plan

A planning command for examining video files or folders and proposing how they should be added to Plex, a media server for organizing and streaming movies and shows.

In plain words
What is it for?
Use it to review a media folder, identify titles from filenames, and produce an ingest plan as a table or JSON.
Why use it?
It shows likely matches, destination paths, duplicates, and uncertain results before anything is changed.

Command

Part of the videodrome plugin — 1 skill, 9 commands, 4 agents, 1 hook shipped together

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 commands/nickperrott/videodrome-plugin/plan
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.

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 1,133 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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.01133
Opus 5 $0.00000 $0.00566
Sonnet 5 $0.00000 $0.00227
Haiku 4.5 $0.00000 $0.00113

Measured 2d ago against content hash d0676f393b83, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

plan 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 2d 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/commands/plan.md · 153 lines

How it starts

The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/videodrome:plan - Generate Ingest Plan

Creates a detailed ingest plan without executing any operations.

Usage

/videodrome:plan <source_path> [--threshold=0.85] [--format=table|json]

Arguments

  • source_path (required): File or directory to analyze
  • --threshold=N (optional): Minimum confidence score (0.0-1.0, default: 0.85)
  • --format=FORMAT (optional): Output format (table or json, default: table)

Examples

/videodrome:plan /data/downloads/movies
/videodrome:plan /data/downloads/season1 --threshold=0.90
/videodrome:plan /tmp/new_media --format=json

What it does

  1. Discovery Phase

    • Recursively scan source directory
    • Filter by supported extensions (.mkv, .mp4, etc.)
    • Calculate total file count and size
  2. Identification Phase

    • Parse each filename with guessit
    • Query TMDb for matches
    • Calculate confidence scores
  3. Path Planning Phase

    • Generate Plex-compliant destination paths
    • Check for conflicts or duplicates
    • Validate paths are within PLEX_MEDIA_ROOT
  4. Classification Phase

    • Group by confidence tier:
      • High (>=threshold): Ready for auto-ingest
      • Medium (0.70-threshold): Manual review recommended
      • Low (<0.70): Requires manual identification
  5. Report Generation

    • Summary statistics
    • Detailed per-file breakdown
    • Warnings and recommendations

Safety Classification

Read-only Operation - Auto-approved, no confirmation needed.

Planning only analyzes files and generates reports. No files or metadata are modified.

MCP Tools Used

  • batch_identify(directory: str) - Identify all files
  • preview_rename(source: str) - Generate destination paths
  • check_duplicates(tmdb_id: int) - Detect existing content

Output

Table Format

Ingest Plan for: /data/downloads/movies/

Discovery: 5 files found (32.4 GB total)
Supported: 5 video files
Unsupported: 0 files skipped

Identification Results:
High Confidence (>=0.85): 3 files
Medium Confidence (0.70-0.85): 1 file
Low Confidence (<0.70): 1 file

HIGH CONFIDENCE - Ready for Auto-ingest
[1] The.Matrix.1999.mkv
    Confidence: 0.95
    TMDb: The Matrix (1999) [ID: 603]
    Destination: /Movies/The Matrix (1999)/The Matrix (1999) - 1080p BluRay.mkv
    Size: 8.2 GB
    Status: READY ✓

[2] Inception.2010.mkv
    Confidence: 0.92
    TMDb: Inception (2010) [ID: 27205]
    Destination: /Movies/Inception (2010)/Inception (2010) - 1080p BluRay.mkv
    Size: 12.1 GB
    Status: READY ✓

MEDIUM CONFIDENCE - Review Recommended
[3] The.Thing.2011.mkv
    Confidence: 0.78
    TMDb: The Thing (2011) [ID: 64686]
    Destination: /Movies/The Thing (2011)/The Thing (2011) - 1080p BluRay.mkv
    Size: 7.8 GB
    Warning: Multiple matches found (1982 vs 2011 version)

LOW CONFIDENCE - Manual Review Required
[4] random.movie.avi
    Confidence: 0.45
    Parsed: random movie (no year)
    TMDb: No confident match
    Status: REQUIRES_MANUAL_REVIEW

Summary:
- Ready for ingest: 2 files (20.3 GB)
- Needs review: 2 files (8.2 GB)
- Total: 4 files (28.5 GB)

Recommendation: Run /videodrome:ingest with --auto flag for high-confidence files

Read the full file on GitHub · 153 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.

  1. 2d ago First seen · 153 lines · 0 tokens per session scan A d0676f393b83

Subscribe to this mod's changes

plan is a command 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 1,133 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.