Trustless Agents

Trustless Agents is an AI Engineering skill for Claude Code, published by internet-court in internet-court-skill.

3K stars68 forkson internet-court/internet-court-skillAdded 2026/08/17+69% in starsRepository updated 2026/08/11

a2aadjudicationagent-paymentsagent-skillsagentic-commerceai-agentsclaude-codeclaude-pluginclaude-skillcodexdispute-resolutionerc-7710erc-8004escrowgenlayerhermes-agentopenclawopencodeweb3x402

Install in seconds

Install Trustless Agents

Copy Trustless Agents into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/internet-court/internet-court-skill/tree/main/vendored/chaingpt/trustless-agents ~/.claude/skills/trustless-agents

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/internet-court/internet-court-skill.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: vendored/chaingpt/trustless-agents/SKILL.md in internet-court/internet-court-skill
Installs to: ~/.claude/skills/trustless-agents
Collection: One of 25 skills cataloged from this repository
Category: AI Engineering — 2451 skills

What Trustless Agents does

Trustless Agents resolves an ERC-8004 agent by ID to its owner and AgentCard, lists canonical identity and reputation registry addresses, and scaffolds a spec-compliant registration-v1 AgentCard with x402 support and trust models. Use it when building or discovering on-chain agent identity, reputation, or discovery flows.

Trustless Agents is cataloged under AI Engineering on DirSkills. Trustless Agents comes from a repository tagged a2a, adjudication, agent-payments, agent-skills and agentic-commerce.

Documentation

README

Excerpt

ERC-8004 Trustless Agents skill

ERC-8004 (draft EIP) gives AI agents a portable on-chain identity + reputation: the Identity Registry is an ERC-721 ("AgentIdentity") deployed as a singleton at the vanity address 0x8004A169… across many chains (verified on Base mainnet). An agent's tokenURI points to an AgentCard describing what it does, its endpoints (A2A/MCP), trust models, and x402 support.

Tools

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Trustless Agents

What else does internet-court publish alongside Trustless Agents?
Trustless Agents is one of 25 skills that DirSkills catalogs from internet-court/internet-court-skill, the repository it ships in. Its siblings there include 0G Compute, Agent Wallet and Alkahest Developer. Each one is a separate skill with its own page in this directory, installs the same way Trustless Agents does, and is maintained by internet-court in that same repository. The rest of the collection is listed on the internet-court/internet-court-skill page.
How does Trustless Agents compare to other AI Engineering skills?
Trustless Agents ranks #681 by stars among the 2451 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Trustless Agents against them. Open each page to compare what they document and how they install.