What is LLMarr AGENTS.md?

Repository instructions for LLMarr, an MCP server that lets an AI agent automate TV shows and movies: finding metadata, searching torrents, downloading files, organising a media library, and asking Plex to scan it.

Adding or changing LLMarr features, configuration, media and download handling, MCP tools, and pytest tests without breaking offline testing.

They explain the project’s design and testing rules, including how to keep network access replaceable in tests and how configuration must be stored.

How himanshugoel2797/LLMarr configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to himanshugoel2797/LLMarr. 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/himanshugoel2797/LLMarr/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/himanshugoel2797/LLMarr

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/himanshugoel2797/llmarr/agents-md/github.svg)](https://agentmods.dev/instructions/himanshugoel2797/llmarr/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/himanshugoel2797/llmarr/agents-md"><img src="https://agentmods.dev/badge/instructions/himanshugoel2797/llmarr/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/himanshugoel2797/llmarr/agents-md"><img src="https://agentmods.dev/badge/instructions/himanshugoel2797/llmarr/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 3,838 This file is loaded in full into every session.

When invoked 3,838 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	$0.03838	$0.03838
Opus 5.5	$0.01535	$0.01535
Sonnet 5.5	$0.00768	$0.00768
Haiku 4.5	$0.00384	$0.00384

Measured 2mo ago against content hash d7b20142b0f3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

LLMarr 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 2mo 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 · 235 lines

How it starts

The opening of the file, as written. The whole thing — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — guidance for coding agents working on LLMarr

LLMarr is an MCP server that replicates Sonarr/Radarr-style media automation but is driven entirely by an LLM: TMDB metadata → Prowlarr torrent search → qBittorrent grab → hardlink import into an organised library → Plex scan, plus a background RSS auto-grab loop. TV and movies are both supported. Prowlarr is assumed to be available.

Ground rules

Python 3.11+, stdlib style. Match the surrounding code: type hints, from __future__ import annotations, module-level docstrings explaining why.
Everything is configurable through MCP tools. If you add a setting, add the config field and a tool to change it, and make sure it round-trips through the YAML store.
Never break offline testability. All network I/O goes through a small number of seams (see below) that tests fake. Don't call httpx/clients from places that can't be mocked.
Run pytest before finishing. Keep it green and add tests for new behaviour.

Layout

llmarr/
  config.py      pydantic models + ConfigStore (YAML, thread-safe, secret redaction)
  db.py          SQLite: series, episodes, movies, downloads, grab_history, kv (+ migrations)
  pathmap.py     translate() paths between container namespaces (single-host = passthrough)
  metadata/      MetadataProvider ABC + TMDB (TV+movies) + Jikan/Tenrai (anime)
  indexers/      Prowlarr search client + Release model
  download/      DownloadClient ABC + qBittorrent (resolves .torrent host-side)
  notify/        Plex library scan + catalog + show_episodes
  importer.py    hardlink/copy/move into <root>/Show (Year)/Season NN/… + movie layout
  selector.py    quality filter + ranking (lightweight, NOT Sonarr custom formats)
  parsing.py     SxxExx / season-pack / resolution / anime absolute+range parsing
  core.py        App engine — the glue used by BOTH tools and the RSS poller
  rss/poller.py  asyncio background loop (auto-grab + import), reads config each tick
  auth.py        mode-aware bearer/OAuth middleware for the HTTP transport
  oauth.py       self-contained OAuth 2.1 authorization + resource server
  plexauth.py    plex.tv PIN (browser) login flow
  setup.py       build_status() — powers the setup_status onboarding tool
  server.py      FastMCP instance + all ~54 tools + lifespan (starts poller)
  __main__.py    stdio (default) or streamable-http entrypoint

Read the full file on GitHub · 235 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.

2mo ago First seen · 235 lines · 3,838 tokens per session scan A d7b20142b0f3

Subscribe to this mod's changes

LLMarr AGENTS.md is an instructions file published in the GitHub repository himanshugoel2797/LLMarr (0 stars, last pushed 3mo ago), licensed MIT. It adds 3,838 tokens to every session, about $0.0154 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.

LLMarr AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
LLMarr AGENTS.mdhimanshugoel2797/LLMarr	Instructions file	0	3mo ago	MIT	A	3,838	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,685	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

LLMarr: Instructions file for Codex