rai

rai is a plugin for Claude Code from RelationalAI/rai-agent-skills. Its manifest loads nothing; the 12 skills it bundles cost 1,259 tokens per session together, scanned A, original, Apache-2.0.

A plugin for RelationalAI, a system that represents data as connected concepts and relationships and can reason over them.

In plain words
What is it for?
Working with RelationalAI models and asking the system to perform advanced reasoning over connected data.
Why use it?
It gives a coding agent access to RelationalAI’s semantic models and reasoning tools, but the description does not specify the exact operations available.

Plugin for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Claude Code
/plugin marketplace add RelationalAI/rai-agent-skills
agentmods
npx agentmods add plugins/relationalai/rai-agent-skills/rai
Clone the repo
git clone --depth 1 https://github.com/RelationalAI/rai-agent-skills

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for rai

README.md
[![agentmods](https://agentmods.dev/badge/plugins/relationalai/rai-agent-skills/rai.svg)](https://agentmods.dev/plugins/relationalai/rai-agent-skills/rai)
Your own site
<a href="https://agentmods.dev/plugins/relationalai/rai-agent-skills/rai"><img src="https://agentmods.dev/badge/plugins/relationalai/rai-agent-skills/rai.svg" alt="Measured on agentmods" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured The manifest loads nothing itself; its 12 skills cost 1,259 tokens a session between them.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

rai scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/rai/.claude-plugin/plugin.json · 12 lines

What it actually says

{
  "name": "rai",
  "version": "3.1.0",
  "description": "RelationalAI semantic models and advanced reasoners",
  "author": {
    "name": "RelationalAI",
    "url": "https://relational.ai"
  },
  "homepage": "https://github.com/RelationalAI/rai-agent-skills",
  "license": "Apache-2.0"
}
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday Changed a04006c27923
  2. 5d ago First seen · 12 lines scan A 7750558db02c

Subscribe to this mod's changes

rai is a plugin published in the GitHub repository RelationalAI/rai-agent-skills (4 stars, last pushed 4d ago), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.