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 tavus-replica-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/tavus-replica-video)<a href="https://agentmods.dev/skills/calesthio/generative-media-skills/tavus-replica-video"><img src="https://agentmods.dev/badge/skills/calesthio/generative-media-skills/tavus-replica-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/tavus-replica-video"><img src="https://agentmods.dev/badge/skills/calesthio/generative-media-skills/tavus-replica-video.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 272 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
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 | $0.00059 | $0.05320 |
| Opus 5 | $0.00030 | $0.02660 |
| Sonnet 5 | $0.00012 | $0.01064 |
| Haiku 4.5 | $0.00006 | $0.00532 |
Grade A, and why
tavus-replica-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 — 409 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tavus replica video production
Use this skill when a task involves Tavus avatars, replicas, faces, PALs/personas, generated talking-head files, real-time conversational video agents, or Tavus-powered lip-synced presenter output.
Documented facts in this skill were checked against official Tavus docs, policies, and pricing on 2026-07-10. Treat API names, model names, plan limits, stock replica availability, language support, pricing, and policy wording as volatile; verify them again before committing spend, launch scope, or regulated workflows.
The current Tavus object model
Tavus docs now use:
- Face: the on-screen likeness and voice rendered by Phoenix. A custom face can be trained from a video URL or image URL. Stock faces/replicas can also be used.
- PAL: behavior, knowledge, pipeline, LLM/TTS/perception/turn-taking/conferencing configuration for real-time CVI.
- Conversation: a real-time video call/session with a PAL and face.
Legacy terms still appear in APIs and production requests:
replica_idin the Video Generation API is the Face ID returned by/v2/faces./v2/personas,persona_id,/v2/replicas,default_replica_id, and related aliases may still exist for backward compatibility.
Do not force the user to rename their mental model. Translate cleanly: "your Tavus replica ID is the face ID needed by the video endpoint."
Choose the Tavus path first
Pick the path by deliverable, not by habit.
- One-way talking-head file: use async Video Generation. Call
POST /v2/videoswithreplica_idplus eitherscriptoraudio_url; pollGET /v2/videos/{video_id}untilready, then capturedownload_url,stream_url, andhosted_url. - Interactive AI human / live agent: use CVI. Create or select a Face, create or select a PAL, then call
POST /v2/conversationswithface_idandpal_id. - Need a new likeness: create/train the Face first with
POST /v2/faces. Use video training for highest fidelity and customer-facing work; use image training when speed/setup simplicity matters more than personalized expressions. - Need exact audio, approved voiceover, or non-Tavus TTS: use the async Video API with
audio_urlrather thanscript, or use CVI echo mode when the app supplies utterances in real time. - Need an existing speaker video re-lip-synced: Tavus Terms define LipSync as a platform feature, but do not assume an endpoint or schema from memory. Check the current OpenAPI contract before promising this path. If no documented endpoint is available, route through async avatar generation with
audio_urlor choose another documented lip-sync provider.
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 · 409 lines · 59 tokens per session scan A a836123b0661
tavus-replica-video is a skill published in the GitHub repository calesthio/generative-media-skills (170 stars, last pushed 2mo ago), licensed MIT. It adds 59 tokens to every session and 5,320 once invoked, about $0.0003 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…