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 All-The-Vibes/ShowOff --skill figureoutgit clone --depth 1 https://github.com/All-The-Vibes/ShowOffWrote 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/all-the-vibes/showoff/figureout)<a href="https://agentmods.dev/skills/all-the-vibes/showoff/figureout"><img src="https://agentmods.dev/badge/skills/all-the-vibes/showoff/figureout/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/all-the-vibes/showoff/figureout"><img src="https://agentmods.dev/badge/skills/all-the-vibes/showoff/figureout.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 | $0.00167 | $0.02228 |
| Opus 5 | $0.00084 | $0.01114 |
| Sonnet 5 | $0.00033 | $0.00446 |
| Haiku 4.5 | $0.00017 | $0.00223 |
Grade A, and why
figureout scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
!node "${CLAUDE_SKILL_DIR}/scripts/project-context.mjs"
figureout
Turn a public video URL or a local video file into representative frames plus a timestamped transcript, then answer grounded questions about it. You run the bundled Node scripts, Read every printed frame so you actually see the footage, and cite MM:SS timestamps for every claim. You never publish and never upload the video itself.
The injected line above prints a compact JSON snapshot of the current project: working
directory, platform, whether ffmpeg, ffprobe, and yt-dlp resolve on PATH, the
detected Whisper backend and whether a key is set, and any prior figureout-output\ runs.
Read it first; it tells you whether setup is ready before you invoke the pipeline.
Setup preflight
Before the first run, sense readiness. Run:
node "${CLAUDE_SKILL_DIR}/scripts/setup.mjs" --json
Branch on the status field:
status value |
Meaning | Action you take |
|---|---|---|
ready |
Binaries present, and either captions-only use is fine or a Whisper key is set | Proceed to invocation. |
needs_install |
One or more of ffmpeg, ffprobe, yt-dlp missing from PATH |
Show the user the missing binaries and OS install hints from setup; do not invoke the pipeline until installed. |
needs_key |
Binaries present but no Whisper key | Proceed for caption-backed videos. If the target has no captions and the user wants a transcript, use AskUserQuestion to offer: set a key, or continue frames-only with --no-whisper. |
needs_install_and_key |
Binaries missing and no key | Resolve binaries first (see setup), then handle the key as in needs_key. |
For a silent gate in a script, use --check, which prints nothing and sets the exit code:
0 ready, 2 missing binaries, 3 missing key, 4 both. To scaffold the config and
print OS-specific install hints, run node "${CLAUDE_SKILL_DIR}/scripts/setup.mjs" install.
What ships with it
13 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.
- references/pipeline.md 4.0 KB
- references/setup.md 3.2 KB
- references/showoff-bridge.md 2.5 KB
- references/transcription.md 2.8 KB
- scripts/config.mjs 4.4 KB runs code
- scripts/figureout.mjs 21 KB runs code
- scripts/frames.mjs 16 KB runs code
- scripts/project-context.mjs 3.9 KB runs code
- scripts/setup.mjs 7.4 KB runs code
- scripts/showoff-bridge.mjs 3.8 KB runs code
- scripts/transcribe.mjs 4.6 KB runs code
- scripts/whisper.mjs 9.7 KB runs code
- templates/analysis-report.md 704 B
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.
- 9d ago First seen · 170 lines · 167 tokens per session scan A 7d6f0c8f707b
figureout is a skill published in the GitHub repository All-The-Vibes/ShowOff (5 stars, last pushed 1mo ago), licensed MIT. It adds 167 tokens to every session and 2,228 once invoked, about $0.0008 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
verticals
AI-native vertical video engine with niche intelligence. Takes a one-line topic and a niche profile, and outputs a finished YouTube Short/Reel/TikTok with AI-generated b-roll, voiceover, burned-in captions, background music, and thumbnail. Supports multiple LLM providers (Claude, Gemini, GPT, Ollama), TTS providers…
pptx
Criar, editar e analisar apresentacoes PowerPoint (.pptx). Trigger quando usuario quer criar slides, pitch deck, editar apresentacao existente, extrair conteudo de .pptx.
gerar-imagem
Gera ou edita imagens com IA via OpenAI gpt-image-1 (default, funcionando) ou Nano Banana/Gemini (aguarda billing). Use quando o usuário pedir para gerar, criar, desenhar ou editar imagem, ilustração, logo, ícone, mockup visual, asset gráfico, foto sintética ou variação de imagem existente.
product-story-pptx
A structured workflow for creating and revising product presentation PowerPoint files with a planned story, visual layouts, editable diagrams, generated assets, and quality checks.
app-store-screenshots
Capture App Store / TestFlight screenshots from the iOS Simulator at native resolution, downscale to every required display size, and upload to App Store Connect via helm-asc. Use when asked to take/produce/refresh App Store screenshots, marketing screenshots, or screenshots for custom product pages.
c-video
Download videos, extract audio, convert formats, and clip segments using yt-dlp and ffmpeg. Supports YouTube, Vimeo, and hundreds of other sites.