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/xiaoleiy/podpull/integrationsnpx skills add xiaoleiy/podpull --skill integrationsgit clone --depth 1 https://github.com/xiaoleiy/podpullWhat 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 | $0.00108 | $0.01024 |
| Opus 5 | $0.00054 | $0.00512 |
| Sonnet 5 | $0.00022 | $0.00205 |
| Haiku 4.5 | $0.00011 | $0.00102 |
Grade A, and why
podpull 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
podpull — download podcast episode audio
Use the installed podpull command-line tool to download podcast audio.
Repo: https://github.com/xiaoleiy/podpull
If it isn't installed: brew install xiaoleiy/tap/podpull (macOS/Linux) or
pipx install git+https://github.com/xiaoleiy/podpull.
How it works (so you pick the right command)
Apple Podcasts holds no audio — it points at each show's RSS feed, where every
episode has a direct <enclosure> URL. podpull resolves Apple show URLs/IDs, raw
RSS feeds, and xiaoyuzhou links to that audio and downloads it.
Commands
podpull search "<keywords>" # find shows -> Apple ID, #episodes, name
podpull info <src> # show metadata (title, author, feed, latest)
podpull list <src> [--match RE] [--all] # list episodes; index 0 = newest
podpull get <src> --match RE | --latest N | --index 0,2[,..] # download (alias: `pull`)
podpull get <episode-url> # download a pasted Apple ?i= or xiaoyuzhou link
podpull get <src> ... -q / --quiet # suppress spinner/progress bar
podpull --json <cmd> … # one JSON document on stdout (flag before command)
podpull serve [--host] [--port] # local UI: search / trending / browser download
Hosted web UI (same idea, no install): https://podpull.xiaolei.work/app
<src> = Apple show URL · bare Apple ID · RSS feed URL · Apple episode ?i= URL · xiaoyuzhou episode URL.
Workflow
- Resolve the show: if you only have a name,
podpull search "<name>"; thenpodpull list <id>to see episodes. - Download with a selector —
--match(title regex),--latest N, or--index 0,2. - Report the saved path. The file path is printed to stdout; progress/UI go to stderr, so capture stdout when scripting.
Important for agents (non-interactive)
- Always pass a selector and
--no-input. Runningpodpull get <show>with no selector opens an interactive keyboard picker — which can't be driven non-interactively and will instead error with a hint. Use e.g.podpull get 1532755821 --latest 1 --no-input. - Add
-q/--quietto suppress the spinner and live progress bar on stderr — recommended for agent transcripts, since neither renders meaningfully outside a live terminal. Saved file paths still print to stdout either way. - Prefer
podpull --json …when you need structured data (search/info/list/get). The flag goes before the command. On success stdout is one JSON document; on failure check the exit code (human error on stderr, no JSON). - Downloads default to
~/Downloads/Podcasts; pass--out DIRto change. - Selecting multiple episodes creates a per-show sub-folder. Filenames are normalized to be cloud-storage-safe (emoji/illegal characters removed; CJK kept).
- Optional: if PODCASTINDEX_API_KEY/PODCASTINDEX_API_SECRET are set,
searchalso queries Podcast Index and feed resolution gains a fallback; ximalaya.com/album/ links work as a source.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago First seen · 69 lines · 0 tokens per session scan A 2a6ab6bbdd8f
podpull is a skill published in the GitHub repository xiaoleiy/podpull (141 stars, last pushed 1mo ago), licensed MIT. It adds 108 tokens to every session and 1,024 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
ui-ux-pro-max
UI/UX design intelligence for web, mobile, and desktop. This skill should be used when designing, building, reviewing, or fixing interfaces, including pages, components, design systems, accessibility, interaction, responsive layout, typography, color, charts, and stack-specific UI implementation. Searchable local…
record-demo
Record or regenerate the mcpc demo GIFs (the README hero docs/images/mcpc-demo.gif and the focused tapes in docs/vhs/) with VHS. Use whenever asked to create, refresh, restyle, shorten, or fix a terminal demo/animation/GIF of mcpc. The tapes drive real mcpc commands; for the authenticated step this skill ALWAYS…
video-gen
Generate AI videos from text prompts or reference materials. Supports HappyHorse, SeeDance, and PixVerse models. Triggers on: "生成视频", "做视频", "video generation", "text to video", "create video", "视频生成", "视频编辑", "video edit", "pixverse", "口型", "lipsync", "对口型".
podcast-transcribe
播客/小宇宙 → 下载 → 转录 → 存为 Markdown 的完整工作流。 支持 RSS 批量下载、单集链接转录。.
listenhub-voice
End-to-end audio generation with ListenHub-Voice-1.0 (text / image → audio). Supports sound effects, multi-voice dialogue, reference-audio cloning, and a duration hint. Triggers on: "生成音频", "语音生成", "端到端音频", "图片转音频", "图片生成音频", "多音色对白", "参考音频克隆", "克隆音色", "音效生成", "生成音效".
music
Generate, remix, extend, edit, and analyze AI music (Mureka). Triggers on: "音乐", "music", "生成音乐", "generate music", "翻唱", "cover", "混音", "remix", "续写", "extend", "纯音乐", "instrumental", "配乐", "soundtrack", "分轨", "stem", "识别歌词", "recognize lyrics", "作曲", "compose", "create a song", "做一首歌".