plex

A guide for interacting with Plex Media Server, software that stores and streams a personal media collection.

In plain words
What is it for?
It is for checking Plex, searching libraries, seeing active streams, browsing media, and viewing recently added or on-deck items.
Why use it?
It gives the coding agent instructions for handling common Plex requests without requiring a separate server connector.

Skill for Claude CodeCodex

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 skills/dinglebear-ai/yarr/plex
Any agent
npx skills add dinglebear-ai/yarr --skill plex
Clone the repo
git clone --depth 1 https://github.com/dinglebear-ai/yarr

Made for: Claude Code, Codex.

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,800 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin unknown 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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.01800
Opus 5 $0.00000 $0.00900
Sonnet 5 $0.00000 $0.00360
Haiku 4.5 $0.00000 $0.00180

Measured 2d ago against content hash 625f3cd0984a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

plex scanned grade A with 1 finding 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 2d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/load-config.sh, scripts/plex-api.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Makes network callslowCapability

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

# Or raw curl
plugins/plex/skills/plex/SKILL.md · 227 lines

The source is not reproduced here

Licensed AGPL-3.0

The repository is licensed AGPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.

Read it on GitHub

Files

What ships with it

8 files beside SKILL.md 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.

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.

  1. 2d ago First seen · 227 lines · 0 tokens per session scan A 625f3cd0984a

Subscribe to this mod's changes

plex is a skill published in the GitHub repository dinglebear-ai/yarr (7 stars, last pushed 7d ago), licensed AGPL-3.0. It costs nothing until one of its globs matches a file; then it loads 1,800 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

arr-connect

Use when pointing a coding agent at Radarr, Sonarr, Prowlarr, or a arr companion for the first time or in a fresh session: "connect to Radarr", "talk to Sonarr's API", find the API key, hit /api/v3, check whether a movie or show is already in the library, confirm a title has a file on disk, work out why an API write…

t3chnaztea/arr-stack-skills · 175 tokens

arr-library-hygiene

Use when the library and the app disagree about what should exist: episodes stuck permanently "missing", a season pack re-grabbed every night, "episode file already imported" looping in the queue, a search that returns queued but finds nothing, seasons that re-monitor themselves after a metadata refresh, deleting a…

t3chnaztea/arr-stack-skills · 142 tokens

arr-quality-profiles

Use when working on what Radarr or Sonarr is allowed to grab and when it stops: quality profiles, custom formats, cutoffs, upgrade behaviour, or Recyclarr and TRaSH guide templates. Triggers include "it keeps re-downloading the same movie", "endless upgrades", "why won't it grab this release", "it grabbed a worse…

t3chnaztea/arr-stack-skills · 176 tokens

arr-context-map

Use when an agent needs to know how THIS media stack is put together before it can safely act: which quality profile id means what, which root folder is for which kind of content, how container paths map to host paths, which download client handles which protocol, and which app is managed by a template sync. Triggers…

t3chnaztea/arr-stack-skills · 143 tokens

arr-downloads

Use when nothing is arriving, or arriving too slowly: searches that find no results, releases grabbed but never downloaded, torrents stuck at zero peers or a few KB/s, Usenet posts that fail to repair, downloads that complete but never import, a VPN-wrapped client that stops working after a restart, or requests from…

t3chnaztea/arr-stack-skills · 156 tokens

arr-playback

Use when playback quality is the real complaint but the arr is the real cause: a 4K file that stutters or shows grey glitches in one player but plays fine in another, "why is this transcoding when direct play should work", constant CPU or GPU load during playback, subtitles that force a re-encode, audio that gets…

t3chnaztea/arr-stack-skills · 147 tokens