What is rag_for_git GEMINI.md?

Project instructions for using rag_for_git with the Gemini command-line tool, including setup for an MCP server and shared or project-specific settings. MCP is a way for an AI tool to connect to extra services.

Use it to configure rag_for_git for Gemini, install its MCP server, and place skills or settings globally or inside one project.

It gives Gemini the project context and setup steps needed to use rag_for_git without guessing where configuration belongs or how to start the server.

rag_for_git GEMINI.md — Instructions file by mimfort

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.

agentmods

npx agentmods add instructions/mimfort/rag_for_git/gemini-md

Clone the repo

git clone --depth 1 https://github.com/mimfort/rag_for_git

Made for: Gemini CLI.

Per session 486 This file is loaded in full into every session.

When invoked 486 The same file — it is already loaded in full.

Security scan B 2 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5	$0.00486	$0.00486
Opus 5	$0.00243	$0.00243
Sonnet 5	$0.00097	$0.00097
Haiku 4.5	$0.00049	$0.00049

Measured 3d ago against content hash 3fd1604e4a26, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

rag_for_git GEMINI.md scanned grade B with 2 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 3d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

This registers the MCP server in `~/.gemini/settings.json` automatically (cross-platform,

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -sL https://github.com/mimfort/rag_for_git/archive/refs/heads/main.tar.gz -o /tmp/rag-reviewer.tgz

GEMINI.md · 63 lines

What it actually says

rag_for_git — Gemini CLI context

See CLAUDE.md for full project documentation (architecture, commands, invariants).

MCP server setup

Quickest way

uvx --from rag-reviewer reviewer install gemini

This registers the MCP server in ~/.gemini/settings.json automatically (cross-platform, uses the absolute path to uvx — no bash -lc wrapper needed).

Global config (manual alternative)

Add to ~/.gemini/settings.json under "mcpServers":

{
  "mcpServers": {
    "reviewer": {
      "command": "/bin/bash",
      "args": ["-lc", "uvx --from rag-reviewer@latest reviewer-mcp"]
    }
  }
}

The bash -lc wrapper loads your shell profile so uvx (in ~/.local/bin) is found by GUI tools that don't inherit the full shell PATH (macOS/Linux only; on Windows use reviewer install gemini or set command to uvx directly).

Project-level config

.gemini/settings.json in this repo already contains the MCP entry — Gemini CLI picks it up automatically when you open this project.

Skills

Gemini CLI discovers skills from .gemini/skills/ (project) or ~/.gemini/skills/ (global). Install globally — no repo clone needed:

curl -sL https://github.com/mimfort/rag_for_git/archive/refs/heads/main.tar.gz -o /tmp/rag-reviewer.tgz
mkdir -p ~/.gemini/skills
tar xz -C ~/.gemini/skills --strip-components=3 -f /tmp/rag-reviewer.tgz 'rag_for_git-main/plugin/skills'
rm /tmp/rag-reviewer.tgz

Skills installed: review-pr, solve-task, sync-codebase, sync-tasks, performance-review, maintainability-review.

Then use them: use skill rag-reviewer:review-pr

Verify

After restarting Gemini CLI, run:

"List available MCP tools"

You should see mcp_reviewer_prepare_review, mcp_reviewer_publish_review, etc.

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.

3d ago First seen · 63 lines · 486 tokens per session scan B 3fd1604e4a26

Subscribe to this mod's changes

rag_for_git GEMINI.md is an instructions file published in the GitHub repository mimfort/rag_for_git (21 stars, last pushed 3d ago), licensed MIT. It adds 486 tokens to every session, about $0.0024 per session on Opus 5. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Data and AI RAG and vectors ai claude-code code-graph developer-tools mcp

GPT-RAG config-python.instructions.md

Instructions for Azure/GPT-RAG, a project described as: Sharing the learning along the way we been gathering to enable Azure OpenAI at enterprise scale in a secure manner. GPT-RAG core is a Retrieval-Augmented Generation pattern running in Azure, using Azure Cognitive Search for retrieval and Azure OpenAI large…

Azure/GPT-RAG · 180 tokens

rag_for_git GEMINI.md