Three Agent Skills for using our services from any agent, served from this domain: as a git repository (smart HTTP v2 with a dumb-HTTP fallback), a Claude Code plugin marketplace, zip archives and plain files. Version 1.0.0, commit fbce5b3b136e, built 2026-09-30. Machine-readable: index.json (sha256 for every file) · llms.txt · .well-known · mcp.json.
| Skill | What it teaches | Get it |
|---|---|---|
| agent-readiness-grade for grade.agentexchange.work | Grade any public website A-F (0-12) on how well AI crawlers and agents can read, cite and transact with it, using grade.agentexchange.work. Checks robots.txt access for AI bots, machine-readable surfaces (llms.txt, sitemap.xml, openapi.json, .well-known/x402, agent-card.json, mcp-registry-auth), readability without JavaScript, structured data (JSON-LD, Open Graph), published legal notices and MCP census presence. Use when asked whether a site is agent-ready or AI-readable, to audit llms.txt or robots.txt for AI crawlers, to explain a grade, or to compare sites. | SKILL.md · agent-readiness-grade.git · zip |
| agentexchange-web-tools for tools.agentexchange.work | Read JavaScript-rendered web pages, take screenshots and extract structured data through a real browser at tools.agentexchange.work, paying per call with USDC on Base (x402). No API key, no account. Use when a page needs JavaScript to render, when a screenshot is needed, or when structured data should be pulled from a page without writing a parser. | SKILL.md · agentexchange-web-tools.git · zip |
| compliance-desk for takeitdown.agentexchange.work | Build, send and track legally-deadlined requests through takeitdown.agentexchange.work (Compliance Desk) - TAKE IT DOWN Act removal of intimate images posted without consent (48-hour deadline), DMCA takedown notices, CCPA/GDPR privacy requests (access, deletion, correction, opt-out of sale) and TCPA/CAN-SPAM do-not-call or unsubscribe requests. Also checks whether a website publishes the notices and request mechanisms it is legally required to have, and sets up a hosted, logged request desk for a site the user operates. Use when a user wants content removed, a takedown or privacy request written, unwanted calls, texts or emails stopped, a site's compliance notices checked, or a takedown, DSA, privacy, accessibility or opt-out intake for their own site. | SKILL.md · compliance-desk.git · zip |
git clone https://skills.agentexchange.work/agentexchange-skills.git # Claude Code (marketplace "agentexchange", one plugin per skill) claude plugin marketplace add https://skills.agentexchange.work/agentexchange-skills.git claude plugin install agent-readiness-grade@agentexchange # Codex, Cursor and OpenClaw all read ~/.agents/skills/<name>/SKILL.md cp -r agentexchange-skills/skills/. ~/.agents/skills/ # OpenClaw straight from git (one repository per skill) openclaw skills install git:https://skills.agentexchange.work/agent-readiness-grade.git
| Client | Command | Status |
|---|---|---|
| git (any client) | git clone https://skills.agentexchange.work/agentexchange-skills.git | verified-by-test |
| git (any client) | git clone --depth 1 --branch v1.0.0 https://skills.agentexchange.work/agentexchange-skills.git | verified-by-test |
| claude-code | claude plugin marketplace add https://skills.agentexchange.work/agentexchange-skills.git && claude plugin install agent-readiness-grade@agentexchange | documented-only |
| claude-code | claude plugin marketplace add https://skills.agentexchange.work/marketplace.json && claude plugin install agent-readiness-grade@agentexchange | documented-only |
| claude-code | git clone https://skills.agentexchange.work/agentexchange-skills.git && claude --plugin-dir ./agentexchange-skills/skills/agent-readiness-grade | documented-only |
| claude-code | git clone https://skills.agentexchange.work/agentexchange-skills.git && cp -r agentexchange-skills/skills/. ~/.claude/skills/ | documented-only |
| openclaw | openclaw skills install git:https://skills.agentexchange.work/agent-readiness-grade.git | documented-only |
| openclaw | git clone https://skills.agentexchange.work/agentexchange-skills.git && openclaw skills install ./agentexchange-skills/skills/agent-readiness-grade | documented-only |
| codex | git clone https://skills.agentexchange.work/agentexchange-skills.git && cp -r agentexchange-skills/skills/. ~/.agents/skills/ | documented-only |
| cursor | git clone https://skills.agentexchange.work/agentexchange-skills.git && cp -r agentexchange-skills/skills/. ~/.cursor/skills/ | documented-only |
| any agent (plain HTTP) | curl -fsSL https://skills.agentexchange.work/skills/agent-readiness-grade/SKILL.md | verified-by-test |
| mcp clients | claude mcp add --transport http agent-economy-index https://index.agentexchange.work/mcp | documented-only |
| mcp clients | codex mcp add agent-economy-index --url https://index.agentexchange.work/mcp | documented-only |
| mcp clients | https://skills.agentexchange.work/mcp.json -> paste into .cursor/mcp.json or .mcp.json | documented-only |
verified-by-test: executed against this host from an external git client or curl. documented-only: the client's published documentation says it works and the underlying fetch is the verified one, but we did not run that client's install command ourselves. Details and doc URLs are in index.json.
mcp.json lists our public Streamable-HTTP MCP servers: agent-economy-index (https://index.agentexchange.work/mcp), measured-data (https://agentexchange.work/data/mcp), agent-exchange-store (https://store.agentexchange.work/mcp), tooldrift (https://tooldrift.agentexchange.work/mcp). Paste it into .mcp.json (Claude Code) or .cursor/mcp.json (Cursor); for Codex, codex mcp add <name> --url <url>.
MIT licensed. Part of Agent Exchange.