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 jykim/claude-obsidian-skills --skill remotion-vloggit clone --depth 1 https://github.com/jykim/claude-obsidian-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/jykim/claude-obsidian-skills/remotion-vlog)<a href="https://agentmods.dev/skills/jykim/claude-obsidian-skills/remotion-vlog"><img src="https://agentmods.dev/badge/skills/jykim/claude-obsidian-skills/remotion-vlog/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/jykim/claude-obsidian-skills/remotion-vlog"><img src="https://agentmods.dev/badge/skills/jykim/claude-obsidian-skills/remotion-vlog.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 | $0.00097 | $0.02981 |
| Opus 5.5 | $0.00039 | $0.01192 |
| Sonnet 5.5 | $0.00019 | $0.00596 |
| Haiku 4.5 | $0.00010 | $0.00298 |
Grade A, and why
remotion-vlog 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 1mo 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 — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Remotion Vlog
Turn raw outing footage into a short story that remains easy to inspect and revise as a Remotion project. Preserve the original media and treat the user's editorial exclusions as hard requirements.
Interpret the request
- Resolve the requested camera or mounted volume, date scope, output folder, title, people, place, and render gate from the user's messages. Treat “today” using the user's local timezone.
- Inspect files and metadata before choosing clips. Do not mix in footage outside the requested event merely because it is adjacent on disk.
- If the destination or event can be inferred confidently from the footage and request, proceed. Ask only when two materially different events remain plausible.
- Prefer an existing Remotion project in the requested output folder. Create a new one only when none exists.
- When available, load
remotion-best-practicesbefore editing Remotion code. Use a speech-cleaning workflow only when spoken content determines the cuts.
Protect the footage
- Never modify, rename, move, or delete camera originals.
- Put selected, trimmed, consistently encoded proxies under the Remotion project's
public/tree. Keep temporary transcripts and contact sheets outside the project unless the user asks to retain them. - Preserve unrelated user changes in an existing project.
- If the user wants to eject a camera or card, copy only the selected source originals when capacity allows, then verify every destination against its source with a byte comparison or checksum before saying it is safe to eject. If capacity only permits proxies, say explicitly that full originals were not preserved locally.
Verified import and automatic eject
When the user asks to import footage and automatically eject the camera or card:
- Resolve the exact date or event scope and choose a dedicated
media-source/<event-date>/originalsdestination outsidepublic/. - Check destination capacity before copying and leave enough free space for the edit. Prefer selected full-resolution originals plus relevant camera stills. Camera-generated LRF proxies are optional when verified local edit proxies already exist. If the full date set does not fit, state what will and will not be imported before proceeding.
- Copy without changing the source files. Verify the destination file count and total bytes, then perform a byte comparison or SHA-256 comparison for every copied file.
- Eject only after all requested copies pass verification. Target the resolved mounted volume explicitly, confirm the eject command succeeds, and confirm that the mount path is gone.
- On a copy, capacity, or verification failure, keep the device mounted and report the exact blocker. Never describe proxy-only storage as a full original import.
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.
- 1mo ago First seen · 165 lines · 97 tokens per session scan A 4f5262b24d85
remotion-vlog is a skill published in the GitHub repository jykim/claude-obsidian-skills (50 stars, last pushed 1mo ago), licensed MIT. It adds 97 tokens to every session and 2,981 once invoked, about $0.0004 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 2026-09-22.
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…