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-downloadsgit 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-downloads)<a href="https://agentmods.dev/skills/t3chnaztea/arr-stack-skills/arr-downloads"><img src="https://agentmods.dev/badge/skills/t3chnaztea/arr-stack-skills/arr-downloads/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-downloads"><img src="https://agentmods.dev/badge/skills/t3chnaztea/arr-stack-skills/arr-downloads.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 | $0.00156 | $0.02005 |
| Opus 5 | $0.00078 | $0.01002 |
| Sonnet 5 | $0.00031 | $0.00401 |
| Haiku 4.5 | $0.00016 | $0.00200 |
Grade A, and why
arr-downloads 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 10d 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/health" \ How it starts
The opening of the file, as written. The whole thing — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Arr Downloads
Nothing arrived. The chain from "user wants a thing" to "file is in the library" has six links, and the useful skill is finding which one broke instead of restarting everything.
request front-end -> arr decides -> indexer search -> release grabbed
-> download client -> import into library
Walk it in order. Assumes arr-connect.
Start with health and history
Two calls answer most of these before you form a theory.
# the app has usually already diagnosed it
curl -sf -H "X-Api-Key: $ARR_KEY" "$ARR_URL/api/v3/health" \
| jq '.[] | {source, type, message}'
# what actually happened recently, per title
curl -sf -H "X-Api-Key: $ARR_KEY" "$ARR_URL/api/v3/history?pageSize=30" \
| jq '.records[] | {date, eventType, sourceTitle, data: (.data.reason // .data.message // empty)}'
eventType tells you exactly how far down the chain a title got:
grabbed then nothing means the client never took it or never finished.
downloadFolderImported means it worked. downloadFailed and
importFailed name their own problem.
Link 1: the request front-end
If users say requests are being declined, check whether they actually failed. Request front-ends often surface a failed hand-off to the arr with wording that reads as a rejection.
The most common cause is a stale quality profile id in the front-end's server
settings, usually after profiles were renumbered. The front-end's log carries
the real error: adding the item failed because the quality profile does not
exist. Fix the server settings, then retry the failed requests rather than
asking users to re-request, because re-requesting hits the duplicate guard.
Details in arr-quality-profiles.
Link 2: is the arr even searching
A search command returning queued means accepted. It does not mean anything
was searched for. The most common reason a search matches nothing is that the
target is not monitored, which arr-library-hygiene covers in depth.
# Sonarr: how many episodes are actually armed
curl -sf -H "X-Api-Key: $ARR_KEY" "$ARR_URL/api/v3/episode?seriesId=$SID" \
| jq '[.[] | select(.monitored)] | length'
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.
- 10d ago First seen · 191 lines · 156 tokens per session scan A 0f2c0fe4de14
arr-downloads is a skill published in the GitHub repository t3chnaztea/arr-stack-skills (1 stars, last pushed 18d ago), licensed MIT. It adds 156 tokens to every session and 2,005 once invoked, about $0.0008 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.