comment_analysis

comment_analysis is a skill for Claude Code, Codex from whiteguo233/OpenBiliClaw. It costs 16 tokens per session (199 once invoked), scanned A, original, MIT.

A video-comment analysis tool that reads comments from a video and identifies recommendations, viewer reactions, and signals about content quality.

In plain words
What is it for?
Use it to discover other videos or creators recommended by viewers and assess how people received the original video.
Why use it?
It turns a large comment section into a short, structured summary, so you can spot useful recommendations without reading every comment.

Skill for Claude CodeCodex

About the project

OpenBiliClaw is a local, open-source AI agent that learns a person's interests and discovers content across multiple social platforms and the open web. It is for people who want personalized content recommendations with their usage data kept on their own machine.

whiteguo233/OpenBiliClaw · 3,203 stars · on GitHub

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.

agentmods
npx agentmods add skills/whiteguo233/openbiliclaw/comment_analysis
Any agent
npx skills add whiteguo233/OpenBiliClaw --skill comment_analysis
Clone the repo
git clone --depth 1 https://github.com/whiteguo233/OpenBiliClaw

Made for: Claude Code, Codex.

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.

agentmods badge for comment_analysis

README.md
[![agentmods](https://agentmods.dev/badge/skills/whiteguo233/openbiliclaw/comment_analysis.svg)](https://agentmods.dev/skills/whiteguo233/openbiliclaw/comment_analysis)
Your own site
<a href="https://agentmods.dev/skills/whiteguo233/openbiliclaw/comment_analysis"><img src="https://agentmods.dev/badge/skills/whiteguo233/openbiliclaw/comment_analysis.svg" alt="Measured on agentmods" height="20"></a>
Per session 16 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 199 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00016 $0.00199
Opus 5 $0.00008 $0.00100
Sonnet 5 $0.00003 $0.00040
Haiku 4.5 $0.00002 $0.00020

Measured 5d ago against content hash 310db176498b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

comment_analysis 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 5d 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.

skills/comment_analysis/SKILL.md · 35 lines

What it actually says

Comment Analysis Skill

Mine video comment sections for content recommendations and quality signals.

When to Use

  • As part of the content discovery cycle
  • To evaluate the quality and reception of discovered content
  • To find user-recommended content and UP主 from comments

How It Works

  1. Fetches comments from a video via API or agent-browser
  2. Uses LLM to identify:
    • Other video/UP主 recommendations mentioned in comments
    • Overall content quality sentiment
    • Common viewer reactions and highlights
  3. Returns structured analysis

Parameters

  • bvid (str): Video BV ID to analyze comments for
  • max_comments (int, optional): Maximum comments to analyze (default: 100)

Output

  • Recommended content/UP主 found in comments
  • Quality sentiment score
  • Key highlights and reactions
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.

  1. 5d ago First seen · 35 lines · 16 tokens per session scan A 310db176498b

Subscribe to this mod's changes

comment_analysis is a skill published in the GitHub repository whiteguo233/OpenBiliClaw (3,203 stars, last pushed today), licensed MIT. It adds 16 tokens to every session and 199 once invoked, about $0.0001 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.