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.
npx agentmods add commands/nickperrott/videodrome-plugin/reviewgit clone --depth 1 https://github.com/nickperrott/videodrome-pluginWrote 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.
[](https://agentmods.dev/commands/nickperrott/videodrome-plugin/review)<a href="https://agentmods.dev/commands/nickperrott/videodrome-plugin/review"><img src="https://agentmods.dev/badge/commands/nickperrott/videodrome-plugin/review.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00000 | $0.01271 |
| Opus 5 | $0.00000 | $0.00635 |
| Sonnet 5 | $0.00000 | $0.00254 |
| Haiku 4.5 | $0.00000 | $0.00127 |
Grade A, and why
review 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/videodrome:review - Review Pending Queue Items
Review and process files in the manual review queue (low-confidence matches).
Usage
/videodrome:review [--all] [--file=<path>] [--approve] [--reject]
Arguments
--all(optional): Show all pending queue items--file=PATH(optional): Review specific file--approve(optional): Approve and ingest the file--reject(optional): Reject and remove from queue
Examples
/videodrome:review
/videodrome:review --all
/videodrome:review --file=/data/ingest/movie.mkv
/videodrome:review --file=/data/ingest/movie.mkv --approve
/videodrome:review --file=/data/ingest/movie.mkv --reject
What it does
List Mode (default)
- Query ingest queue for pending items
- Display items requiring manual review
- Show identification results and confidence scores
- Present suggested matches from TMDb
- Provide commands for approval/rejection
Single File Review
- Load file from queue
- Display parsed metadata from guessit
- Show top TMDb matches with confidence scores
- Present destination path preview
- Offer interactive approval/rejection
Approve Action
- Validate user confirmation
- Execute ingest pipeline for approved item
- Remove from queue
- Log to history database
Reject Action
- Remove item from queue
- Optionally move to rejected directory
- Log rejection reason
Safety Classification
Mixed Operation
- List/review: Read-only (auto-approved)
- Approve: Write operation (requires confirmation)
- Reject: Write operation (requires confirmation)
MCP Tools Used
get_ingest_queue()- Retrieve pending items (read-only)get_queue_item(file_path: str)- Get specific item details (read-only)approve_queue_item(file_path: str)- Process approved item (write)reject_queue_item(file_path: str, reason: str)- Remove rejected item (write)
Output
List All Items
Manual Review Queue: 3 items
[1] /data/ingest/The.Thing.mkv
Parsed: The Thing (no year)
Confidence: 0.68
Possible Matches:
A) The Thing (1982) [ID: 1091] - Confidence: 0.68
Genre: Horror, Science Fiction
Rating: 8.1/10
B) The Thing (2011) [ID: 64686] - Confidence: 0.66
Genre: Horror, Science Fiction
Rating: 6.2/10
Command: /videodrome:review --file=/data/ingest/The.Thing.mkv
[2] /data/ingest/random.movie.avi
Parsed: random movie (no year)
Confidence: 0.45
No confident TMDb matches found
Recommendation: Rename file or provide more metadata
[3] /data/ingest/foreign.film.mkv
Parsed: foreign film (no year)
Confidence: 0.52
Multiple ambiguous matches - manual selection required
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.
- 5d ago First seen · 174 lines · 0 tokens per session scan A 4af04a8d750a
review 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 1,271 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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.