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/phense/agentic-ragWrote 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/phense/agentic-rag/gemini)<a href="https://agentmods.dev/plugins/phense/agentic-rag/gemini"><img src="https://agentmods.dev/badge/plugins/phense/agentic-rag/gemini/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/phense/agentic-rag/gemini"><img src="https://agentmods.dev/badge/plugins/phense/agentic-rag/gemini.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
agentic-rag 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.
What it actually says
{
"description": "Source-backed knowledge, durable compaction handoffs and bounded queued tools.",
"mcpServers": {
"agentic-rag": {
"args": [
"-m",
"agentic_rag.plugins.mcp"
],
"command": "python3"
}
},
"name": "agentic-rag",
"version": "0.6.12"
}
What ships with it
1 file beside gemini-extension.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday First seen · 15 lines scan A e396d334ff51
agentic-rag is a plugin published in the GitHub repository phense/agentic-rag (0 stars, last pushed yesterday), 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 2026-10-30.
Other plugins, from other repositories
xerj
XERJ: the search engine for AI agents. A new way for AI to search for data: one local Rust binary that indexes your code, docs, specs and logs, plus Corpus Hub packs, and returns cited answers.
agent-brain
Document search with hybrid BM25/semantic retrieval, GraphRAG knowledge graphs, and pluggable providers for Claude Code. Index documentation and code, then search using keyword matching, semantic similarity, graph relationships, or comprehensive multi-mode fusion.
open-webui
Open WebUI operator suite — REST API administration (v0.10.x: user/group lifecycle, model catalog GitOps via models/sync, config-as-code, SCIM, event webhooks, the 0.10.0 accesscontrol→accessgrants break, auth traps), RAG pipeline wiring (HuggingFace embedding + reranker via LiteLLM in front of HuggingFace Text Embed.
context-canopy
Portable personal AI context: search and capture knowledge, then read allowlisted user authority across agents.
keymem
Associative long-term memory — recall by key-graph association, plus passive memory surfacing on every prompt.
core-memory-kit
Per-project in-repo memory system for Claude Code. Frozen-snapshot session loads, auto-extract Stop hook, memory-write + memory-search + troubleshooting skills, keyword search, optional auto-curation crons.