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 bravew/trove --skill trove-product-videogit clone --depth 1 https://github.com/bravew/troveWrote 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/bravew/trove/trove-product-video)<a href="https://agentmods.dev/skills/bravew/trove/trove-product-video"><img src="https://agentmods.dev/badge/skills/bravew/trove/trove-product-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/bravew/trove/trove-product-video"><img src="https://agentmods.dev/badge/skills/bravew/trove/trove-product-video.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 | $0.00050 | $0.01006 |
| Opus 5.5 | $0.00020 | $0.00402 |
| Sonnet 5.5 | $0.00010 | $0.00201 |
| Haiku 4.5 | $0.00005 | $0.00101 |
Grade A, and why
trove-product-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 8d 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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product video production
Use this skill for a product promo built around a real product interface. For ordinary editing or transcoding of existing footage, use trove-ffmpeg directly. This skill owns direction, storyboard, capture, Remotion implementation, and the product-video handoff.
Choose a mode
Start with a minimal, read-only inspection of the product and the user's stated goals. Do not start its server, capture pages, inspect live data, install dependencies, or modify files during this inspection. Then select one of three modes:
- Template adaptation when the user names the video-shotcraft template or wants its established structure. Locate the user's checkout and follow its template branch.
- Autonomous creation when the user asks the agent to decide the creative direction and make the promo. Record the evidence and decisions as you proceed.
- Guided co-creation when the user wants to participate in visual direction, storyboard, or other creative decisions.
When the user has named a mode, honor it without asking them to choose again. Otherwise recommend the best fit from their request and product evidence. Ask only when an unresolved decision would materially change the result. Read modes.md and pipeline.md before production.
Production rules
- Reproduce a real interface with genuine screenshots from the user's product. Do not redraw a live UI as invented markup and present it as a capture.
- Extract colors, typography, spacing, surfaces, and motion character from the product. Use the same design tokens across screens, transitions, and effects.
- Before any capture, identify private, customer, personal, internal, credential, or live data. Use a safe frozen dataset or mask it. Capture only after sensitive content is protected.
- Follow stages 0–7 and the default energy arc in pipeline.md. Keep a clear hold after important information lands.
- Make renders deterministic. Do not use wall-clock time, unseeded randomness, or other changing inputs in frame calculations.
- A vertical version is a new composition designed for a 9:16 frame. Re-layout interface elements and protect readability. Never make it by cropping the finished 16:9 render.
What ships with it
3 files 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.
- 8d ago First seen · 44 lines · 50 tokens per session scan A a44bba4a8577
trove-product-video is a skill published in the GitHub repository bravew/trove (10 stars, last pushed yesterday), licensed MIT. It adds 50 tokens to every session and 1,006 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-09.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…