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 thewolffish/wolffish-app --skill videogit clone --depth 1 https://github.com/thewolffish/wolffish-appWrote 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/thewolffish/wolffish-app/video)<a href="https://agentmods.dev/skills/thewolffish/wolffish-app/video"><img src="https://agentmods.dev/badge/skills/thewolffish/wolffish-app/video/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/thewolffish/wolffish-app/video"><img src="https://agentmods.dev/badge/skills/thewolffish/wolffish-app/video.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00049 | $0.03532 |
| Opus 5 | $0.00024 | $0.01766 |
| Sonnet 5 | $0.00010 | $0.00706 |
| Haiku 4.5 | $0.00005 | $0.00353 |
Grade A, and why
video 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 — 257 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Video generation (MiniMax H3)
Runs on the key saved under Settings → Services → Video generation. That
is a SEPARATE field from the MiniMax chat provider: the same MiniMax key
value works in both, but the app never copies one into the other, so a user
with MiniMax configured as a chat brain may still have video generation
unconfigured. When in doubt call video_check before generating — it is free
and tells you exactly what to say if something is missing.
One model, four modes, all through video_generate:
| Mode | Inputs | Notes |
|---|---|---|
| Text-to-video | prompt only |
ratio required (defaults to 16:9) |
| Image-to-video | first_frame and/or last_frame |
output adapts to the image — omit ratio |
| Reference | reference_images / reference_videos / reference_audios |
keeps subject, motion, or voice consistent |
| Mixed | any combination of the above | ≤12 media items total |
Output: H.264 mp4 with an AI-generated soundtrack, 24 fps, 768P (≈1344×768)
or 2K (≈2560×1440), 4–15 s. Saved automatically under
generations/video/conv-<conversation>/ in the workspace — never re-download it.
Placing the user's media (you do this, not the UI)
There is no picker that tells the app which link is the first frame and which is the voice reference. The user writes a message; you read the media out of it and put every item in the right parameter. Do this before anything else in a video turn:
- Collect every media reference in the request — attached files (their
absolute paths come in the
<attachments>note), https URLs written in the prose, and paths named earlier in the conversation that they are pointing back at ("use the logo from before"). - Classify each one by what it IS. Extension first (
.png→ image,.mp4→ video,.mp3/.wav→ audio), then the sentence around it — "start on this", "her voice", "match this camera move". An attachment'stype=field settles it outright. - Assign by what it is FOR, which the wording tells you:
What ships with it
1 file 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.
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 · 257 lines · 49 tokens per session scan A 6cd8b4c122a0
video is a skill published in the GitHub repository thewolffish/wolffish-app (5 stars, last pushed 2d ago), licensed MIT. It adds 49 tokens to every session and 3,532 once invoked, about $0.0002 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
make-viral-video
Build a short news-explainer video tuned for shareability. One striking moment per video; real fetched assets; self-heal validation; pluggable TTS (Gemini-free default, OpenAI fallback).
image-generation
Generate and edit images using Gemini Flash Image, and generate videos using Veo. Supports text-to-image, image editing, text-to-video, and image-to-video.
gemini-tts
Render text to mp3 via Google Gemini Flash TTS. Free-tier eligible (1500 req/day). Use for video narration, demo voiceovers, audio notes. Parallels openai-tts; default for make-viral-video.
audio-transcribe
Transcribes audio files and voice notes to text via Gemini 2.5-flash. Integrates with Slack, Discord, and Telegram bridges so voice clips surface as readable text in tasks.
screen-record
Start or stop a screen recording of the Mac via ffmpeg. Use when the user asks to record/capture their screen to a video file (a demo, a repro, a walkthrough) — not for a single still screenshot (use macos-tools screen capture for that).
openai-tts
Render text to mp3 via OpenAI's tts-1-hd. Use for video narration, demo voiceovers, audio notes.