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 queue-managementgit 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/queue-management)<a href="https://agentmods.dev/skills/ondrejmirtes/mcparr/queue-management"><img src="https://agentmods.dev/badge/skills/ondrejmirtes/mcparr/queue-management.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 | $0.00137 | $0.00568 |
| Opus 5 | $0.00068 | $0.00284 |
| Sonnet 5 | $0.00027 | $0.00114 |
| Haiku 4.5 | $0.00014 | $0.00057 |
Grade A, and why
queue-management 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 8d 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
Queue management
1. Look at the queue
sonarr_queue / radarr_queue. For each item note status,
trackedDownloadState, trackedStatus, error, and timeleft.
Common states:
- downloading / queued, time remaining shrinking → healthy, just wait.
- stalled (no peers) → torrent with no seeders; unlikely to finish.
- warning / error with a message → import failed, disk full, etc. Read
error. - completed but stuck on import → usually a path/permission issue; report it.
2. Decide the action
| Situation | Action |
|---|---|
| Healthy, progressing | Do nothing; report ETA. |
| Stalled / no seeders | Remove with blocklist, then re-search for a better release. |
| Failed / errored grab | Remove with blocklist, then re-search. |
| Wrong release grabbed | Remove with blocklist; grab the correct one. |
| Disk full / health issue | Don't blocklist — fix the underlying issue (see health skill). |
3. Remove (and usually blocklist)
sonarr_remove_queue_item / radarr_remove_queue_item:
removeFromClient: true(default) deletes the failed download from the client.blocklist: trueprevents that exact release from being grabbed again — use it for bad/stalled releases so the re-search picks something different.
4. Re-search after removal
After removing a bad download, the item is missing again — run the interactive search
(*_search_releases) and grab a different release. This is the
late-episode-troubleshooter loop.
Caution
Always confirm before removing items that are still progressing. Blocklisting a good release just because it's slow can push the next search toward a worse option.
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.
- 8d ago First seen · 55 lines · 137 tokens per session scan A c9e2abc82b6f
queue-management is a skill published in the GitHub repository ondrejmirtes/mcparr (6 stars, last pushed 2mo ago), licensed MIT. It adds 137 tokens to every session and 568 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.
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.