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 t3chnaztea/arr-stack-skills --skill arr-quality-profilesgit clone --depth 1 https://github.com/t3chnaztea/arr-stack-skillsWrote 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/t3chnaztea/arr-stack-skills/arr-quality-profiles)<a href="https://agentmods.dev/skills/t3chnaztea/arr-stack-skills/arr-quality-profiles"><img src="https://agentmods.dev/badge/skills/t3chnaztea/arr-stack-skills/arr-quality-profiles/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/t3chnaztea/arr-stack-skills/arr-quality-profiles"><img src="https://agentmods.dev/badge/skills/t3chnaztea/arr-stack-skills/arr-quality-profiles.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 | $0.00176 | $0.02793 |
| Opus 5 | $0.00088 | $0.01396 |
| Sonnet 5 | $0.00035 | $0.00559 |
| Haiku 4.5 | $0.00018 | $0.00279 |
Grade A, and why
arr-quality-profiles scanned grade A with 1 finding 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 9d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sf -H "X-Api-Key: $ARR_KEY" "$ARR_URL/api/v3/qualityprofile" \ How it starts
The opening of the file, as written. The whole thing — 264 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Arr Quality Profiles
A quality profile answers two questions: what may this app grab, and when may it stop looking. Most "the arr is behaving insanely" reports are one of those two answers being wrong in a way the UI does not make obvious.
Assumes arr-connect for the API pattern. Read the whole profile object,
modify, PUT it back, read it again.
The model, briefly
A profile has an allowed quality list (an ordered ladder, with optional groups), a cutoff (the rung at which "good enough" is reached), a set of custom format scores, and a cutoffFormatScore (the format score at which format-driven upgrading stops).
Two independent stop conditions, and both must be reachable:
- Quality cutoff reached, and
- Format score at or above
cutoffFormatScore.
If either is unreachable by any release that actually exists, the app never considers the item done and keeps searching forever.
curl -sf -H "X-Api-Key: $ARR_KEY" "$ARR_URL/api/v3/qualityprofile" \
| jq '.[] | {id, name, cutoff, cutoffFormatScore, upgradeAllowed,
allowed: [.items[] | select(.allowed) | (.quality.name // .name)]}'
Run that first, every time. Profile ids are per-instance. Any document that tells you "use profile 6" is describing someone else's install.
Trap: cutoffFormatScore left at 10000 causes endless upgrade storms
This is the highest-value item in this skill.
Several popular profile templates ship cutoffFormatScore: 10000 as a
placeholder meaning "effectively never stop upgrading on format". If no
release in existence can score 10000 under your custom format set, the app
treats every item as permanently cutoff-unmet. It re-searches nightly,
re-grabs marginally different releases, churns your download client, and
rewrites files that were already fine.
The symptom people report is "it keeps downloading the same movie over and over" or "my seedbox is constantly busy and nothing changes".
Diagnose:
curl -sf -H "X-Api-Key: $ARR_KEY" "$ARR_URL/api/v3/qualityprofile" \
| jq '.[] | select(.cutoffFormatScore >= 1000) | {id,name,cutoffFormatScore}'
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.
- 9d ago First seen · 264 lines · 176 tokens per session scan A 50e99da6554d
arr-quality-profiles is a skill published in the GitHub repository t3chnaztea/arr-stack-skills (1 stars, last pushed 17d ago), licensed MIT. It adds 176 tokens to every session and 2,793 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
yarr
This skill should be used when the user wants to query or automate their media automation stack — Sonarr (TV shows), Radarr (movies), Prowlarr (indexers), Tautulli (Plex stats), Overseerr (media requests), SABnzbd (Usenet downloads), qBittorrent (torrents), Plex (media server), Jellyfin, Bazarr (subtitles), or…
overseerr
This skill should be used when the user wants to request movies or TV shows via Overseerr, monitor or manage media requests, or check request status. Triggers include: "request a movie", "request a TV show", "add to Overseerr", "check request status", "pending requests", "is my request done", "Overseerr status"…
plex
This skill should be used when the user wants to interact with their Plex Media Server. Triggers include: "check Plex", "search Plex", "what's on Plex", "what's playing on Plex", "who's watching", "Plex sessions", "active streams", "Plex library", "browse movies", "browse TV shows", "recently added", "on deck"…
radarr
This skill should be used when the user wants to manage movies in Radarr. Triggers include: "add a movie", "search Radarr", "find a film", "download a movie", "remove a movie", "add movie collection", "check if movie exists", "is [film] in my library", "monitor a film", "check download queue", "Radarr library", or any…
prowlarr
This skill should be used when the user asks to search torrent or usenet indexers, find a release (by title, TVDB/IMDB/TMDB id), list or check indexer health/status, test indexers, enable/disable/delete an indexer, sync indexers to Sonarr or Radarr, connect Prowlarr to another app, or mentions Prowlarr or indexer…
qbittorrent
This skill should be used when the user asks about torrents, downloading, seeding, or the qBittorrent client. Triggers include: "what's downloading", "list torrents", "add a torrent", "pause/resume/delete torrent", "torrent speed", "download queue", "qbit", "qBittorrent stats", "check download status", or any mention…