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/kewton/commandmate/demo-videonpx skills add Kewton/CommandMate --skill demo-videogit clone --depth 1 https://github.com/Kewton/CommandMateWrote 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/kewton/commandmate/demo-video)<a href="https://agentmods.dev/skills/kewton/commandmate/demo-video"><img src="https://agentmods.dev/badge/skills/kewton/commandmate/demo-video.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 | $0.00084 | $0.12011 |
| Opus 5 | $0.00042 | $0.06006 |
| Sonnet 5 | $0.00017 | $0.02402 |
| Haiku 4.5 | $0.00008 | $0.01201 |
Grade A, and why
demo-video 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.
command -v tmux git curl node claude || echo "missing" How it starts
The opening of the file, as written. The whole thing — 425 lines — stays where its author put it; the contents beside it link to each section on GitHub.
demo-video
CommandMate の 30 秒デモ動画を全自動生成する。demo-video.sh 一発で demo-30s.ja.mp4 と demo-30s.en.mp4 が出る。
.claude/skills/demo-video/scripts/demo-video.sh # ja + en
.claude/skills/demo-video/scripts/demo-video.sh --check # 依存＋絵コンテ検証だけ
.claude/skills/demo-video/scripts/demo-video.sh --locale ja --gif --out ~/Desktop/cm-demo
出力先の既定は ~/Desktop/commandmate-demo/。リポジトリ外である。mp4 / GIF / 中間 PNG はコミットしない（配布は GitHub Release アセット等）。生成後に git status がクリーンであることが受入条件のひとつ。
設計判断
実 LLM は使わない。 実セッションは非決定的で、生成に数分かかり 30 秒に収まらない。代わりにキャプチャ済み ANSI 出力をタイミング付きで再生する「偽エージェント」を tmux セッションで動かす。
置き換えるのは LLM だけで、モックは 1 つも入れていない。CommandMate から見た入力は tmux pane の中身だけなので、status-detector.ts / response poller / サイドバーの状態ドットはすべて製品コードのまま動く。偽エージェントが差し込まれるのは tmux capture-pane が返すバイト列の出所だけである。
テロップは HTML → PNG → ffmpeg overlay で焼き込む。drawtext は日本語に fontfile の明示が要り、: や ' のエスケープ規則のせいで絵コンテの文字列をそのまま渡せない。HTML なら意匠が CSS 1 箇所に集約でき、文字列は textContent で入るので絵コンテがマークアップを注入することもない。
ロケールはフル録画方式。 --locale ja はアプリ UI ごと日本語にして撮り直す。テロップだけ差し替えると、画面は英語・字幕は日本語という動画になる。日英の文言は絵コンテに直書きで、生成時に機械翻訳はしない（人間がレビューできない文字列を画面に出さないため）。
構成
demo-video/
├── SKILL.md
├── scripts/
│ ├── demo-video.sh # パイプライン全体（依存確認 → ロケールごとに録画 → 合成 → 尺検証）
│ ├── env-up.sh # 隔離デモ環境の起動（seed repo 生成 → サーバ起動 → Ready 確認）
│ ├── env-down.sh # 停止・後片付け（PID 経由の kill のみ。pkill は使わない）
│ ├── fake-agent.sh # カセット再生（tmux セッション作成も担当）
│ ├── cli-scene.sh # contract-verify の中身（隔離 CLI で実ゲートを回す）
│ ├── record-scenes.ts # Playwright をライブラリとして使うシーン録画
│ ├── terminal-scene.ts # tmux pane の収録（ANSI→HTML→PNG→webm）
│ ├── stills.ts # LP / README 用の静止画 5 点（予算ゲートつき）
│ ├── storyboard.ts # 絵コンテの検証と尺の機械算出（YAML サブセット）
│ ├── render-overlays.ts # テロップ／カード／コードカードを HTML から PNG 化
│ └── compose.sh # ffmpeg 合成 + 尺検証ゲート
├── storyboard/
│ ├── default.yaml # 文言を編集する唯一の場所
│ ├── contract-verify.yaml # 契約 → 検証の 30 秒（code card + terminal シーン）
│ └── code/ # code card が読む実ファイル（絵コンテの配下に閉じる）
├── templates/
│ ├── telop.html # 画面下部のテロップ帯（透過 PNG）
│ ├── card.html # タイトル／アウトロカード（不透過 PNG）
│ ├── code-card.html # code card（等幅・行番号つき。card.html と同じ地色）
│ └── terminal.html # tmux pane の組版（常時ダーク）
└── fixtures/
└── claude-session-sample.cast # 採取済みカセット（テキスト。コミット可）
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.
- fixtures/claude-session-sample.cast 17 KB
- scripts/cli-scene.sh 18 KB runs code
- scripts/compose.sh 12 KB runs code
- scripts/demo-video.sh 9.3 KB runs code
- scripts/env-down.sh 7.4 KB runs code
- scripts/env-up.sh 16 KB runs code
- scripts/fake-agent.sh 9.5 KB runs code
- scripts/record-scenes.ts 56 KB runs code
- scripts/render-overlays.ts 9.0 KB runs code
- scripts/stills.ts 16 KB runs code
- scripts/storyboard.ts 28 KB runs code
- scripts/terminal-scene.ts 19 KB runs code
- storyboard/code/dark-mode.contract.yaml 317 B
- storyboard/code/verify.yaml 134 B
- storyboard/contract-verify.yaml 1.6 KB
- storyboard/default.yaml 1.9 KB
- templates/card.html 1.4 KB
- templates/code-card.html 3.4 KB
- templates/telop.html 2.1 KB
- templates/terminal.html 3.1 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.
- 5d ago First seen · 425 lines · 84 tokens per session scan A 1ff6d9f69629
demo-video is a skill published in the GitHub repository Kewton/CommandMate (39 stars, last pushed yesterday), licensed MIT. It adds 84 tokens to every session and 12,011 once invoked, about $0.0004 per session on Opus 5. 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 2026-08-30.
Other skills, from other repositories
aoe
Use when launching, monitoring, or controlling AI coding agents (Claude Code, Codex, OpenCode, etc.) in tmux via Agent of Empires (aoe). Covers creating sessions, capturing agent output, running parallel worktree agents, and organizing work into groups and profiles. Prefer aoe over raw tmux for agent management.
aoe
Manage AI coding agent sessions via Agent of Empires (aoe).
verify
Drive CrowTelemetry's OTLP ingest end-to-end — boot the real receiver, POST OTLP JSON with curl, inspect the SQLite db.
crow-show-image
Surface an image you've generated (a diagram, chart, screenshot, or rendered figure) in Crow's Images panel so the user can see it inline. Use whenever you produce a visual artifact worth showing.
remobi-setup
Full interactive onboarding for remobi — the mobile terminal overlay for tmux. Checks prerequisites, inspects tmux config, interviews the user about their workflow, generates a validated remobi.config.ts, suggests tmux mobile optimisations, and walks through deployment. Use this skill whenever someone asks to set up…
build-and-verify
Build, test, and end-to-end verify the Multiplex visionOS/iPadOS SSH-tmux terminal app. Use this whenever you need to compile the app, run its unit tests, regenerate the Xcode project after editing project.yml or adding/ removing source files, or confirm a change works in the real app on the visionOS or iPad…