Agent skill

External Agents

by BuilderIO in BuilderIO/agent-native

Connect external agents and MCP hosts (Claude, Claude Desktop, Claude Code, ChatGPT custom MCP apps, Codex, Cursor, Claude Cowork, VS Code GitHub Copilot, Goose, Postman, MCPJam) to an agent-native…

No licenceAuto-check: notesMobile

Install External Agents

skills CLI
$ npx skills add BuilderIO/agent-native --skill external-agents -a claude-code

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

GitHub CLI
$ gh skill install BuilderIO/agent-native external-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/BuilderIO/agent-native.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/external-agents .claude/skills/external-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
external-agents
GitHub stars
7.1k
Token cost
~7.2k tokens
SKILL.md length
3,602 words
Files
2 (incl. references)
Skills in repo
102
Repo updated
First seen
Licence
None found

At a glance

Connect external agents and MCP hosts (Claude, Claude Desktop, Claude Code, ChatGPT custom MCP apps, Codex, Cursor, Claude Cowork, VS Code GitHub Copilot, Goose, Postman, MCPJam) to an agent-native…

  • Works in 5 steps: Connect to hosted apps → Add a link builder to an action → The /_agent-native/open route → …
  • Adding an actions link builder
  • SKILL.md covers Rule, Why, App-facing MCP connectors and Provider API connectors, plus 5 more sections
  • Calls npx, pnpm and codex; reaches dispatch.agent-native.com and mail.agent-native.com; needs A2A_SECRET and ACCESS_TOKEN

What it does

External Agents is an agent skill from BuilderIO/agent-native. Connect external agents and MCP hosts (Claude, Claude Desktop, Claude Code, ChatGPT custom MCP apps, Codex, Cursor, Claude Cowork, VS Code GitHub Copilot, Goose, Postman, MCPJam) to an agent-native app over MCP, and round-trip artifacts back into the UI with MCP Apps and deep links. Use when adding an action's link builder or mcpApp, wiring the /agent-native/open route, exposing an "ingest" action to MCP/A2A, or scaffolding apps from an external agent.

Its SKILL.md is about 7.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/mcp-apps-embedding.md`).

It sits in Mobile, covering Project scaffolding, API testing and MCP servers. It works with Model Context Protocol, OpenAI, Postman and Visual Studio Code. The repository describes itself as: A framework for building agentic apps.

When your agent uses it

  • Adding an actions link builder
  • Wiring the /agent-native/open route
  • Exposing an ingest action to MCP/A2A
  • Scaffolding apps from an external agent

Example prompts

  • “ingest”
  • “/external-agents”

Requirements

  • Node.js
  • A credential in A2A_SECRET

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Connect to hosted apps
  2. Add a link builder to an action
  3. The /_agent-native/open route
  4. "Ingest" actions for external agents
  5. Advanced: local development & manual setup

What it can do on your machine

Read from SKILL.md and the folder at commit e16da0c. 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
    • pnpm
    • codex
    • cursor
    • opencode

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

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • dispatch.agent-native.com
    • mail.agent-native.com

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

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • A2A_SECRET
    • ACCESS_TOKEN
    • BETTER_AUTH_SECRET

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

Context cost

External Agents loads about 7.2k tokens when it runs, and up to ~9.6k if it reads all its reference files. Until then it costs about 120 tokens; SKILL.md has 3,602 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~120
When it runs · the whole SKILL.md, loaded when a task matches
~7.2k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~9.6k

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:452
    andom `ACCESS_TOKEN` into the workspace `.env` for

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 3,602 words (~7,152 tokens).

“An agent-native app is reachable by any MCP-compatible host. Keep setup simple: for workspace or cross-app access, add one remote MCP connector: https://dispatch.agent-native.com/mcp. Dispatch's Agents page controls whether that single connector reaches all apps or only selected apps, and Dispatch…”

— opening of SKILL.md by BuilderIO
name
external-agents
scope
dev
metadata.internal
true

Read the full SKILL.md on GitHub

Files

SKILL.md and 1 other file (references) in .agents/skills/external-agents of BuilderIO/agent-native.

  • SKILL.md
  • references/mcp-apps-embedding.md

Open the folder on GitHubat commit e16da0c

Compare with similar skills

External 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.

External Agents compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
External Agents this skillBuilderIO/agent-native7.1k—~7.2kAutomated safety check: NotesNone
Cao MCP Appsawslabs/cli-agent-orchestrator1.4k—~1.9kAutomated safety check: PassApache-2.0
UI Widget Developermicrosoft/work-iq1k—~6.1kAutomated safety check: NotesCustom licence
Flutter MCP Toolkit Maintain WebArenukvern/mcp_flutter386—~1.6kAutomated safety check: PassMIT
Chatgpt AppsHaohao-end/openagent8071 repos~4.9kAutomated safety check: PassApache-2.0
Xquik MCPXquik-dev/x-twitter-scraper2091 repos~997Automated safety check: PassMIT

Similar skills

  • Cao MCP Apps

    awslabs/cli-agent-orchestrator

    Official

    Enable, operate, and extend CAO's MCP Apps surface — the host-rendered fleet dashboard visible inside MCP App hosts (Claude Desktop, ChatGPT, VS Code Copilot, Goose, Postman).

    1.4k GitHub stars~1.9k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • UI Widget Developer

    microsoft/work-iq

    Official

    Build MCP servers for Copilot Chat using the OpenAI Apps SDK or MCP Apps SDK widget rendering support (any language).

    1k GitHub stars~6.1k tokensUpdated yesterday
    Agent WorkflowsAuto-check: notes
  • Flutter MCP Toolkit Maintain Web

    Arenukvern/mcp_flutter

    Maintains showcase/fluttertestapp and intentcall web targets (Chrome, web codegen, WebMCP bootstrap, web-showcase, webmcp verify, Chrome DevTools MCP).

    386 GitHub stars~1.6k tokensUpdated 5 days ago
    MobileAuto-check passed
  • Chatgpt Apps

    Haohao-end/openagent

    Build, scaffold, refactor, and troubleshoot ChatGPT Apps SDK applications that combine an MCP server and widget UI.

    807 GitHub starsUsed in 1 repo~4.9k tokens
    Agent WorkflowsAuto-check passed
  • Xquik MCP

    Xquik-dev/x-twitter-scraper

    Connect, verify, and troubleshoot Xquik's remote MCP server.

    209 GitHub starsUsed in 1 repo~997 tokens
    Backend & APIsAuto-check passed
  • Setup MCP Server

    nesquikm/mcp-rubber-duck

    Add mcp-rubber-duck MCP server to an AI coding tool (Claude Desktop, Cursor, VS Code, Windsurf, etc.)

    178 GitHub stars~1.3k tokensUpdated 2 days ago
    Agent WorkflowsAuto-check: notes

More from BuilderIO/agent-native

All 102 skills in this repo
  • Actions

    BuilderIO/agent-native

    How to create and run agent actions. An agent skill from BuilderIO/agent-native.

    7.1k GitHub stars~4.4k tokensUpdated today
    Auto-check passed
  • Client Methods

    BuilderIO/agent-native

    Client method surface rules. An agent skill from BuilderIO/agent-native.

    7.1k GitHub stars~1.2k tokensUpdated today
    Auto-check passed
  • Adding A Feature

    BuilderIO/agent-native

    The four-area checklist every new feature must complete. An agent skill from BuilderIO/agent-native.

    7.1k GitHub stars~4k tokensUpdated today
    Auto-check passed
  • Address Feedback

    BuilderIO/agent-native

    Triage feedback from docs, issues, Slack threads, or pasted notes into verified bugs, UX proposals, unclear questions, and skipped noise.

    7.1k GitHub stars~4.4k tokensUpdated today
    Auto-check passed
  • Audit Log

    BuilderIO/agent-native

    Durable, access-scoped, append-only record of who changed what app data, when, and whether it was the agent or a human.

    7.1k GitHub stars~2k tokensUpdated today
    Auto-check passed
  • Automations

    BuilderIO/agent-native

    Event-triggered and schedule-triggered automations with natural-language conditions.

    7.1k GitHub stars~4.4k tokensUpdated today
    Auto-check passed

Questions about External Agents

What does External Agents do?

Connect external agents and MCP hosts (Claude, Claude Desktop, Claude Code, ChatGPT custom MCP apps, Codex, Cursor, Claude Cowork, VS Code GitHub Copilot, Goose, Postman, MCPJam) to an agent-native…. External Agents is an agent skill from BuilderIO/agent-native. Connect external agents and MCP hosts (Claude, Claude Desktop, Claude Code, ChatGPT custom MCP apps, Codex, Cursor, Claude Cowork, VS Code GitHub Copilot, Goose, Postman, MCPJam) to an agent-native app over MCP, and round-trip artifacts back into the UI with MCP Apps and deep links.

When should I use External Agents?

External Agents fits situations like: adding an actions link builder; wiring the /agent-native/open route; exposing an ingest action to MCP/A2A; scaffolding apps from an external agent.

How do I install External Agents in Claude Code?

Run `npx skills add BuilderIO/agent-native --skill external-agents -a claude-code`. Or copy the skill folder (.agents/skills/external-agents in BuilderIO/agent-native) into .claude/skills/external-agents in your project. Claude Code loads it when a task matches its description.

How do I install External Agents in Codex?

Run `npx skills add BuilderIO/agent-native --skill external-agents -a codex`. Or copy the skill folder (.agents/skills/external-agents in BuilderIO/agent-native) into .agents/skills/external-agents in your project. Codex loads it when a task matches its description.

Can I use External 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 BuilderIO/agent-native --skill external-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/external-agents, .gemini/skills/external-agents, .github/skills/external-agents and .opencode/skills/external-agents in your project.

What does External Agents need to run?

Going by SKILL.md and its folder, External Agents needs the command-line tools its instructions call (npx, pnpm, codex, cursor and opencode) and credentials named A2A_SECRET, ACCESS_TOKEN and BETTER_AUTH_SECRET. Our summary lists: Node.js; A credential in A2A_SECRET.

Does External Agents access the network?

SKILL.md names 2 domains. In commands or code: dispatch.agent-native.com and mail.agent-native.com; the agent is likely to contact these when it follows the instructions. This is read from the text; nothing was executed.

Is External Agents 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 External Agents use?

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

How many tokens does External Agents use?

About 7.2k tokens (SKILL.md is roughly 29k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2.4k tokens, read only when the agent opens those files.

What are the alternatives to External Agents?

Skills that share tags, products or a category with External Agents: Cao MCP Apps (awslabs/cli-agent-orchestrator, 1.4k stars), UI Widget Developer (microsoft/work-iq, 1k stars), Flutter MCP Toolkit Maintain Web (Arenukvern/mcp_flutter, 386 stars) and Chatgpt Apps (Haohao-end/openagent, 807 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains External Agents?

BuilderIO (a GitHub organization) maintains it in BuilderIO/agent-native, which has 7,087 GitHub stars. The repository holds 102 skills in this directory. The repository was last updated on October 8, 2026.

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