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-library-hygienegit 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-library-hygiene)<a href="https://agentmods.dev/skills/t3chnaztea/arr-stack-skills/arr-library-hygiene"><img src="https://agentmods.dev/badge/skills/t3chnaztea/arr-stack-skills/arr-library-hygiene/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-library-hygiene"><img src="https://agentmods.dev/badge/skills/t3chnaztea/arr-stack-skills/arr-library-hygiene.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 | $0.00142 | $0.02522 |
| Opus 5 | $0.00071 | $0.01261 |
| Sonnet 5 | $0.00028 | $0.00504 |
| Haiku 4.5 | $0.00014 | $0.00252 |
Grade A, and why
arr-library-hygiene 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/series/$SID?includeSeriesStats=true" \ How it starts
The opening of the file, as written. The whole thing — 236 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Arr Library Hygiene
The monitored flag drives every automated search. When it drifts from what
you intended, the app either hunts for things it should ignore or sits silent
when you expect it to work. Both look like bugs elsewhere.
Assumes arr-connect. In particular: deletes are permanent, there is no
recycle bin unless you configured one, and a command returning queued means
accepted, not successful.
Three ways monitoring drifts
1. Segment-aired shows create permanent phantom missing episodes
Cartoons and sketch shows that aired as segments are often catalogued with each segment as its own episode entry, while your files are whole broadcast episodes. The app counts the extra segment entries as missing forever. Every night it re-searches, grabs a season pack, fails to import with episode file already imported, and refills the queue. The queue length looks alarming and never drops.
Diagnose by comparing counts, not by reading the queue:
curl -sf -H "X-Api-Key: $ARR_KEY" "$ARR_URL/api/v3/series/$SID?includeSeriesStats=true" \
| jq '{title, episodeCount: .statistics.episodeCount,
episodeFileCount: .statistics.episodeFileCount,
pct: (.statistics.episodeFileCount / .statistics.episodeCount * 100 | floor)}'
A gap that never closes across days, on a show that finished airing years ago, is this pattern rather than a sourcing problem.
Fix: unmonitor only the monitored-but-file-less episodes, then clear the stuck queue.
# the episodes that will never arrive
IDS=$(curl -sf -H "X-Api-Key: $ARR_KEY" "$ARR_URL/api/v3/episode?seriesId=$SID" \
| jq -c '[.[] | select(.monitored and (.hasFile | not)) | .id]')
curl -sf -X PUT -H "X-Api-Key: $ARR_KEY" -H 'Content-Type: application/json' \
-d "{\"episodeIds\": $IDS, \"monitored\": false}" \
"$ARR_URL/api/v3/episode/monitor"
For a finished show this stops the grabbing and keeps every existing file. For a still-airing show, do not do this: you would unmonitor genuinely missing episodes. Check the series status first.
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 · 236 lines · 142 tokens per session scan A 1e4cb35e43b2
arr-library-hygiene is a skill published in the GitHub repository t3chnaztea/arr-stack-skills (1 stars, last pushed 17d ago), licensed MIT. It adds 142 tokens to every session and 2,522 once invoked, about $0.0007 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
release-it
Build production-ready systems with stability patterns: circuit breakers, bulkheads, timeouts, and retry logic. Use when the user mentions "production outage", "circuit breaker", "deployment pipeline", "chaos engineering", "retry storm", "health checks", "my service keeps crashing", "prevent cascading failures", or…
tidewave-integration
Tidewave MCP runtime tools — debugging, smoke testing, live state inspection, SQL queries, hex docs. Use when evaluating code in a running Phoenix app.
debug
Interactive debugging workflow with hypothesis-driven probe loop. Use when: unknown bugs, script errors, silent failures, troubleshooting. Not for: known bugs (use bug-fix), GitHub issue analysis (use issue-analyze), code understanding (use code-explore). Output: debug report with probe journal + root cause + fix.
git-investigate
Git history investigation. Use when: tracking code changes, finding where bugs were introduced, root cause analysis. Not for: code exploration (use code-explore), issue analysis (use issue-analyze). Output: history trace + root cause report.
analyze
Deep-dive codebase analysis that explains how things actually work — business rules, architecture patterns, auth flows, data models, integrations, and performance hotspots. Use whenever the user asks "how does X work", "map the Y flow", "what are the business rules for Z", "trace the auth path", "explore the codebase…
simplify
Wrap-up refactoring — simplify code, eliminate duplication, preserve behavior.