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 calesthio/generative-media-skills --skill google-veogit clone --depth 1 https://github.com/calesthio/generative-media-skillsWrote 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/calesthio/generative-media-skills/google-veo)<a href="https://agentmods.dev/skills/calesthio/generative-media-skills/google-veo"><img src="https://agentmods.dev/badge/skills/calesthio/generative-media-skills/google-veo/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/calesthio/generative-media-skills/google-veo"><img src="https://agentmods.dev/badge/skills/calesthio/generative-media-skills/google-veo.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 | $0.00075 | $0.08915 |
| Opus 5 | $0.00037 | $0.04457 |
| Sonnet 5 | $0.00015 | $0.01783 |
| Haiku 4.5 | $0.00007 | $0.00891 |
Grade C, and why
google-veo scanned grade C 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 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.
Instruction-override phrasinghighPrompt injection
Text telling the model to disregard its earlier instructions or safety rules is the shape of a prompt injection, whoever wrote it.
Do not use negative prompts to bypass safety filters or request disallowed content indirectly. How it starts
The opening of the file, as written. The whole thing — 504 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Produce with Google Veo
Treat a Veo request as a shot-production job, not as a generic text completion. Lock the access route, model, input mode, shot contract, and delivery constraints before generating.
Read evidence labels correctly
- Documented means a current first-party Google API document, model card, policy, or technical report says it.
- First-party evaluation means Google measured or reported it; do not restate it as independent superiority.
- Production heuristic means a practical operating recommendation derived from the documented interface and common shot-production constraints. It is not a provider guarantee.
- Documentation gap means Google's current pages conflict or a generic schema exposes a field that the selected model card does not support. Run a low-cost preflight instead of guessing.
All volatile facts in this skill were verified 2026-07-09. Recheck model lifecycle, quotas, pricing, regional availability, and terms before a paid production run.
Confirm that Veo is the right Google video model
Use Veo for a shot-generation workflow that specifically benefits from Veo's first/last-frame control, asset references, extension, established publisher-model integration, or Veo-native audio contract. Do not use this skill for video understanding or transcription.
Documented current product guidance: Google's Gemini API video overview now recommends Gemini Omni Flash as the default for multimodal coherence, character consistency, factual accuracy, and conversational multi-turn video editing; it positions Veo 3.1 for capabilities such as scene extension, last-frame control, and legacy pipeline integration. Treat that as provider routing guidance, not independent quality proof. If the request is simply “make a video” and does not need a Veo-specific control, compare the current Google video models before committing. See Video generation in the Gemini API.
Start with the route, because “Veo 3.1” is not one API contract
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 · 504 lines · 75 tokens per session scan C ae9ed459097c
google-veo is a skill published in the GitHub repository calesthio/generative-media-skills (171 stars, last pushed 2mo ago), licensed MIT. It adds 75 tokens to every session and 8,915 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 1 finding (instruction-override phrasing). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
cliptalk-cover-director
Produces evidence-backed cover candidates and reviewable cover variants for a ClipTalk video. Use when the user asks for a cover, poster frame, thumbnail, or multiple cover directions; do not use for timeline editing or social-video reframing.
cliptalk-smart-reframe
Creates a subject-aware, time-varying crop track and a review-only social-format preview from an accepted ClipTalk cut. Use for automatic vertical, square, or portrait reframing; do not use for a fixed manual crop or before content editing is accepted.
cliptalk-content-extractor
Locates and assembles source passages matching a semantic request. Use for extracting explanations, topics, quotes, demonstrations, or other specifically described content.
cliptalk-interview-editor
Produces a coherent interview edit by combining speaker discovery, topic selection, dialogue context, cleanup, subtitles, and preview. Use for interviews, podcasts, testimonials, or question-and-answer recordings.
cliptalk-shortform-hook-director
Finds and assembles a reviewable short-form cut with a strong opening hook. Use for Shorts, Reels, social clips, talking-head cutdowns, or requests for a punchier opening.
cliptalk-social-reframe-exporter
Creates a review-only 9:16, 4:5, 1:1, or 16:9 version from an existing accepted ClipTalk cut, then checks the rendered preview. Use only when a cut already exists and the user asks to adapt it for Shorts, Reels, Douyin, Xiaohongshu, WeChat Channels, or square feeds; do not use when the user still needs content found…