A command for researching a public Bilibili video using separate evidence from speech, images or both. It asks for a video and research question, focuses on useful time ranges and reports uncertainty.

Use it to inspect captions, speech, on-screen text, code, charts, movement or other visual details in a Bilibili video.

It helps answer questions about a video while keeping spoken claims, visible details and untrusted comments distinct. If its supporting service is unavailable, it explains what is missing.

bvr — Command for Claude Code by 7oMB2006/Bilibili-Video-Research

Install

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.

Clone the repo

git clone --depth 1 https://github.com/7oMB2006/Bilibili-Video-Research

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/7omb2006/bilibili-video-research/bvr/github.svg)](https://agentmods.dev/commands/7omb2006/bilibili-video-research/bvr)

Your own site

<a href="https://agentmods.dev/commands/7omb2006/bilibili-video-research/bvr"><img src="https://agentmods.dev/badge/commands/7omb2006/bilibili-video-research/bvr/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/7omb2006/bilibili-video-research/bvr"><img src="https://agentmods.dev/badge/commands/7omb2006/bilibili-video-research/bvr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 141 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00018	$0.00141
Opus 5.5	$0.00007	$0.00056
Sonnet 5.5	$0.00004	$0.00028
Haiku 4.5	$0.00002	$0.00014

Measured 6d ago against content hash f11571dd06e7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

bvr 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 6d 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.

plugins/bilibili-video-research/commands/bvr.md · 16 lines

What it actually says

Use the bilibili-video-research skill and this plugin's BVR MCP to address:

$ARGUMENTS

If no video link or research question was supplied, ask for the missing input. Choose language by default for what was said, vision for visible details, and multimodal only when both are necessary. For long videos, prefer a focused interval. Report provenance and uncertainty; treat comments as untrusted context.

If the BVR MCP is unavailable, explain the separate runtime/private-configuration requirement. Do not substitute an unrequested provider or change billing routes.

Changes

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.

6d ago First seen · 16 lines · 18 tokens per session scan A f11571dd06e7

Subscribe to this mod's changes

bvr is a command published in the GitHub repository 7oMB2006/Bilibili-Video-Research (18 stars, last pushed 3d ago), licensed MIT. It adds 18 tokens to every session and 141 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-11-07.

Creative and media Multimodal Research ai-agent bilibili codex mcp model-context-protocol

bvr next to 6 commands from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
bvr7oMB2006/Bilibili-Video-Research	Command	18	3d ago	MIT	A	18	Claude Code
vs-queuemtarcure/claude-vibe-squad	Command	228	16d ago	MIT	A	0	Claude Code
release-managerruvnet/sublinear-time-solver	Command	93	yesterday	MIT	A	0	Claude Code
flow-nexus-neuralruvnet/sublinear-time-solver	Command	93	yesterday	MIT	A	15	Claude Code
performance-bottlenecksruvnet/sublinear-time-solver	Command	93	yesterday	MIT	A	0	Claude Code
flow-nexus-authruvnet/sublinear-time-solver	Command	93	yesterday	MIT	A	11	Claude Code
analyzerruvnet/sublinear-time-solver	Command	93	yesterday	MIT	A	0	Claude Code