Syncable Entity Validation

    twentyhq/twenty

    Contributor guide for step three of adding a syncable entity to the Twenty server: write the validator, the migration action builder and the orchestrator wiring.

    58k GitHub stars~3.3k tokensUpdated today
    Backend & APIsAuto-check passed

More from medusajs/medusa-agent-skills

All 16 skills in this repo

  • 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.

    228 GitHub stars~4.1k tokensUpdated 4 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.

    228 GitHub stars~1.1k tokensUpdated 4 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.

    228 GitHub stars~883 tokensUpdated 4 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.

    228 GitHub stars~1.2k tokensUpdated 4 days ago
    Auto-check passed

  • Medusa Cloud Local Build

    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.

    228 GitHub stars~1k tokensUpdated 4 days ago
    Auto-check: notes

  • Mcloud Logs

    medusajs/medusa-agent-skills

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

    228 GitHub stars~811 tokensUpdated 4 days ago
    Auto-check passed

Works with

Categories

Questions about Medusa Internal Admin Agents

What does Medusa Internal Admin Agents do?

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. The target is an internal, admin-facing agent used by merchants and store operators through the Medusa admin dashboard, not a storefront chatbot for customers. The agent writes TypeScript and runs it with MedusaExec for data operations, with custom tools reserved for things code cannot express, such as an external API call with a secret key.

When should I use Medusa Internal Admin Agents?

Medusa Internal Admin Agents fits situations like: building a store operations assistant inside the Medusa admin dashboard; adding a product audit or cohort analysis agent for merchants; streaming agent replies to an admin chat panel.

How do I install Medusa Internal Admin Agents in Claude Code?

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

How do I install Medusa Internal Admin Agents in Codex?

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

Can I use Medusa Internal Admin Agents 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 creating-internal-agents -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/creating-internal-agents, .gemini/skills/creating-internal-agents, .github/skills/creating-internal-agents and .opencode/skills/creating-internal-agents in your project.

What does Medusa Internal Admin Agents need to run?

Going by SKILL.md and its folder, Medusa Internal Admin Agents needs the command-line tools its instructions call (npx). Our summary lists: A Medusa project with its admin dashboard.

Does Medusa Internal Admin Agents access the network?

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

Is Medusa Internal Admin Agents safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Medusa Internal Admin Agents use?

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

How many tokens does Medusa Internal Admin Agents use?

About 1.9k tokens (SKILL.md is roughly 7.5k 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 Internal Admin Agents?

Skills that share tags, products or a category with Medusa Internal Admin Agents: Posthog Desktop (PostHog/posthog, 40k stars), AWS Harness (hoodini/ai-agents-skills, 282 stars), Node Backend Development Guidelines (diet103/claude-code-infrastructure-showcase, 10k stars) and cmux Backend Rules (manaflow-ai/cmux, 28k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Medusa Internal Admin Agents?

medusajs (a GitHub organization) maintains it in medusajs/medusa-agent-skills, which has 228 GitHub stars. The repository holds 16 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.