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 PrunaAI/pruna-skills --skill p-video-replacegit clone --depth 1 https://github.com/PrunaAI/pruna-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/prunaai/pruna-skills/p-video-replace)<a href="https://agentmods.dev/skills/prunaai/pruna-skills/p-video-replace"><img src="https://agentmods.dev/badge/skills/prunaai/pruna-skills/p-video-replace/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/prunaai/pruna-skills/p-video-replace"><img src="https://agentmods.dev/badge/skills/prunaai/pruna-skills/p-video-replace.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 | $0.00029 | $0.02267 |
| Opus 5.5 | $0.00012 | $0.00907 |
| Sonnet 5.5 | $0.00006 | $0.00453 |
| Haiku 4.5 | $0.00003 | $0.00227 |
Grade A, and why
p-video-replace scanned grade A 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 10d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
## HTTP (curl) This is a copy
86% identical to video-editing — 180 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prerequisites
Install and load these skills before generating (skip if already in context via @pruna):
| Skill | Description | Install |
|---|---|---|
generation-diversity |
Use when writing any generative prompt — ritual seed, explicit structure, scenario axes, and quality gates before paid API calls. | npx skills add PrunaAI/pruna-skills@generation-diversity -y |
video-prompting |
Use when crafting video or motion prompts for any generative model — dramaturgy, camera, physics-safe motion, frame anchors, and clip chaining. | npx skills add PrunaAI/pruna-skills@video-prompting -y |
pruna-api |
Use before any Pruna or Replicate HTTP call — credentials, upload/poll/download, parallel batches, and agent safety. | npx skills add PrunaAI/pruna-skills@pruna-api -y |
Or install the full suite once: npx skills add PrunaAI/pruna-skills@pruna -y
Follow each skill's Before generating / craft sections — do not restate guide content here.
Agent habit
In the first reply, name `p-video-replace` in backticks, confirm PRUNA_API_KEY (or stop with signup links from pruna-api), then ask for required inputs. Open intake → generation-diversity clarification intake before the first POST. Draft swaps with Prompt craft (dynamic + faithful) — do not paste skill examples. Redirect when When NOT to use fits better.
Prompt craft (dynamic + faithful)
instruction_prompt maps source slots → reference images → preserve-list. Change only what the user asked; keep camera, audio, and unmentioned elements identical.
| Do | Don't |
|---|---|
Formula: name source element → map each ref (first reference, image 2) → preserve-list (walking pace, camera tracking, audio) |
Vague replace the person with no slot mapping |
| Ritual seed before drafting; fresh wording for preserve clauses when the brief allows | Copy this skill's sample (olive coat, navy jacket) when the user described different targets |
| Lock swap intent (character / clothing-only / object / mixed) from the user | Drop preserve-list and hope motion/audio hold |
Show instruction_prompt before POST when wording is not locked |
Silent swap that changes background, cast, or unrequested regions |
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.
- 10d ago Changed a81be0b245da
- 26d ago Changed 526a145e54ce
- 1mo ago Changed ec95ffdeebe7
- 1mo ago Changed 58fba05dde47
- 1mo ago Changed · +2 lines 893a99804a06
- 1mo ago First seen · 155 lines · 29 tokens per session scan A c497724370c9
p-video-replace is a skill published in the GitHub repository PrunaAI/pruna-skills (20 stars, last pushed 11d ago), licensed Apache-2.0. It adds 29 tokens to every session and 2,267 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). It is 86% identical to video-editing, differing in 180 lines, and is treated as a copy.
Other skills, from other repositories
geminigen-ai
Use when unified multimedia API for image generation (nano-banana-pro, imagen-4), video generation (Grok, Veo, Sora), and text-to-speech. Replaces grok-video-generation, seedance, and gemini-image-generator. Use when working with geminigen ai.
paperpod
Use when isolated agent runtime for code execution, live preview URLs, browser automation, 50+ tools (ffmpeg, sqlite, pandoc, imagemagick), LLM inference, and persistent memory — all via CLI or HTTP, no SDK or API keys required. Use when working with paperpod.
ad-creative
Create, iterate, and scale paid ad creative for Google Ads, Meta, LinkedIn, TikTok, and similar platforms. Use when generating headlines, descriptions, primary text, or large sets of ad variations for.
ai-image-realism
Install and use the official AI Image Realism package, pinned by digest, for paid hosted work on the Beatra service.
agentfolio
Skill for discovering and researching autonomous AI agents, tools, and ecosystems using the AgentFolio directory.
gzh-design
A document-formatting skill that turns Markdown, Word files, PDFs, or plain text into HTML that can be pasted into a WeChat public-account editor. WeChat public accounts are publishing pages inside China's WeChat platform.