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 limuzi23/bilibili-video-reader-mcp --skill bilibili-video-readergit clone --depth 1 https://github.com/limuzi23/bilibili-video-reader-mcpWrote 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/limuzi23/bilibili-video-reader-mcp/bilibili-video-reader)<a href="https://agentmods.dev/skills/limuzi23/bilibili-video-reader-mcp/bilibili-video-reader"><img src="https://agentmods.dev/badge/skills/limuzi23/bilibili-video-reader-mcp/bilibili-video-reader/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/limuzi23/bilibili-video-reader-mcp/bilibili-video-reader"><img src="https://agentmods.dev/badge/skills/limuzi23/bilibili-video-reader-mcp/bilibili-video-reader.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 | $0.00083 | $0.00565 |
| Opus 5 | $0.00042 | $0.00282 |
| Sonnet 5 | $0.00017 | $0.00113 |
| Haiku 4.5 | $0.00008 | $0.00056 |
Grade A, and why
bilibili-video-reader 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 11d 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bilibili Video Reader v2.1
Use the bundled MCP tools for live Bilibili data. Do not run local yt-dlp scripts in ChatGPT.
Required workflow
- For any Bilibili/B23/BV input, call
get_bilibili_video_partsfirst. - If the user asks for the whole collection/all P, verify
total_partsand iterate over every requested part. - Call
get_bilibili_part_transcriptonce per part. - Respect tool statuses exactly:
ok: summarize the returned transcript.login_required: tell the user this subtitle track requires login state; never invent text.no_subtitles: state that no official/AI subtitle is exposed; do not pretend otherwise.error: report the error and do not fabricate missing content.
- Keep speaker content separate from your own reconstruction.
- If code is visible on screen but not spoken in the subtitle, label it as unavailable from subtitle-only extraction. Never claim reconstructed code is verbatim.
Output modes
For algorithm / machine-test videos, use references/OUTPUT_FORMAT.md and organize each P as:
- P number and title
- Problem / task
- Method used in the video
- Key steps
- Complexity when justified
- Edge cases / pitfalls
- Python code, only when supported by the transcript or clearly labeled
根据讲解重写
For tutorials, organize by method → purpose → steps → parameters → pitfalls.
For a transcript-only request, return cleaned timestamped transcript and do not over-summarize.
Multi-P completeness rule
When the user asks for all P, the final answer must state how many parts were discovered, how many were successfully transcribed, and list any missing/login-required parts. Never silently omit a part.
Security
- Never ask the user to paste passwords,
SESSDATA, access tokens, or raw cookie text into chat. - Public subtitle access requires no secret.
- If login-only subtitle support is needed, it may be configured privately as an encrypted Cloudflare Worker secret named
BILI_COOKIE; the user should set it directly in Cloudflare, never in chat or GitHub. - Do not bypass paywalls, VIP restrictions, DRM, geographic restrictions, or account permissions.
What ships with it
1 file 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.
- 11d ago First seen · 49 lines · 83 tokens per session scan A cf3a7fb96b90
bilibili-video-reader is a skill published in the GitHub repository limuzi23/bilibili-video-reader-mcp (0 stars, last pushed 22d ago), licensed MIT. It adds 83 tokens to every session and 565 once invoked, about $0.0004 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
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
book-mirror
Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…
miniapp
Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
deck-course-module
A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.
master-yinguang
A reference-based assistant for questions about Yinguang and Pure Land Buddhism, a Buddhist tradition focused on faith, ethical living, and practice connected with rebirth in the Pure Land. It can answer in Yinguang’s historical teaching style.