Agent Wormhole logo

Agent Wormhole

OrganizationPopular
BankrBot
agent-wormhole

Use Agent Wormhole for one-time sealed handoffs between autonomous agents, including encrypted mission briefs, scoped secrets, temporary artifacts, receipts, config drops, CLI/API usage, ECHO holder access, and Bankr x402 paid opens.

Overview

PublisherBankrBot
Repositoryskills
Skill nameagent-wormhole
Stars
1.2K
Forks
622
Bundled files
1
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by BankrBot on GitHub. Read the source before you install it.

Installation

Install the Agent Wormhole AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/BankrBot/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/agent-wormhole .claude/skills/agent-wormhole
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Agent Wormhole in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Agent Wormhole on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Agent Wormhole is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Agent Wormhole

Agent Wormhole opens a temporary encrypted passage for agent handoffs. The payload can be claimed once, then the channel collapses.

Before First Use

This skill executes the @builtbyecho/agent-wormhole npm package. Before running any agent-wormhole or npx @builtbyecho/agent-wormhole command for the first time in a session, tell the user:

About to install/run @builtbyecho/agent-wormhole (v0.1.2) from npm. It is an encrypted one-time-handoff CLI that writes payloads to a local .agent-wormholes/ directory and (for holder/paid opens) calls storage.builtbyecho.xyz and the Bankr x402 endpoint. It does NOT sign transactions or access private keys.

Proceed? (y/n)

Wait for explicit confirmation before the first invocation. Subsequent calls in the same session do not need to re-prompt.

Pin the version when invoking via npx:

bash
npx -p @builtbyecho/agent-wormhole@0.1.2 agent-wormhole <args>

Links

  • Website: https://www.builtbyecho.xyz
  • Product page: https://www.builtbyecho.xyz/agent-wormhole.html
  • Source: https://github.com/BuiltByEcho/agent-wormhole
  • Package: https://www.npmjs.com/package/@builtbyecho/agent-wormhole
  • Hosted skill file: https://www.builtbyecho.xyz/skills/agent-wormhole/SKILL.md

Use this skill when a task involves:

  • sending or receiving one-time agent handoffs
  • passing mission briefs, configs, receipts, files, or scoped secrets
  • using the agent-wormhole CLI or HTTP API
  • checking ECHO holder sponsored access
  • checking Bankr x402 paid open status
  • deploying or operating the VPS service

Quick Commands

From a project that has the package installed:

bash
agent-wormhole send --text "mission brief" --ttl 10m
agent-wormhole send --file ./artifact.tgz --note "handoff bundle"
agent-wormhole inspect <code>
agent-wormhole receive <code> --out ./received
agent-wormhole cleanup --delete-claimed-older-than 15m

For one-off use without installing globally:

bash
npx -p @builtbyecho/agent-wormhole@0.1.2 agent-wormhole send --text "mission brief"

Mental Model

  • Codes are id.secret.
  • id locates stored metadata.
  • secret derives the AES-256-GCM decrypt key and is not stored.
  • Default TTL is 10 minutes.
  • Max TTL is 24 hours unless explicitly configured lower.
  • Default max payload is 5 MB.
  • Receipts are written for opens and claims.

Access Paths

  • Local CLI/library opens record access.path = local.
  • Direct API holder opens require an EIP-191 signature from a wallet holding at least 50,000,000 ECHO on Base and record access.path = echo_holder.
  • Bankr x402 paid opens are handled by agent-wormhole-open and record access.path = x402_paid.
  • Claiming is free.

Live Endpoints

  • Direct holder/API route: https://storage.builtbyecho.xyz/agent-wormhole
  • Bankr x402 paid open: https://x402.bankr.bot/0x2a16625fad3b0d840ac02c7c59edea3781e340ae/agent-wormhole-open
  • Self-hosted local service default: http://127.0.0.1:8791

Verification

From the package root:

bash
npm test
node --check src/cli.js
node --check src/index.js
node --check src/server.js
npm pack --json --dry-run

For live health:

bash
curl -sS https://storage.builtbyecho.xyz/agent-wormhole/health

For Bankr status, check both registry and execution:

bash
bankr --config "$BANKR_OWNER_CONFIG" x402 list
bankr x402 schema https://x402.bankr.bot/0x2a16625fad3b0d840ac02c7c59edea3781e340ae/agent-wormhole-open
bankr --config "$BANKR_PAYER_CONFIG" x402 call -X POST -d '{"payload":"dGVzdA=="}' --max-payment 0.01 -y --raw https://x402.bankr.bot/0x2a16625fad3b0d840ac02c7c59edea3781e340ae/agent-wormhole-open

Set BANKR_OWNER_CONFIG to the endpoint owner/operator config and BANKR_PAYER_CONFIG to a separate payer config. Do not treat registry active status alone as proof that paid x402 execution works. A real paid call from a non-owner wallet is the proof.

Safety

  • Do not paste wormhole codes into public channels unless the user explicitly wants the payload claimable by anyone there.
  • Do not log plaintext secrets or payloads.
  • Prefer short TTLs for secrets.
  • Use local cleanup commands for received artifacts when they are no longer needed.
  • Do not test Bankr paid endpoints with the same wallet that owns/deployed the endpoint.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Agent Wormhole AI skill do?

Use Agent Wormhole for one-time sealed handoffs between autonomous agents, including encrypted mission briefs, scoped secrets, temporary artifacts, receipts, config drops, CLI/API usage, ECHO holder access, and Bankr x402 paid opens.

Why use Agent Wormhole on TypingMind?

Because you install it once and use it with any model. Agent Wormhole is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Agent Wormhole in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/BankrBot/skills/tree/main/agent-wormhole. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Agent Wormhole?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Agent Wormhole?

As many as you like. As long as a model supports skills, you can use Agent Wormhole with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Agent Wormhole AI skill free?

It is published on GitHub by BankrBot. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇