runningoffcode

Agent Wormhole — AI skill for Claude Code

AI community

Stop self-replicating prompt payloads from writing themselves into your AI agent's config files.

How to install Agent Wormhole

This entry records only its repository, not the path inside it, so there is no exact command to give. Open runningoffcode/agent-wormhole and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Agent Wormhole does

Stop self-replicating prompt payloads from writing themselves into your AI agent's config files.

Alternatives in AI

Memory Forge Rs — Stop resetting satisfying AI chats — edit the memory instead 474 ★
Mancode — AI coding agent harness 358 ★
Prismor — Self-hosted runtime control plane for AI agents 334 ★

README

Agent Wormhole

[Integration guide: payment safety, policy, confirmed top-ups and launch attestations](docs/integration.md).

[![ci](https://github.com/runningoffcode/agent-wormhole/actions/workflows/ci.yml/badge.svg)](https://github.com/runningoffcode/agent-wormhole/actions/workflows/ci.yml) [![PyPI](https://img.shields.io/pypi/v/wormhole-guard?label=pypi%20wormhole-guard)](https://pypi.org/project/wormhole-guard/) [![npm](https://img.shields.io/npm/v/wormhole-x402?label=npm%20wormhole-x402)](https://www.npmjs.com/package/wormhole-x402) [![Python](https://img.shields.io/pypi/pyversions/wormhole-guard)](https://pypi.org/project/wormhole-guard/) [![License](https://img.shields.io/badge/license-Apache%202.0-blue)](LICENSE) [![Telemetry](https://img.shields.io/badge/telemetry-none-brightgreen)](docs/limits.md#no-telemetry)

**The security layer for agentic commerce.**

**[agentwormhole.com](https://agentwormhole.com)** · [docs](https://docs.agentwormhole.com) · [dashboard](https://dashboard.agentwormhole.com) · [research](https://agentwormhole.com/research)

AI agents now read instructions they did not write, sign payments a merchant priced, and buy tokens whose metadata an attacker typed. All three are the same problem — **untrusted text reaching a model that acts** — and this is one stack that covers all three:

Surface	What reaches the agent	The guard
Instructions	`CLAUDE.md`, `.cursor/rules`, hooks, fetched pages	`wormhole-guard` (Python, offline, free)
Payments	x402 quotes, EIP-3009 authorizations, Solana transactions	`wormhole-x402` (TypeScript, offline core)
Token launches	names, symbols, descriptions, links	the launch layer (hosted, $0.01/token)

Everything verifiable is free forever — badges, attestations, signatures, verdicts. The metered work is what costs, in USDC over x402, and an agent can pay for itself with no human in the loop.

![Launch badges — every state](docs/assets/badge-states.png)