Skip to content
Back to search

internet-court

MarketplaceWorks with Claude CodeGitHub

Internet Court — the trust layer for agent-to-agent commerce.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/internet-court-internet-court-skill/badge.svg)](/listings/internet-court-internet-court-skill)

HTML

<a href="/listings/internet-court-internet-court-skill"><img src="/api/listings/internet-court-internet-court-skill/badge.svg" alt="findsafeskills safety rating" /></a>

Install

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Internet Court is **one catch-all skill**. Whatever harness you use, only the root `SKILL.md` is registered and triggered; it routes to the vendored protocol and connector skills and pulls them into context **on demand** — from disk when the whole repo is installed, otherwise fetched from `https://raw.githubusercontent.com/internet-court/internet-court-skill/main/<path>`. Installing the whole repository (not just `SKILL.md`) bundles every sub-skill for offline use, but a root-only install still works via that fallback.

Pick your harness:

Claude Code (plugin — recommended)

# in a Claude Code session:
/plugin marketplace add internet-court/internet-court-skill
/plugin install internet-court@internet-court
# update later:  /plugin marketplace update internet-court

Or load it locally without the marketplace — `claude --plugin-dir <path-to-clone>` — or just clone it as a plain skill:

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

npx skills (skills.sh)

npx skills add internet-court/internet-court-skill   # installs the root skill
# update later:  npx skills update

Codex

git clone https://github.com/internet-court/internet-court-skill ~/.agents/skills/internet-court
# or, per-repo:  .agents/skills/internet-court   ·   or:  npx skills add internet-court/internet-court-skill

Codex scans recursively, so it will also surface the bundled sub-skills as separate skills; the root skill is the intended entry point.

opencode

git clone https://github.com/internet-court/internet-court-skill ~/.config/opencode/skills/internet-court

opencode also reads `~/.claude/skills/` and `~/.agents/skills/`, so a single clone into any of those is enough.

OpenClaw

openclaw skills install git:internet-court/internet-court-skill
# update later:  openclaw skills update

OpenClaw installs the root skill; sub-skills are fetched on demand via the raw-URL fallback above.

Hermes

git clone https://github.com/internet-court/internet-court-skill ~/.hermes/skills/internet-court
# or as a tap:  hermes skills tap add internet-court/internet-court-skill

Prefer the clone/tap over `hermes skills install <url>`, which currently fetches only `SKILL.md` and misses bundled reference files.

---

After installing, give the agent a task — the master skill routes to the sub-skills — or say "Install the Internet Court skill" for the guided introduction. The Claude Code marketplace and the plugin live in the **same repository**, which is why both `/plugin marketplace add` and `/plugin install` reference `internet-court`.

Some vendored skills need their provider's credentials to act (e.g. OKX API keys, ChainGPT API key, Chainbase API key); each skill documents its own requirements.

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

.claude-plugin/marketplace.json · Manifest · 16 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. {
  2. "name": "internet-court",
  3. "owner": {
  4. "name": "Internet Court Consortium"
  5. },
  6. "description": "Internet Court \u2014 the trust layer for agent-to-agent commerce.",
  7. "plugins": [
  8. {
  9. "name": "internet-court",
  10. "source": "./",
  11. "description": "Entry point for Internet Court and the agentic economy stack: natural-language mandates, ERC-7710 delegated permissions, x402 payments, escrow, GenLayer dispute resolution, and the vendored protocol + connector skills it routes to.",
  12. "version": "0.2.0",
  13. "license": "MIT"
  14. }
  15. ]
  16. }
README.md · README · 208 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. # Internet Court Skill
  2. **An open skill for agent-to-agent contracts.**
  3. Agents are beginning to transact, negotiate, and pay one another without
  4. humans in the loop. What they still lack is a way to trust each other. The
  5. building blocks already exist, but they are fragmented, and each one is built
  6. for the happy path. When a deal goes wrong, every layer passes the problem
  7. down the line.
  8. Internet Court does two things. It connects that fragmented ecosystem into a
  9. single open skill, and it builds in **adjudication**: when two agents make a
  10. deal, they also agree up front how it will be settled if something goes wrong,
  11. written into the contract itself. Payments let agents transact. Adjudication
  12. makes them accountable — and accountability is what turns transactions into a
  13. real economy.
  14. This repository is that skill: a master router (`SKILL.md`), the Internet
  15. Court connector skills, and vendored copies of the official skills published by
  16. the protocols in the stack. It gives an agent everything it needs to structure
  17. a deal, hold funds safely, and settle disagreements fairly — all in natural
  18. language, at internet speed.
  19. ## The stack
  20. From discovery to disputes, agentic commerce runs through six layers. Each
  21. existing standard solves one of them and assumes everything goes right. Internet
  22. Court is the open skill that connects them and adds the layer nobody else owns —
  23. verification and dispute resolution — so the whole lifecycle of a deal sits
  24. behind one skill instead of a stack the agent has to wire up itself.
  25. | # | Layer | Standards | In this repo |
  26. |---|---|---|---|
  27. | 1 | Discovery, identity & reputation | ERC-8004, ERC-7857 | [`chaingpt/trustless-agents/`](vendored/chaingpt/trustless-agents/) (ERC-8004 registries), [`bnb-chain/bnbchain-mcp/`](vendored/bnb-chain/bnbchain-mcp/) (ERC-8004 registration), [`starknet/starknet-identity/`](vendored/starknet/starknet-identity/), [`certisyn/certisyn-independent-verification/`](vendored/certisyn/certisyn-independent-verification/) (vet a counterparty's own claim before relying on it); ERC-7857 has no public skill yet |
  28. | 2 | Negotiation | A2A | [`terminalskills/a2a-protocol/`](vendored/terminalskills/a2a-protocol/), [`openserv/openserv-multi-agent-workflows/`](vendored/openserv/openserv-multi-agent-workflows/) |
  29. | 3 | Contracts & obligations | ERC-7710, ERC-8183, Arkhai | [`arkhai/`](vendored/arkhai/) (Alkahest escrow, natural-language agreements, git escrow), [`metamask/smart-accounts-kit/`](vendored/metamask/smart-accounts-kit/) (ERC-7710 delegations); connector [`integrations/genlayer-erc7710-connector/`](integrations/genlayer-erc7710-connector/); ERC-8183 has no public skill yet |
  30. | 4 | Payment & escrow | x402, MPP, APP | [`yellow/yellow-settlement-room/`](vendored/yellow/yellow-settlement-room/) (multiparty off-chain settlement, one on-chain split), [`coinbase/agentic-wallet/`](vendored/coinbase/agentic-wallet/), [`chaingpt/x402/`](vendored/chaingpt/x402/) + [`agent-wallet/`](vendored/chaingpt/agent-wallet/), [`okx/okx-agent-payments-protocol/`](vendored/okx/okx-agent-payments-protocol/), [`tempo/mppx/`](vendored/tempo/mppx/), [`nansen/nansen-mpp-payment/`](vendored/nansen/nansen-mpp-payment/), [`privy/`](vendored/privy/); connector [`integrations/x402-erc7710/`](integrations/x402-erc7710/) |
  31. | 5 | Execution | compute, data & value rails | [`0g/0g-compute/`](vendored/0g/0g-compute/), [`antseed/antseed-connect/`](vendored/antseed/antseed-connect/), [`lifi/`](vendored/lifi/), [`chainbase/web3-data/`](vendored/chainbase/web3-data/), [`heurist/`](vendored/heurist/), [`near/`](vendored/near/), [`starknet/`](vendored/starknet/), [`solana/`](vendored/solana/), [`nansen/`](vendored/nansen/), OKX + AltLayer + BNB Chain packs |
  32. | 6 | Verification & disputes | GenLayer, Kleros, UMA | GenLayer dev skills + [`intelligent-oracle/`](vendored/intelligent-oracle/), [`kleros/`](vendored/kleros/) (curate, IPFS), [`certisyn/certisyn-independent-verification/`](vendored/certisyn/certisyn-independent-verification/) (pre-transaction verification, not adjudication); connectors [`integrations/genlayer-intelligent-contracts/`](integrations/genlayer-intelligent-contracts/), [`integrations/genlayer-erc7710-connector/`](integrations/genlayer-erc7710-connector/); UMA has no public skill yet |
  33. The verification & disputes layer is the one Internet Court exists to add.
  34. Agents agree in advance who judges a dispute if one arises — GenLayer, Kleros,
  35. UMA, or whatever they choose. Most deals never get there: when both sides agree,
  36. the contract simply settles. What the skill standardizes is how the contract is
  37. structured around that choice, for the cases that fall off the happy path.
  38. ## The consortium
  39. Internet Court is built by a consortium of companies working across the agentic
  40. commerce stack — not a closed product from a single vendor. The founding
  41. members span every layer, and each member's protocol is embedded directly into
  42. the standard.
  43. **Founding members:** GenLayer, MetaMask, OKX, NEAR, Starknet, x402, 0G Labs,
  44. ZKsync, Nansen, Kleros, Privy, AntSeed, Collective Memory, UMA, Arkhai, AltLayer,
  45. Anoma, AppLayer, BNB Chain, LI.FI, Chainbase, io.net, Heurist, Chutes, ChainGPT,
  46. OpenServ, Humanode, Humanity Protocol.
  47. The standard is open and openly governed — any agent can adopt it now. Not every
  48. founding member ships a public agent skill yet; the vendored table below is the
  49. set available in this repository today, and it grows as members publish.
  50. ## Repository layout
  51. ```
  52. SKILL.md Master skill — start here; routes to everything below
  53. integrations/ Internet Court connector & adapter skills
  54. vendored/ Committed copies of official protocol skills (92 skills, 34 owners)
  55. skills-lock.json Pinned source + hash + refresh command per vendored skill
  56. ```
  57. Two kinds of content:
  58. - **First-party** — only the master skill and the connectors. This repo
  59. never re-implements a protocol's own skill.
  60. - **Vendored** — copies of publicly published skills, fetched from official
  61. sources and pinned in `skills-lock.json`.
  62. ## Vendored skills
  63. | Source | Skills | Repo |
  64. |---|---|---|
  65. | GenLayer | `write-contract`, `genlayer-cli`, `direct-tests`, `integration-tests`, `genvm-lint` | [genlayerlabs/skills](https://github.com/genlayerlabs/skills) · [skills.genlayer.com](https://skills.genlayer.com/) |
  66. | MetaMask | `smart-accounts-kit` (ERC-4337/7710/7715 delegations) | [metamask/skills](https://github.com/metamask/skills) |
  67. | OKX OnchainOS | 9 `okx-*` skills incl. `okx-agent-payments-protocol` (x402/MPP), `okx-agentic-wallet`, `okx-dex-market`, `okx-defi` | [okx/onchainos-skills](https://github.com/okx/onchainos-skills) |
  68. | NEAR | 6 `near-*` skills (`near-intents`, `near-ai-cloud`, `near-kit`, `near-dapp`, `near-api-js`, `near-smart-contracts`) | [near/agent-skills](https://github.com/near/agent-skills) |
  69. | Starknet | `starknet-defi`, `starknet-dex` … `starknet-identity`, `starknet-wallet`, `starknet-js` | [keep-starknet-strange/starknet-agentic](https://github.com/keep-starknet-strange/starknet-agentic) |
  70. | Solana | `solana-dev` — one catch-all Foundation skill (Anchor/Pinocchio programs, SPL payments, RPC lookups, security/testing) | [solana-foundation/solana-dev-skill](https://github.com/solana-foundation/solana-dev-skill) · [solana.com/skills](https://solana.com/skills) |
  71. | Solana agent-commerce (community) | 19 skills across 8 owners from the [solana.com/skills](https://solana.com/skills) community catalog — `sendaifun/*` (Squads, Pyth, Switchboard, Helius, Birdeye, deBridge, MetEngine, GLAM, Agent Kit), `magicblock/*`, `quicknode/*`, `jupiter/*`, `octav/*`, `dflow/*`, `metaplex/*`, `pnp/*` | [sendaifun/skills](https://github.com/sendaifun/skills) · [magicblock-labs](https://github.com/magicblock-labs/magicblock-dev-skill) · [quiknode-labs](https://github.com/quiknode-labs/blockchain-skills) · [jup-ag](https://github.com/jup-ag/agent-skills) · [Octav-Labs](https://github.com/Octav-Labs/octav-api-skill) · [DFlowProtocol](https://github.com/DFlowProtocol/dflow_phantom-connect-skill) · [metaplex-foundation](https://github.com/metaplex-foundation/skill) · [pnp-protocol](https://github.com/pnp-protocol/solana-skill) |
  72. | Coinbase (x402) | `agentic-wallet` (x402 pay/search/monetize) | [coinbase/agentic-wallet-skills](https://github.com/coinbase/agentic-wallet-skills) |
  73. | Yellow | `yellow-settlement-room` (Yellow Network app sessions: N agents pool funds, reallocate off-chain, co-sign one final settlement) | [layer-3/nitrolite](https://github.com/layer-3/nitrolite) (`agent-skills/`) |
  74. | 0G | `0g-compute` (verifiable decentralized inference) | [0gfoundation/0g-compute-skills](https://github.com/0gfoundation/0g-compute-skills) |
  75. | Nansen | 7 `nansen-*` skills (token research, wallet profiler, smart-money, holder analysis, prediction markets, MPP payment, search) | [nansen-ai/nansen-cli](https://github.com/nansen-ai/nansen-cli) |
  76. | Certisyn | `certisyn-independent-verification` (independent, pre-transaction verification of counterparty claims: four outcomes incl. `UNDETERMINED`, mandatory `could_not_determine`; declared coverage is vehicle telemetry and orbital node claims) | [certisyn/genlayer-attestation](https://github.com/certisyn/genlayer-attestation) (`skills/`) |
  77. | Kleros | `kleros-curate`, `kleros-ipfs-upload` (curated registries, evidence pinning) | [kleros/kleros-skills](https://github.com/kleros/kleros-skills) |
  78. | Privy | `privy` (embedded agent wallets) | [docs.privy.io/skill.md](https://docs.privy.io/skill.md) |
  79. | AntSeed | `antseed-connect` (P2P inference, USDC channels) | [antseed.com/skill.md](https://antseed.com/skill.md) |
  80. | Arkhai | `alkahest-user`, `alkahest-developer` (conditional escrow & arbitration), `nla-*` (natural-language agreements), `*-git-escrow` | [arkhai-io/alkahest](https://github.com/arkhai-io/alkahest) · [natural-language-agreements](https://github.com/arkhai-io/natural-language-agreements) · [git-commit-trading](https://github.com/arkhai-io/git-commit-trading) |
  81. | AltLayer | 7 `altllm-portal-*` / `cloud-claw*` skills (autonomous agent hosting) | [alt-research/altllm-skills](https://github.com/alt-research/altllm-skills) |
  82. | BNB Chain | `bnbchain-mcp` (chain ops, ERC-8004 registration, Greenfield) | [bnb-chain/bnbchain-skills](https://github.com/bnb-chain/bnbchain-skills) |
  83. | LI.FI | `lifi`, `lifi-stablecoin-swap` (cross-chain routing) | [lifinance/lifi-agent-skills](https://github.com/lifinance/lifi-agent-skills) |
  84. | Chainbase | `web3-data` (90-chain data, x402 pay-per-call) | [lxcong/web3-data-skill](https://github.com/lxcong/web3-data-skill) (officially documented) |
  85. | Heurist | `heurist-mesh-skill` (hosted agent-mesh MCP + x402 facilitator) | [heurist-network/heurist-mesh-skill](https://github.com/heurist-network/heurist-mesh-skill) |
  86. | ChainGPT | `chaingpt`, `x402`, `trustless-agents` (ERC-8004), `agent-wallet` | [ChainGPT-org/chaingpt-claude-skill](https://github.com/ChainGPT-org/chaingpt-claude-skill) |
  87. | OpenServ | 5 skills incl. `openserv-multi-agent-workflows` (mints ERC-8004), `agent-sdk`, `client`, `launch`, `ideaboard-api` | [openserv-labs/skills](https://github.com/openserv-labs/skills) |
  88. | Humanode | `humanode-agentlink` (biometric agent identity) | [agentlink.id/skill.md](https://agentlink.id/skill.md) |
  89. | Intelligent Oracle | `intelligent-oracle` (web-evidence prediction markets) | [intelligentoracle.com/skill.md](https://www.intelligentoracle.com/skill.md) |
  90. | Tempo | `mppx` (Merchant Payment Protocol) | [tempoxyz/mpp](https://github.com/tempoxyz/mpp) |
  91. | TerminalSkills | `a2a-protocol` (community — no official A2A skill exists) | [TerminalSkills/skills](https://github.com/TerminalSkills/skills) |
  92. Pinned hashes and refresh commands per skill: [`skills-lock.json`](skills-lock.json)
  93. and [`vendored/README.md`](vendored/README.md).
  94. ## Install
  95. Internet Court is **one catch-all skill**. Whatever harness you use, only the
  96. root `SKILL.md` is registered and triggered; it routes to the vendored protocol
  97. and connector skills and pulls them into context **on demand** — from disk when
  98. the whole repo is installed, otherwise fetched from
  99. `https://raw.githubusercontent.com/internet-court/internet-court-skill/main/<path>`.
  100. Installing the whole repository (not just `SKILL.md`) bundles every sub-skill for
  101. offline use, but a root-only install still works via that fallback.
  102. Pick your harness:
  103. ### Claude Code (plugin — recommended)
  104. ```bash
  105. # in a Claude Code session:
  106. /plugin marketplace add internet-court/internet-court-skill
  107. /plugin install internet-court@internet-court
  108. # update later: /plugin marketplace update internet-court
  109. ```
  110. Or load it locally without the marketplace — `claude --plugin-dir <path-to-clone>`
  111. — or just clone it as a plain skill:
  112. ```bash
  113. git clone https://github.com/internet-court/internet-court-skill ~/.claude/skills/internet-court
  114. ```
  115. ### npx skills (skills.sh)
  116. ```bash
  117. npx skills add internet-court/internet-court-skill # installs the root skill
  118. # update later: npx skills update
  119. ```
  120. ### Codex
  121. ```bash
  122. git clone https://github.com/internet-court/internet-court-skill ~/.agents/skills/internet-court
  123. # or, per-repo: .agents/skills/internet-court · or: npx skills add internet-court/internet-court-skill
  124. ```
  125. Codex scans recursively, so it will also surface the bundled sub-skills as
  126. separate skills; the root skill is the intended entry point.
  127. ### opencode
  128. ```bash
  129. git clone https://github.com/internet-court/internet-court-skill ~/.config/opencode/skills/internet-court
  130. ```
  131. opencode also reads `~/.claude/skills/` and `~/.agents/skills/`, so a single
  132. clone into any of those is enough.
  133. ### OpenClaw
  134. ```bash
  135. openclaw skills install git:internet-court/internet-court-skill
  136. # update later: openclaw skills update
  137. ```
  138. OpenClaw installs the root skill; sub-skills are fetched on demand via the
  139. raw-URL fallback above.
  140. ### Hermes
  141. ```bash
  142. git clone https://github.com/internet-court/internet-court-skill ~/.hermes/skills/internet-court
  143. # or as a tap: hermes skills tap add internet-court/internet-court-skill
  144. ```
  145. Prefer the clone/tap over `hermes skills install <url>`, which currently fetches
  146. only `SKILL.md` and misses bundled reference files.
  147. ---
  148. After installing, give the agent a task — the master skill routes to the
  149. sub-skills — or say "Install the Internet Court skill" for the guided
  150. introduction. The Claude Code marketplace and the plugin live in the **same
  151. repository**, which is why both `/plugin marketplace add` and `/plugin install`
  152. reference `internet-court`.
  153. Some vendored skills need their provider's credentials to act (e.g. OKX API
  154. keys, ChainGPT API key, Chainbase API key); each skill documents its own
  155. requirements.
  156. ## License
  157. The first-party work in this repository — the master skill and the connectors —
  158. is released under the [MIT License](LICENSE). Vendored skills under `vendored/`
  159. are copies of upstream projects and remain under their own licenses; see each
  160. skill's source repository (and `skills-lock.json`) for terms.
  161. © 2026 Internet Court Consortium · Open standard, openly governed ·
  162. [internetcourt.org](https://internetcourt.org)

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.