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 agentmods add skills/nikets40/fleapit/torrentsnpx skills add nikets40/fleapit --skill torrentsgit clone --depth 1 https://github.com/nikets40/fleapitWrote 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/nikets40/fleapit/torrents)<a href="https://agentmods.dev/skills/nikets40/fleapit/torrents"><img src="https://agentmods.dev/badge/skills/nikets40/fleapit/torrents.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 | $0.00048 | $0.00453 |
| Opus 5 | $0.00024 | $0.00227 |
| Sonnet 5 | $0.00010 | $0.00091 |
| Haiku 4.5 | $0.00005 | $0.00045 |
Grade A, and why
torrents 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 5d 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
Torrents
The fleapit MCP server provides: search_torrents, download_torrent, stream_torrent, list_files, list_downloads, control_torrent.
Workflow
- Search first.
search_torrentswith the user's query; passcategory(movies/tv/anime/games) when obvious — it's faster and cleaner. Results are sorted by seeders. - Pick sensibly. Prefer high seeders and reasonable size. For movies, a 1–4 GB 1080p file beats a 60 GB remux unless asked. Show the user 2–3 candidates if the choice isn't obvious.
- Download or stream:
- User wants the file →
download_torrentwith the magnet. - User wants to watch it →
stream_torrent; it picks the largest video file and opens VLC automatically. Playback starts within seconds; the download continues behind it. - Multi-episode torrent →
list_filesfirst, thenstream_torrentwith the rightfileIndex.
- User wants the file →
- Progress.
list_downloadsshows progress/speed/ETA. Don't poll in a loop unless asked to babysit a download. - Cleanup.
control_torrentpauses/resumes;removeforgets but keeps files;deletealso removes files from disk — confirm with the user beforedelete.
Notes
- Downloads go to
~/Downloadsunless the user gives a folder (orFLEAPIT_DIRis set). - Torrents live only while the MCP server runs; interrupted downloads resume from existing file data when re-added.
- If metadata fetch times out, the swarm is weak — suggest a better-seeded result instead of retrying blindly.
- A seeders count of 0 from a source that doesn't report health means "unknown", not "dead".
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.
- 5d ago First seen · 27 lines · 48 tokens per session scan A 9bdaf78cc6b7
torrents is a skill published in the GitHub repository nikets40/fleapit (0 stars, last pushed 1mo ago), licensed MIT. It adds 48 tokens to every session and 453 once invoked, about $0.0002 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
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…