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 heygen-avatar-videogit 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/heygen-avatar-video)<a href="https://agentmods.dev/skills/calesthio/generative-media-skills/heygen-avatar-video"><img src="https://agentmods.dev/badge/skills/calesthio/generative-media-skills/heygen-avatar-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/calesthio/generative-media-skills/heygen-avatar-video"><img src="https://agentmods.dev/badge/skills/calesthio/generative-media-skills/heygen-avatar-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 | $0.00083 | $0.04995 |
| Opus 5 | $0.00042 | $0.02498 |
| Sonnet 5 | $0.00017 | $0.00999 |
| Haiku 4.5 | $0.00008 | $0.00500 |
Grade A, and why
heygen-avatar-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 — 364 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HeyGen avatar video production
Use this skill when the production path is HeyGen and the deliverable involves an AI presenter, digital twin, photo avatar, studio avatar, prompt-composed avatar clip, or real-time streaming avatar. Treat HeyGen as both a creative video tool and a likeness-handling system: lock consent, identity rights, script intent, voice rights, and output custody before generation.
Facts below were verified from official HeyGen documentation and policy pages on 2026-07-10. Recheck the linked docs for volatile fields such as prices, engine support, endpoint shapes, limits, status values, moderation policy, and plan entitlements before a paid run.
Choose the right HeyGen route
Prefer the most controllable API that still fits the brief.
- Use Video Agent (
POST /v3/video-agents) when the user wants a complete avatar video from a natural-language brief and accepts HeyGen choosing or composing the script, avatar, voice, and visual style. It is the fastest exploration path and supports one-shot generation or interactive chat-style iteration, but it gives less deterministic scene control. - Use Direct Video (
POST /v3/videos,type: "avatar") when the script, avatar look, voice, aspect ratio, background, captions, watermark, output format, or motion prompt must be explicit and repeatable. This is the default for production pipelines, personalized campaigns, compliance-reviewed scripts, and brand-controlled spokesperson videos. - Use Cinematic Avatar (
POST /v3/videos,type: "cinematic_avatar") only when the output is a short prompt-composed cinematic shot with 1-3 avatar looks and no spoken script. Do not choose it for normal talking-head narration. - Use Avatar Realtime (
POST /v3/avatar-realtime) when the user needs a live HLS stream of an avatar speaking in real time. It is for kiosks, live agents, assistants, and broadcasts where the application owns STT/LLM orchestration. It is not a rendered MP4 workflow. - Use Video Translation or Lipsync APIs for post-hoc localization or replacing audio on existing footage rather than regenerating the whole video when the visual source must be preserved.
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 · 364 lines · 83 tokens per session scan A 9ceaa3f5f940
heygen-avatar-video is a skill published in the GitHub repository calesthio/generative-media-skills (170 stars, last pushed 2mo ago), licensed MIT. It adds 83 tokens to every session and 4,995 once invoked, about $0.0004 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 2026-09-03.
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…