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/chianw/c31/video-content-analysisnpx skills add ChianW/C31 --skill video-content-analysisgit clone --depth 1 https://github.com/ChianW/C31Wrote 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/chianw/c31/video-content-analysis)<a href="https://agentmods.dev/skills/chianw/c31/video-content-analysis"><img src="https://agentmods.dev/badge/skills/chianw/c31/video-content-analysis.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 5.1 | $0.00000 | $0.01357 |
| Opus 5 | $0.00000 | $0.00678 |
| Sonnet 5 | $0.00000 | $0.00271 |
| Haiku 4.5 | $0.00000 | $0.00136 |
Grade A, and why
video-content-analysis 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s --max-time 10 ipinfo.io How it starts
The opening of the file, as written. The whole thing — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Video Content Analysis
Status: Three-tier fallback video content analysis Dependencies: yt-dlp (proxy required), kimi_search, kimi_fetch Tags: #content-analysis #video #tech-pulse #youtube #bilibili
Three-Tier Fallback Strategy
L1: yt-dlp direct subtitle extraction (most accurate, requires proxy)
L2: Search third-party transcripts (Lilys.ai, Glasp, YouTube auto-captions, note sites)
L3: web_fetch page metadata (title, description — lightest option)
Multilingual Triggers
| Language | Trigger phrases |
|---|---|
| EN | video-content-analysis |
| ZH | 视频分析, 内容分析 |
| JA | 動画分析, コンテンツ分析 |
Output language: Respond automatically in the user's conversation language.
L1: yt-dlp Direct Extraction (Most Accurate)
Prerequisite: Proxy configured on the server
# Extract subtitles
yt-dlp --write-sub --skip-download --sub-langs en,zh-CN,zh-TW,auto "URL"
# Extract metadata + subtitle list
yt-dlp --dump-json --skip-download "URL" | jq '{title, uploader, duration, upload_date, subtitle_languages: (.subtitles | keys)}'
# Extract audio + Whisper transcription (fallback)
yt-dlp --extract-audio --audio-format mp3 -o "audio.%(ext)s" "URL"
Proxy Configuration:
# Temporary proxy (single command)
export http_proxy="socks5://user:pass@host:port"
export https_proxy="socks5://user:pass@host:port"
yt-dlp --write-sub --skip-download "URL"
# Or use yt-dlp's built-in proxy flag
yt-dlp --proxy "socks5://user:pass@host:port" --write-sub --skip-download "URL"
L2: Third-Party Transcript Search (Fallback)
Triggered automatically when L1 fails. Search the following sources:
Search Query Templates
# YouTube video
site:lilys.ai "youtube.com/watch?v=VIDEO_ID"
site:lilys.ai "youtu.be/VIDEO_ID"
VIDEO_TITLE "transcript" "summary"
VIDEO_TITLE "文字稿" "笔记"
# Bilibili video
site:lilys.ai "bilibili.com/video/BV"
site:bilibili.com "BV" "字幕"
"BVxxxxx" "transcript"
# General
"VIDEO_TITLE" "字幕" "完整"
"VIDEO_TITLE" "transcript" "full"
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.
- 5d ago First seen · 177 lines · 0 tokens per session scan A 00dfe7069e6f
video-content-analysis is a skill published in the GitHub repository ChianW/C31 (1 stars, last pushed 10d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,357 tokens. 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
compare-harnesses
Diff two scaffolded harnesses (ADR-031). Reports manifest meta drift + host list + per-file fingerprint changes (added/removed/changed). Exits 0 IDENTICAL, 1 DRIFT, 2 missing manifest. Use --bundle for the ADR-031 schema-1 JSON envelope.
diag-harness
Kernel-version skew check (ADR-027). Reports manifest surface + manifest kernel + installed kernel + verdict (match/patch-diff/minor-diff/major-diff). Exits 1 on minor/major skew with a copy-pasteable npm install @metaharness/[email protected] next step. Exits 2 if no .harness/manifest.json at path.
oia-manifest
Emit .harness/oia-manifest.json declaring layer alignment with the OIA v0.1 9-layer reference architecture. Self-describes the harness's MCP wiring, witness signing, audit log, identity posture (always 'none' at v0.1). --check verifies an existing manifest, --dry-run prints without writing, --json emits to stdout.
create-harness
Scaffold your own focused AI agent harness — pick host (Claude Code, Codex, pi.dev, Hermes), template, agents, skills, and ship a npm-publishable harness with its own npx CLI. Use when a user asks to "create my own agent harness", "scaffold a harness", "make a custom Claude Code plugin like ruflo", or "build a…
example-harness
Scaffold a ready-made AI agent harness in one command from the 19 published @metaharness/ example packages — 9 host integrations (Claude Code, Codex, Hermes, pi.dev, OpenClaw, RVM, Copilot, OpenCode, GitHub Actions) + 10 vertical pods (devops, research, trading, support, legal, coding, education, sales, gaming…
repo-genome
7-section readiness scorecard for a LOCAL repo. Reports repo type + agent topology + MCP risk + test confidence + release readiness + recommended harness plan + scorecard. Exit 0 ready, 1 needs-work, 2 blocked. --json for the 6-field scorecard, --bundle for the ADR-031 schema-1 envelope.