internet-court/internet-court-skill

The trust layer for agent-to-agent commerce — natural-language mandates, ERC-7710 delegated permissions, x402 payments, escrow, and dispute resolution as...

View on GitHub ↗Jump to charts ↓

Summary Information

Updated 32 minutes ago
Added to GitGenius on September 12th, 2026
Created on June 16th, 2026
Open Issues & Pull Requests: 26 (+1)
GitHub issues: Enabled
Number of forks: 104
Total Stargazers: 5,641 (+3)
Total Subscribers: 9 (+0)

Repository Insights (GitGenius)

Most active contributors

Sign in to see contributor activity.

Related repositories by overlapping contributors

No overlapping-contributor repos identified yet.

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Issue API getrepoissuespagesummary failed: 429 Rate limit exceeded. Please try again later.

Detailed Description

Internet Court Skill is an open agent skill that provides a trust layer for agent-to-agent commerce by integrating natural-language mandates, delegated permissions, payments, escrow, and dispute resolution.

The problem it addresses is that autonomous agents increasingly transact and negotiate with each other, but lack mechanisms to trust one another or resolve disputes when agreements fail. Existing blockchain and payment standards handle the happy path but fragment responsibility when things go wrong. Internet Court connects these fragmented layers—discovery, negotiation, permissions, payments, escrow, and settlement—into a single unified skill. It adds adjudication as a core layer, allowing agents to agree upfront how disagreements will be resolved, with dispute resolution written into the contract itself. This transforms agent transactions from isolated exchanges into an accountable economy where agents can be held responsible for their commitments.

Developers should adopt this tool if they are building systems where autonomous agents need to transact with each other reliably and require built-in dispute resolution. It suits projects involving agent-to-agent commerce, multi-agent negotiation, or decentralized autonomous systems where trust and accountability matter. The skill works as a Claude Code plugin and integrates with the broader agentic commerce stack, including ERC-7710 delegated permissions and x402 payment standards. It is designed to eliminate the need for agents to wire together multiple disparate protocols themselves.

The project maintains a master router and connector skills alongside vendored copies of official protocol implementations, providing agents with a complete toolkit for structuring deals, holding funds safely, and settling disagreements. Development activity shows consistent engagement with the agentic commerce ecosystem, as evidenced by active topic tracking across agent payments, dispute resolution, and multiple blockchain standards. The codebase is written in TypeScript and positioned as an open standard for agent-to-agent contracts rather than a proprietary solution.