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/imoonkey/openweb/bilibilinpx skills add imoonkey/openweb --skill bilibiligit clone --depth 1 https://github.com/imoonkey/openwebWrote 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/imoonkey/openweb/bilibili)<a href="https://agentmods.dev/skills/imoonkey/openweb/bilibili"><img src="https://agentmods.dev/badge/skills/imoonkey/openweb/bilibili.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 | $0.00000 | $0.01466 |
| Opus 5 | $0.00000 | $0.00733 |
| Sonnet 5 | $0.00000 | $0.00293 |
| Haiku 4.5 | $0.00000 | $0.00147 |
Grade A, and why
bilibili scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bilibili
Overview
Chinese video sharing and social platform (similar to YouTube). Archetype: Chinese Web / Video + Social.
Workflows
Browse trending and drill into a video
getPopularVideos()→ browse trending →bvid,aidgetVideoDetail(bvid)→ full metadata, stats →aid,cid,owner.midgetVideoComments(oid=aid, type=1)→ comments withrpid, text, likesgetDanmaku(oid=cid)→ bullet comments (弹幕) with content, progress_ms
Search and engage
searchVideos(keyword)→ results →bvid,author.midgetVideoDetail(bvid)→ full video info →aid,cid,owner.midlikeVideo(aid=aid)→ engage (requires auth + write)unlikeVideo(aid=aid)→ undo engagement
Favorite a video (chains via favorite folder)
listFavoriteFolders()→ user's folders →data.list[0].id(folder media_id)getVideoDetail(bvid)→aidaddToFavorites(rid=aid, add_media_ids=${prev.listFavoriteFolders.data.list.0.id})→ add (requires auth + write)removeFromFavorites(rid=aid, del_media_ids=${prev.listFavoriteFolders.data.list.0.id})→ undo
Explore a creator's content
getUserProfile(mid)→ bio, level, follower count →midsearchUserVideos(mid)→ paginated list of uploads →bvid, title, play count
Follow/unfollow flow
searchVideos(keyword)→author.midorgetUserProfile(mid)→ confirm user →midfollowUploader(fid=mid)→ followunfollowUploader(fid=mid)→ unfollow
Operations
| Operation | Intent | Key Input | Key Output | Notes |
|---|---|---|---|---|
| getPopularVideos | browse trending videos | pn, ps |
bvid, aid, title, play count, uploader, duration | entry point, no auth needed |
| searchVideos | find videos by keyword | keyword |
bvid, title, author.mid, play, danmaku, duration | adapter op, slower |
| getVideoDetail | full video metadata + stats | bvid <- getPopularVideos/searchVideos |
title, desc, aid, cid, owner.mid, play/like/coin/fav stats | wbi-signed |
| getVideoComments | read comments with replies | oid (=aid) <- getVideoDetail, type=1 |
rpid, text, author, likes, reply_count, timestamp | wbi-signed |
| getDanmaku | bullet comments (弹幕) | oid (=cid) <- getVideoDetail, segment_index |
content, progress_ms, mode, color, ctime | adapter op, protobuf decoded |
| getUserProfile | user bio, level, stats | mid <- searchVideos.author.mid / getVideoDetail.owner.mid |
name, sign, level, face, fans_medal | wbi-signed |
| searchUserVideos | user's uploaded videos | mid <- getUserProfile, pn, ps |
title, play, duration, bvid, created | wbi-signed |
| getRecommendedFeed | personalized feed | ps |
bvid, title, play, uploader, duration | entry point |
| listFavoriteFolders | list user's favorite folders | — | data.list[].id (folder media_id), title, media_count |
entry point for favorite chains, requires auth |
| likeVideo | like a video | aid <- getVideoDetail, like=1 |
code, message | write, requires auth |
| unlikeVideo | unlike a video | aid <- getVideoDetail |
code, message | write, reverse of likeVideo |
| addToFavorites | add video to favorites | rid (=aid) <- getVideoDetail, add_media_ids <- listFavoriteFolders.data.list[0].id |
code, message | write, requires auth |
| removeFromFavorites | remove from favorites | rid (=aid) <- getVideoDetail, del_media_ids <- listFavoriteFolders.data.list[0].id |
code, message | write, reverse of addToFavorites |
| followUploader | follow a user | fid (=mid) <- getUserProfile/getVideoDetail.owner.mid |
code, message | write, requires auth |
| unfollowUploader | unfollow a user | fid (=mid) <- getUserProfile/getVideoDetail.owner.mid |
code, message | write, reverse of followUploader |
What ships with it
20 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.
- adapters/bilibili-web.ts 21 KB runs code
- DOC.md 6.4 KB
- examples/addToFavorites.example.json 351 B
- examples/followUploader.example.json 293 B
- examples/getDanmaku.example.json 226 B
- examples/getPopularVideos.example.json 240 B
- examples/getRecommendedFeed.example.json 938 B
- examples/getUserProfile.example.json 249 B
- examples/getVideoComments.example.json 289 B
- examples/getVideoDetail.example.json 246 B
- examples/likeVideo.example.json 294 B
- examples/listFavoriteFolders.example.json 217 B
- examples/removeFromFavorites.example.json 356 B
- examples/searchUserVideos.example.json 366 B
- examples/searchVideos.example.json 250 B
- examples/unfollowUploader.example.json 263 B
- examples/unlikeVideo.example.json 263 B
- manifest.json 517 B
- openapi.yaml 588 KB
- PROGRESS.md 9.3 KB
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.
- 3d ago First seen · 100 lines · 0 tokens per session scan A ae9887069e0b
bilibili is a skill published in the GitHub repository imoonkey/openweb (58 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,466 tokens. 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…