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.
npx agentmods add instructions/mimfort/rag_for_git/claude-mdgit clone --depth 1 https://github.com/mimfort/rag_for_gitWrote 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/instructions/mimfort/rag_for_git/claude-md)<a href="https://agentmods.dev/instructions/mimfort/rag_for_git/claude-md"><img src="https://agentmods.dev/badge/instructions/mimfort/rag_for_git/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.19171 | $0.19171 |
| Opus 5 | $0.09585 | $0.09585 |
| Sonnet 5 | $0.03834 | $0.03834 |
| Haiku 4.5 | $0.01917 | $0.01917 |
Grade A, and why
rag_for_git CLAUDE.md 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 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.
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.
How it starts
The opening of the file, as written. The whole thing — 622 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
О проекте
rag_for_git — агент автоматического ревью pull/merge request'ов: RAG (гибридный поиск) + граф кода + Claude Code-плагин. На вход — PR на GitHub, на выход — inline-комментарии на строки диффа + сводка. Целевой язык анализа — Python; VCS — GitHub (за интерфейсом VCSProvider). Подробный разбор архитектуры и потока данных — в README.md (написан на русском, сверен с кодом).
Язык проекта — русский: комментарии, докстринги, сообщения CLI. Сохраняй этот стиль в новом коде.
Команды
# Инфраструктура: ParadeDB (5433) + Neo4j (7687)
docker compose up -d
# Конфиг: ключи Voyage/GitHub
cp .env.example .env # .env gitignored, ключи только локально
# Тесты
# unit: без Postgres, Neo4j, localhost-сервисов и внешней сети
.venv/bin/pytest -q
# изолированная инфраструктура integration-тестов
docker compose --profile test up -d --wait paradedb-test neo4j-test
# integration; пайплайну также нужен VOYAGE_API_KEY
.venv/bin/pytest -q -m integration
# только безопасное удаление
docker compose --profile test rm -sfv paradedb-test neo4j-test
# Линт
git config core.hooksPath .githooks # один раз на клон: pre-commit гоняет ruff по staged .py
# CLI (после pip install -e .)
reviewer check --board-project jira=PRI # проверить окружение и project-scoped board permissions
reviewer index /path/to/repo --ref main # построить/обновить base-индекс (вектора + граф) из локального клона
reviewer index /path/to/repo --ref master # индекс второй ветки (изолированный, тот же деплой)
reviewer search "token verification" # диагностический гибрид-поиск по base-индексу (первичная ветка)
reviewer search "token verification" --branch master # поиск по индексу конкретной ветки
reviewer status # здоровье/свежесть индекса по веткам (не тратит Voyage)
reviewer status /path/to/repo --branch dev # статус конкретной ветки (дрейф vs git HEAD клона)
reviewer migrate-branches # одноразовая миграция legacy base → base:<primary> после апгрейда
reviewer serve # веб-админка наблюдаемости на хосте (история прогонов, находки)
# MCP-сервер (для Claude Code-плагина)
reviewer-mcp # запустить MCP-сервер (используется плагином)
# Ревью через Claude Code-плагин:
# 1. Открыть репозиторий как проект в Claude Code
# 2. Использовать скилл /rag-reviewer:review-pr (из plugin/)
# Плагин вызывает prepare_review → analyze (Claude subagents) → publish_review
# На хосте (для разработки фронта): pip install -e ".[web]" && (cd web/frontend && npm install && npm run build) && reviewer serve
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 · 622 lines · 19,171 tokens per session scan A 70ee80ceb3d6
rag_for_git CLAUDE.md is an instructions file published in the GitHub repository mimfort/rag_for_git (21 stars, last pushed 4d ago), licensed MIT. It adds 19,171 tokens to every session, about $0.0959 per session on Opus 5. 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 instructions, from other repositories
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…
GPT-RAG release.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…
orbit CLAUDE.md
Instructions for schmitech/orbit, covering claude.md, project overview, commands, setup and running the server.
pdf-brain AGENTS.md
Instructions for joelhooks/pdf-brain, covering pdf-brain agent notes, libsql quirks, ai sdk pattern, key files and docs.
rag-code-mcp copilot-instructions.md
Instructions for doITmagic/rag-code-mcp, covering copilot instructions - ragcode mcp, ⚖️ the golden rule, project overview, architecture & patterns and developer workflows.
gpt-rag-mcp AGENTS.md
Instructions for Azure/gpt-rag-mcp, covering gpt-rag mcp engineering-agent contract, priority, what this repository is, repository boundaries and how to work.