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 skills add ondrejmirtes/mcparr --skill monitoring-and-cleanupgit clone --depth 1 https://github.com/ondrejmirtes/mcparrWrote 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/skills/ondrejmirtes/mcparr/monitoring-and-cleanup)<a href="https://agentmods.dev/skills/ondrejmirtes/mcparr/monitoring-and-cleanup"><img src="https://agentmods.dev/badge/skills/ondrejmirtes/mcparr/monitoring-and-cleanup/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/ondrejmirtes/mcparr/monitoring-and-cleanup"><img src="https://agentmods.dev/badge/skills/ondrejmirtes/mcparr/monitoring-and-cleanup.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00139 | $0.00565 |
| Opus 5 | $0.00069 | $0.00282 |
| Sonnet 5 | $0.00028 | $0.00113 |
| Haiku 4.5 | $0.00014 | $0.00056 |
Grade A, and why
monitoring-and-cleanup 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 11d 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.
What it actually says
Monitoring & cleanup
Monitoring vs. deleting — clarify intent
These are very different:
- Unmonitor = keep the item and its files, but stop searching/grabbing new content.
- Delete = remove the item from Sonarr/Radarr (optionally also delete files).
If the user says "stop downloading season 1", they almost always mean unmonitor, not delete. Confirm if ambiguous.
Change monitoring
- TV series / seasons:
sonarr_set_monitoringwithseriesId, plusmonitoredfor the whole show and/or aseasonsarray for individual seasons. Example: keep only the latest season by unmonitoring older ones. - Movie:
radarr_set_monitoringwithmovieId+monitored.
Remove an item
- TV:
sonarr_delete_series(deleteFilesdefaults false). - Movie:
radarr_delete_movie(deleteFilesdefaults false).
Always confirm before deleting, and confirm explicitly before deleteFiles: true
— that erases downloaded media from disk and is not reversible from MCPArr. State the
title and whether files will be deleted, then proceed.
Reclaiming disk space
*_healthreports free space per volume.- To find space hogs:
radarr_search_library(movies have sizes via files) andsonarr_search_library(episode/file counts) to identify large or finished items. - Suggest candidates (finished shows the user no longer wants, low-rated movies) and let the user choose what to delete. Don't mass-delete on your own initiative.
Safety checklist before any delete
- Correct item identified by id (not just a fuzzy title match)
- User asked to delete (not merely unmonitor)
-
deleteFilesintent explicitly confirmed
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.
- 11d ago First seen · 54 lines · 139 tokens per session scan A c5262cfdda35
monitoring-and-cleanup is a skill published in the GitHub repository ondrejmirtes/mcparr (6 stars, last pushed 2mo ago), licensed MIT. It adds 139 tokens to every session and 565 once invoked, about $0.0007 per session on Opus 5. 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 skills, from other repositories
overseerr
Search, request, and manage media through Overseerr (movies/TV shows via Radarr/Sonarr). Use when someone asks to find, request, or check the status of a movie or TV show on your Plex server.
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…