What is rtorrent-mcp AGENTS.md?

Repository instructions for rtorrent-mcp, a service that controls rTorrent, a command-line torrent client, through a web-connected interface. They document its ports, project structure, and testing commands.

Use them when developing, running, or testing rtorrent-mcp, including its torrent management, search, frontend, and end-to-end tests.

They give coding agents the project-specific rules needed to run the service and test changes correctly. This avoids guessing which commands, ports, or coverage requirements apply.

How sandraschi/rtorrent-mcp configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to sandraschi/rtorrent-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/sandraschi/rtorrent-mcp/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/sandraschi/rtorrent-mcp

Made for: Codex, OpenCode.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/sandraschi/rtorrent-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/sandraschi/rtorrent-mcp/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/sandraschi/rtorrent-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/sandraschi/rtorrent-mcp/agents-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/sandraschi/rtorrent-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/sandraschi/rtorrent-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,382 This file is loaded in full into every session.

When invoked 1,382 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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 5.1	$0.01382	$0.01382
Opus 5.5	$0.00553	$0.00553
Sonnet 5.5	$0.00276	$0.00276
Haiku 4.5	$0.00138	$0.00138

Measured 20d ago against content hash 670b77829715, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

rtorrent-mcp AGENTS.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 20d 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.

AGENTS.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — rtorrent-mcp (qbt-mcp)

Per-repo overrides for the fleet-wide AGENTS.md. Repo dir: rtorrent-mcp; Python package rtorrent_mcp; PyPI name rtorrent-mcp (historic qBittorrent prototype name qbtmcp is retired).

Ports

Service	Port	Notes
rTorrent XML-RPC (nginx)	`12224`	In Docker: crazymax/rtorrent-rutorrent
ruTorrent WebUI	`12222`	In Docker container
rtorrent-mcp backend (uvicorn)	`10910`	MCP HTTP `/mcp` + REST `/api/*`
rtorrent-mcp frontend (Vite)	`10911`	Proxies `/api` + `/mcp` → 10910

Tests

# Run all tests (coverage requires 80%)
uv run pytest

# Run specific files
uv run pytest tests/test_media_integrator.py -v -o "addopts="

# Playwright e2e (in web_sota/)
cd web_sota
npx playwright test

Architecture

6 portmanteau tools + 1 agentic workflow:

torrent_management (13 actions)  — add, list, pause, resume, delete, status, info,
                                   notify_media, check_completed, process,
                                   start_processing, stop_processing, normalize
search_management  (14 actions)  — anime, manga, japanese_tv, movies, tv_shows,
                                   tv_smart, ebooks_annas, ebooks_gutenberg,
                                   ebooks_pb, comics, annas_detail, imdb, imdb_search, tvdb
nlp_management      (3 actions)  — command, parse, help
legal_management    (4 actions)  — risk, check, advice, status
system_management   (5 actions)  — help, status, health, info, analyze
workflow_management (8 actions)  — franchise, batch_series, status, cancel,
                                   list, estimate, queue, schedule
agentic_rtorrent_workflow        — LLM-orchestrated multi-step (requires Ollama)

Cross-Connect

Plex/Jellyfin: MediaIntegrator fires library scans after direct downloads (anime via nyaa). Configure via PLEX_URL/PLEX_TOKEN/JELLYFIN_URL/JELLYFIN_API_KEY in .env.
*arr apps (Radarr/Sonarr): Do NOT go through rtorrent-mcp. Configure rTorrent as a download client directly in each *arr (Settings > Download Clients > rTorrent, host: localhost, port: 12224, path: /RPC2). See docs/ARR_RTORRENT_SETUP.md.
Obscura MCP (obscura-mcp): Uses the Obscura Rust headless engine to solve Cloudflare/Turnstile/CAPTCHA challenges and JS countdown queues on protected indexers or Anna's Archive slow mirror links.

Read the full file on GitHub · 106 lines

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.

20d ago Changed · +2 lines · +53 tokens per session 670b77829715
2mo ago First seen · 104 lines · 1,329 tokens per session scan A 622c9c747e01

Subscribe to this mod's changes

rtorrent-mcp AGENTS.md is an instructions file published in the GitHub repository sandraschi/rtorrent-mcp (1 stars, last pushed 4d ago), licensed MIT. It adds 1,382 tokens to every session, about $0.0055 per session on Opus 5.5. 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 2026-08-31.

mcp-server torrent-client-desktop torrent-tool webapp windows-app

rtorrent-mcp AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
rtorrent-mcp AGENTS.mdsandraschi/rtorrent-mcp	Instructions file	1	4d ago	MIT	A	1,382	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

rtorrent-mcp: Instructions file for Codex