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.
git clone --depth 1 https://github.com/cq27-dev/rag-ratWrote 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.
[](https://agentmods.dev/plugins/cq27-dev/rag-rat/plugin)<a href="https://agentmods.dev/plugins/cq27-dev/rag-rat/plugin"><img src="https://agentmods.dev/badge/plugins/cq27-dev/rag-rat/plugin/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/plugins/cq27-dev/rag-rat/plugin"><img src="https://agentmods.dev/badge/plugins/cq27-dev/rag-rat/plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
rag-rat 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 6d ago.
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.
What it actually says
{
"name": "rag-rat",
"displayName": "rag-rat",
"description": "Local repo-intelligence index + MCP server: semantic search, symbol/graph navigation, impact-surface preflight, git + GitHub papertrail, and a source-anchored memory graph.",
"version": "0.24.1",
"author": { "name": "Kristaps Karlsons" },
"homepage": "https://github.com/cq27-dev/rag-rat",
"repository": "https://github.com/cq27-dev/rag-rat",
"license": "MIT",
"keywords": ["mcp", "code-intelligence", "semantic-search", "code-graph", "repo-memory"],
"mcpServers": {
"rag-rat": {
"command": "npx",
"args": ["-y", "@rag-rat/[email protected]", "mcp"]
}
}
}
What it installs
The manifest is a name and a version. 2 hooks, 1 MCP server travel with it, and installing the plugin installs all of them. Each is measured on its own page, and each can be installed alone.
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.
- 6d ago Changed 5850c8e9dcb2
- 1mo ago Changed 286f8c6a9a9f
- 1mo ago Changed 38c74a2b63a3
- 1mo ago First seen · 18 lines scan A ee9cad660b68
rag-rat is a plugin published in the GitHub repository cq27-dev/rag-rat (24 stars, last pushed 7d ago), licensed MIT. 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 2026-08-30.
Other plugins, from other repositories
iai-memory
Persistent local memory for your assistant: every turn captured verbatim, relevant memory injected at session start and before each turn, and fourteen memory tools over MCP. Requires the iai-pme package (pip install iai-pme).
anytype-toolbox-skills
Agent Skills for Anytype setup, including a dedicated headless account for one LLM-sharing space, plus anyr and any-mcp workflows.
memem
Persistent, self-evolving memory for Claude Code. Local-first, no cloud, browsable Obsidian vault.
captain-memo
Cross-AI local memory layer for Claude Code, Codex, Gemini CLI, Antigravity, goose, Cursor, opencode, Kimi CLI and more: hybrid search, six summarizer providers, hosted or local embedder. Replaces claude-mem.
alice-memory
Local-first memory for Claude Code: an MCP server and a SessionStart brief on one SQLite file.
alicememory marketplace
Alice Memory plugins for Claude Code.