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 TikHub/tikhub-plugin --skill social-media-downloadergit clone --depth 1 https://github.com/TikHub/tikhub-pluginWrote 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/tikhub/tikhub-plugin/social-media-downloader)<a href="https://agentmods.dev/skills/tikhub/tikhub-plugin/social-media-downloader"><img src="https://agentmods.dev/badge/skills/tikhub/tikhub-plugin/social-media-downloader/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/tikhub/tikhub-plugin/social-media-downloader"><img src="https://agentmods.dev/badge/skills/tikhub/tikhub-plugin/social-media-downloader.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 | $0.00088 | $0.01028 |
| Opus 5 | $0.00044 | $0.00514 |
| Sonnet 5 | $0.00018 | $0.00206 |
| Haiku 4.5 | $0.00009 | $0.00103 |
Grade A, and why
social-media-downloader scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s "https://api.tikhub.io/api/v1/tiktok/app/v3/fetch_one_video_by_share_url?share_url=$(python3 -c "import urllib.parse,sys;print(urllib.parse.quote(sys.argv[1],safe=''))" "$URL")" \ How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Social Media Downloader
Turn a post URL into a saved media file by routing it to the correct platform endpoint, extracting the media URL from the response, and downloading it.
Setup gate
[ -z "${TIKHUB_API_KEY:-}" ] && echo "Set TIKHUB_API_KEY first (see tikhub-onboarding)."
Step 1 — Detect the platform from the URL and pick the endpoint
| Platform | Endpoint | Input | Media field |
|---|---|---|---|
| TikTok | GET /api/v1/tiktok/app/v3/fetch_one_video_by_share_url |
share_url |
no-watermark play_addr / download_addr url_list |
| TikTok (by id) | GET /api/v1/tiktok/app/v3/fetch_one_video |
aweme_id |
url_list |
| Douyin | GET /api/v1/douyin/app/v3/fetch_one_video_by_share_url |
share_url |
video url_list |
| Douyin (by id) | GET /api/v1/douyin/app/v3/fetch_one_video_v2 |
aweme_id |
video url_list |
| YouTube | GET /api/v1/youtube/web_v2/get_video_streams_v2 |
video_id | video_url |
stream URLs (pick resolution) |
GET /api/v1/instagram/v2/fetch_post_info |
code_or_url |
media URL(s) | |
| Xiaohongshu | GET /api/v1/xiaohongshu/app_v2/get_video_note_detail (video) / get_image_note_detail (images) |
note_id |
video / image URLs |
| Twitter/X | GET /api/v1/twitter/web/fetch_tweet_detail |
tweet_id |
media url_list |
For TikTok/Douyin, the *_by_share_url endpoints take the raw URL directly — no need to extract an
id. For the others, pull the id/code from the URL (or resolve it via the platform skill).
Step 2 — Call the endpoint
# TikTok by share URL (simplest — pass the URL straight through)
URL="https://www.tiktok.com/@nasa/video/7650608519288245534"
curl -s "https://api.tikhub.io/api/v1/tiktok/app/v3/fetch_one_video_by_share_url?share_url=$(python3 -c "import urllib.parse,sys;print(urllib.parse.quote(sys.argv[1],safe=''))" "$URL")" \
-H "Authorization: Bearer $TIKHUB_API_KEY" -o /tmp/media.json
# YouTube streams
curl -s "https://api.tikhub.io/api/v1/youtube/web_v2/get_video_streams_v2?video_id=dQw4w9WgXcQ" \
-H "Authorization: Bearer $TIKHUB_API_KEY" -o /tmp/media.json
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.
- 12d ago First seen · 73 lines · 88 tokens per session scan A b70f834a1b0c
social-media-downloader is a skill published in the GitHub repository TikHub/tikhub-plugin (7 stars, last pushed 2mo ago), licensed MIT. It adds 88 tokens to every session and 1,028 once invoked, about $0.0004 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
deck-xhs-post
A nine-page vertical image-carousel template for Xiaohongshu or Instagram, using warm pastel colors and dashed sticker-style cards.
ltxv2-video
Build Lightricks LTX-2 / LTX-2.3 video workflows covering text-to-video, image-to-video, GGUF and bundled checkpoints, distilled model, camera control LoRAs, synchronized audio, two-stage upscaling, and swapping alternate/GGUF base models.
ideogram-ultra
Build Ideogram 4 (Ideogram Ultra) txt2img and img2img workflows with the local open-weights model, dual conditional/unconditional models with DualModelGuider, Qwen3-VL text encoder, and structured JSON ("compositional deconstruction") prompts for strong text rendering and layout control.
video-extend
Extend / continue a video temporally with Pusa 2.2 in ComfyUI. Temporal flowmatching (the flowmatchpusa scheduler + WanVideoAddPusaNoise) on the WanVideoWrapper stack with WAN 2.2 T2V A14B (HIGH/LOW) models and the Pusa V1 LoRAs, conditioning on the loaded clip via WanVideoEncode so the existing motion carries into…
model-compatibility
Model family compatibility matrix covering loaders, resolutions, samplers, CFG, VAE, ControlNet, and LoRA compatibility for SD 1.5, SDXL, Flux, SD3, and video models.
qwen-image-edit
Build Qwen Image Edit workflows covering model loading, conditioning, LoRAs, prompt patterns, and XY plot testing.