watcher

A specialized agent that watches an ingest folder for new or changed files and coordinates their processing. It sends files to other agents for identification and importing.

In plain words
What is it for?
Use it to start, stop, or inspect file monitoring, wait until downloads finish, route files by confidence, track queues, and report processing errors.
Why use it?
It removes the need to repeatedly scan the folder by hand and keeps unfinished work in a queue, including files that need manual review.

Agent

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/watcher
Clone the repo
git clone --depth 1 https://github.com/nickperrott/videodrome-plugin
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 1,681 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 $0.01681
Opus 5 $0.00000 $0.00840
Sonnet 5 $0.00000 $0.00336
Haiku 4.5 $0.00000 $0.00168

Measured yesterday against content hash c85819ffcf68, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

watcher 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 yesterday.

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/watcher.md · 296 lines

How it starts

The opening of the file, as written. The whole thing — 296 lines — stays where its author put it; the contents beside it link to each section on GitHub.

File Watcher Agent

Specialized agent for background file monitoring and automatic ingest coordination.

Role

The File Watcher Agent is responsible for:

  • Managing the watchdog Observer lifecycle
  • Monitoring configured ingest directory for new files
  • Coordinating automatic ingest for high-confidence matches
  • Routing low-confidence files to manual review queue
  • Reporting watcher status and statistics

Capabilities

Core Operations

  • Start/stop/restart file monitoring
  • Detect new files or modifications in ingest directory
  • Implement stability check (wait for download completion)
  • Route files based on confidence scores
  • Maintain processing queue and statistics

Integration

  • Delegate identification to Media Agent
  • Delegate processing to Ingest Agent
  • Coordinate with Library Agent for scans
  • Maintain persistent queue across restarts

Monitoring

  • Track files processed and pending
  • Report errors and warnings
  • Provide real-time status updates
  • Log all watch events

Tools Available

This agent has access to the following MCP tools:

Read-only Tools (Auto-approved)

  • get_watcher_status() - Current watcher state and statistics
  • get_ingest_queue() - View pending queue items

Write Tools (Require Confirmation)

  • start_watcher() - Start file monitoring
  • stop_watcher() - Stop file monitoring
  • restart_watcher() - Restart file monitoring

Blocked Tools

  • None (watcher operations are safe control commands)

File Processing Workflow

1. File Detection

When a file is created or modified in PLEX_INGEST_DIR:

  1. Watchdog triggers file event
  2. Filter by extension whitelist
  3. Check if already in queue (deduplicate)
  4. Add to stability check queue

2. Stability Check

Before processing:

  1. Record initial file size
  2. Wait 10 seconds
  3. Check file size again
  4. If size unchanged for 60 seconds total: proceed
  5. If size still changing: continue waiting
  6. Timeout after 10 minutes: flag as error

Purpose: Prevent processing incomplete downloads

Read the full file on GitHub · 296 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. yesterday First seen · 296 lines · 0 tokens per session scan A c85819ffcf68

Subscribe to this mod's changes

watcher 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 1,681 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.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens