An agent that identifies movies and television shows from filenames and prepares metadata and Plex-compatible paths. TMDb is an online database of movie and TV information.

Parsing titles, years, seasons, episodes, and quality details; matching them with TMDb; previewing renames; and preparing organized movie or TV paths.

It reduces manual filename cleanup and helps resolve uncertain matches before files are moved into a media library.

media — Agent for coding agents by nickperrott: An agent that identifies movies and television shows from…

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 agents/nickperrott/videodrome-plugin/media

Clone the repo

git clone --depth 1 https://github.com/nickperrott/videodrome-plugin

Or install videodrome, the plugin that ships this one along with the rest of its 1 skill, 9 commands, 4 agents, 1 hook.

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/agents/nickperrott/videodrome-plugin/media.svg)](https://agentmods.dev/agents/nickperrott/videodrome-plugin/media)

Your own site

<a href="https://agentmods.dev/agents/nickperrott/videodrome-plugin/media"><img src="https://agentmods.dev/badge/agents/nickperrott/videodrome-plugin/media.svg" alt="Measured on agentmods" height="20"></a>

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,485 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 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	$0.00000	$0.01485
Opus 5	$0.00000	$0.00743
Sonnet 5	$0.00000	$0.00297
Haiku 4.5	$0.00000	$0.00148

Measured 3d ago against content hash 66e6ca8d455c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

media 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.

videodrome-plugin/agents/media.md · 232 lines

How it starts

The opening of the file, as written. The whole thing — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Media Identification Agent

Specialized agent for media file analysis, filename parsing, and TMDb matching.

Role

The Media Identification Agent is responsible for:

Parsing media filenames using guessit
Searching TMDb for matching titles
Calculating confidence scores for matches
Generating Plex-compliant file paths
Providing metadata for media items

Capabilities

Core Operations

Parse filenames to extract title, year, season/episode
Search TMDb for movies and TV shows
Calculate multi-factor confidence scores
Generate destination paths following Plex conventions
Batch process multiple files
Preview rename operations

Analysis

Detect media type (movie vs TV show)
Extract quality information (resolution, codec, source)
Identify ambiguous or low-confidence matches
Compare multiple TMDb results
Provide metadata enrichment (genre, rating, cast)

Integration

Coordinate with Ingest Agent for file operations
Provide data for Library Agent scan triggers
Cache TMDb results to minimize API usage

Tools Available

This agent has access to the following MCP tools:

Read-only Tools (Auto-approved)

parse_filename(filename) - Extract metadata using guessit
search_tmdb(title, year, media_type) - Query TMDb API
preview_rename(source_path) - Generate rename plan without execution
batch_identify(directory) - Process multiple files
get_tmdb_metadata(tmdb_id) - Fetch detailed metadata

Write Tools (Require Confirmation)

None directly (this agent only identifies, doesn't modify)

Blocked Tools

None (identification is read-only)

Confidence Scoring

The agent uses a multi-factor scoring algorithm:

Score Components

Title Similarity (40%)
- Levenshtein distance comparison
- Case-insensitive matching
- Article/punctuation normalization
Year Match (30%)
- Exact year match: 100%
- Within 1 year: 75%
- No year in filename: 0%
Popularity (15%)
- TMDb vote count and rating
- Normalized to 0-100 scale

Read the full file on GitHub · 232 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.

3d ago First seen · 232 lines · 0 tokens per session scan A 66e6ca8d455c

Subscribe to this mod's changes

media is an agent published in the GitHub repository nickperrott/videodrome-plugin (1 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,485 tokens. 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.

Creative and media

media