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 siarhei-belavus/agent-public --skill video-productiongit clone --depth 1 https://github.com/siarhei-belavus/agent-publicWrote 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/siarhei-belavus/agent-public/video-production)<a href="https://agentmods.dev/skills/siarhei-belavus/agent-public/video-production"><img src="https://agentmods.dev/badge/skills/siarhei-belavus/agent-public/video-production/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/siarhei-belavus/agent-public/video-production"><img src="https://agentmods.dev/badge/skills/siarhei-belavus/agent-public/video-production.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 | $0.00051 | $0.01660 |
| Opus 5.5 | $0.00020 | $0.00664 |
| Sonnet 5.5 | $0.00010 | $0.00332 |
| Haiku 4.5 | $0.00005 | $0.00166 |
Grade A, and why
video-production 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 2mo 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 — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.
User input (must consider):
$ARGUMENTS
Objective
Transform the brief into a production-ready script a video editor can execute in CapCut (or similar): exact timings, track plan, assets, and steps. Min tokens, max signal.
Operating Rules (hard)
- Ask ≤ 8 clarification questions total.
- Ask exactly 1 question per message.
- Do not ask what the user already specified.
- Stop questions when: critical gaps filled OR user says “proceed/done/enough”.
- After questions: output Configuration Summary + ask for confirmation (“Generate script now? yes/adjust”).
- On confirmation: output the full script in Markdown (content only; also suggest a filename).
Precision Standards
- Timestamp format:
M:SS.s(round to 0.1s). - Use absolute times across the whole video.
- Every timeline element must have: Track, Start, End, Duration.
- Prefer tables over prose.
- Per scene: include an ASCII track timeline if the scene has overlapping elements (text+SFX+VO), otherwise omit.
CapCut Reality / Non-hallucination
- Menu/UI varies by platform/version.
- If a path is uncertain, write:
Path (may vary): …and addSearch keyword: “…”.
- Never invent ultra-specific UI labels or pixel-perfect coordinates.
Critical clarifications to enforce (prevent common errors)
- Transitions = between 2 clips that touch/overlap on the timeline.
- Animations = on a single clip/layer (IN / COMBO / OUT).
- Font size (pt) ≠ text box size.
Track Convention (fixed)
- Visual Track 1 = base/background (bottom). Track 2+ = overlays (higher = on top).
- Audio A1 = music bed, A2 = SFX, A3 = voiceover (adjust if user prefers).
Step 1 — Parse brief (internal)
Extract (don’t over-explain): purpose, audience, platform hints, duration hints, style references, required topics, constraints.
Step 2 — Gap check → question queue (internal)
Prioritize asking only what blocks a correct script:
- Target duration
- Primary platform / aspect ratio
- Audience + tone/style
- Key message + CTA
- Voiceover approach
- Brand constraints (logo/colors/fonts)
- Budget tier (assets)
- Any must-include footage (screen recording, talking head, stock)
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.
- 2mo ago First seen · 216 lines · 51 tokens per session scan A da535b0ae064
video-production is a skill published in the GitHub repository siarhei-belavus/agent-public (2 stars, last pushed 5mo ago), licensed MIT. It adds 51 tokens to every session and 1,660 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 2026-08-31.
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…