TREEBEARD™BETA
← Back to Skills

treebeard-trust-check

A Treebeard skill for Claude, Cursor, OpenClaw, and Codex. Your AI assistant checks Treebeard’s independent trust rating for any on-chain AI agent before recommending it or transacting with it.

When it activates

  • Before your assistant recommends an agent for any task
  • When you ask “is X agent safe / trustworthy / legit / good”
  • When evaluating an integration target (an agent’s API, MCP server, or x402 endpoint)
  • When comparing two or more agents
  • When an ERC-8004 registered agent is mentioned by name, slug, or wallet address

Install — Claude Code

From your terminal:

mkdir -p ~/.claude/skills/treebeard-trust-check && curl -fsSL https://treebeardai.com/skills/treebeard-trust-check/SKILL.md -o ~/.claude/skills/treebeard-trust-check/SKILL.md

The skill loads automatically on next Claude Code session. To install per-project instead, replace ~/.claude with ./.claude.

Install — other tools

The SKILL.md is plain Markdown at a stable URL. Each tool has its own skill-loading convention; the pattern is:

  • Cursor — save to .cursor/rules/treebeard-trust-check.md in your project
  • OpenClaw — save to ~/.openclaw/skills/treebeard-trust-check/SKILL.md
  • Codex — paste the SKILL.md body into your custom-instructions field

Canonical source

The SKILL.md is the source of truth. Stable URL, public, no token, no auth:

https://treebeardai.com/skills/treebeard-trust-check/SKILL.md

Versioned by repo commit. Updates publish on the next Vercel deploy of treebeardai.com.

About Treebeard

Treebeard is independent trust intelligence for AI agents. No token, no sponsored listings, no payment from rated entities. See our independence page for full disclosure and the methodology whitepaper for the structural argument.