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 skillmds/skillmd --skill kinetic-multicamgit clone --depth 1 https://github.com/skillmds/skillmdWrote 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/skillmds/skillmd/kinetic-multicam)<a href="https://agentmods.dev/skills/skillmds/skillmd/kinetic-multicam"><img src="https://agentmods.dev/badge/skills/skillmds/skillmd/kinetic-multicam/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/skillmds/skillmd/kinetic-multicam"><img src="https://agentmods.dev/badge/skills/skillmds/skillmd/kinetic-multicam.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 | $0.00130 | $0.04881 |
| Opus 5.5 | $0.00052 | $0.01952 |
| Sonnet 5 | $0.00026 | $0.00976 |
| Haiku 4.5 | $0.00013 | $0.00488 |
Grade A, and why
kinetic-multicam 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 4d 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.
This is a copy
100% identical to kinetic-multicam — 1 line 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 — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/kinetic-multicam: One Take → Kinetic Supers + Camera Snaps
Overview
Turns ONE real talking-head take into the proven video-to-video prompt — best on Seedance 2.0 Fast (Google Omni runs it but with clearly weaker results; don't recommend it) — that adds two things to the untouched footage: split-second visible camera whips — motion-blurred moves that lock into stable frames on arrival — and bold kinetic supers (motion-graphics text, NOT captions) synced to the speech beats. The prompt preserves the uploaded source video — face, room, audio, lip sync all frozen. It does NOT describe or regenerate the scene.
Core principle: the template is frozen; only three zones ever change — the [Xs] timestamps (always), the "[TEXT]" supers (cut from the words actually spoken; not every block gets one — supers follow their own density rule), and the camera position descriptions (only if the user asks).
Sibling skill, not the same skill: /multicam does hard cuts with no text. NEVER mix the two templates — this one never says "hard cut", uses From [Xs] to [Xs] ranges (not * At [Xs]:), and carries its own typography direction. The transition itself is the differential: /multicam CUTS between angles; this skill TRAVELS between them with a visible motion-blurred whip.
Input
Local video file only (the user's own footage). If the user only has a URL (an Instagram link, a Drive link), ask them to save the video as a local file first. If more than one video could be "the video", ask — never guess via ls -t.
Step 0 — Preflight (first run, or on any missing-tool error)
python "<this skill's base directory>/scripts/check_env.py"
It verifies Python 3.8+, ffmpeg, ffprobe and Whisper, and for anything missing it prints what the tool is FOR plus the exact install command for the user's OS. It never installs anything itself — relay what is missing, ask the user for permission, install, then re-run the check. If everything passed recently in this session, skip straight to Step 1.
What ships with it
4 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.
- 4d ago First seen · 229 lines · 130 tokens per session scan A 6ec070659b96
kinetic-multicam is a skill published in the GitHub repository skillmds/skillmd (1 stars, last pushed yesterday), licensed MIT. It adds 130 tokens to every session and 4,881 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to kinetic-multicam, differing in 1 line, and is treated as a copy.
Other skills, from other repositories
slopless
Use Slopless to review English Markdown for deterministic AI and human slop signals, including vague phrasing, formulaic prose, weak rhythm, filler, and cliches.
suiko
A Japanese writing and review workflow for checking whether text sounds uniform, translated, unnatural, or difficult to read. It supports writing and editing documents such as reports, guides, meeting notes, proposals, and emails.
poly-lint-and-format
Running poly lint / poly fmt — --fix, --format pretty|json|toon, --exclude, --config, exit codes, inline suppression, and the check → read-json → fix → re-check loop.
poly-orchestrator
Use poly as the single lint/format gate instead of invoking ruff/oxlint/rustfmt directly — one poly.toml, poly hooks install, poly migrate, CI via the Goldziher/poly setup Action.
poly-mcp
The poly MCP server — the eleven tools and which are read-only vs mutating, the paths/exclude/config/format params, async Tasks for the whole-project phase, and the isError contract.
poly-tiers-and-scope
Five mechanisms decide what actually inspects a file (crates/poly-core/src/registry.rs).