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 crealwork/ai-marketing-kit --skill youtube-edit-kitgit clone --depth 1 https://github.com/crealwork/ai-marketing-kitWrote 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/crealwork/ai-marketing-kit/youtube-edit-kit)<a href="https://agentmods.dev/skills/crealwork/ai-marketing-kit/youtube-edit-kit"><img src="https://agentmods.dev/badge/skills/crealwork/ai-marketing-kit/youtube-edit-kit/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/crealwork/ai-marketing-kit/youtube-edit-kit"><img src="https://agentmods.dev/badge/skills/crealwork/ai-marketing-kit/youtube-edit-kit.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 | $0.00100 | $0.01217 |
| Opus 5 | $0.00050 | $0.00609 |
| Sonnet 5 | $0.00020 | $0.00243 |
| Haiku 4.5 | $0.00010 | $0.00122 |
Grade A, and why
youtube-edit-kit 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 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.
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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
YouTube Edit Kit
One source video in → a clean YouTube cut out: silence + disfluency cuts, burned corrected captions, SRT + chapters, and optional vertical shorts. Free and local — ffmpeg + faster-whisper, no API key.
Every gate below is MANDATORY, in order. Skipping a gate or a self-test is a failure, not a shortcut. Violating the letter of these rules is violating their spirit. Each rule exists because an agent already broke it in production.
Gates (run in order)
digraph gates {
"G0 Setup check" -> "G1 Transcribe + read" -> "G2 Strategy confirm" -> "G3 Cut + render" -> "G4 Captions" -> "G5 Shorts (optional)" -> "G6 Self-review";
"G0 Setup check" -> "STOP: give user references/SETUP.md installs, wait" [label="tool missing"];
"G2 Strategy confirm" -> "WAIT for user OK" [label="no approval"];
}
G0 — Setup. Verify EVERY tool in references/SETUP.md with its verify command. Missing → hand the user that file's install instructions and wait. Never substitute a "similar" tool.
G1 — Transcribe. references/EDIT.md §1: word-level verbatim, cached per source, then READ the entire packed transcript. Cut decisions come from reading.
G2 — Strategy confirm. Present cut approach + estimated length (+ shorts count and hook list if applicable) and WAIT for the user's OK. Rendering before approval is a violation, not initiative.
G3 — Cut. references/EDIT.md §3–5: EDL (silence + disfluency) → per-segment render → lossless concat.
G4 — Captions. references/CAPTIONS.md — read it before writing any cue. Term review first (scan_terms.py + reading; YOU are the AI reviewer for proper nouns/jargon/onomatopoeia — ask the user what you can't verify), then corrections dictionary, output-timeline mapping, burn LAST.
G5 — Shorts. references/SHORTS.md — moment selection, hook titles, first-frame rule, blocking self-tests.
G6 — Self-review. references/EDIT.md §7: look at frames, check duration, spot-check sync. If you wouldn't ship it, don't present it.
What ships with it
15 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.
- BOOTSTRAP.md 1.2 KB
- LICENSE 1.0 KB
- llms.txt 2.8 KB
- README.md 3.8 KB
- references/CAPTIONS.md 4.7 KB
- references/EDIT.md 4.4 KB
- references/SETUP.md 2.3 KB
- references/SHORTS.md 3.6 KB
- scripts/gen_edl.py 4.3 KB runs code
- scripts/gen_shorts.py 8.5 KB runs code
- scripts/gen_srt.py 4.3 KB runs code
- scripts/render_cut.py 3.3 KB runs code
- scripts/scan_fillers.py 3.8 KB runs code
- scripts/scan_terms.py 5.2 KB runs code
- scripts/transcribe.py 3.0 KB runs code
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 First seen · 94 lines · 100 tokens per session scan A 4f05aae0e86d
youtube-edit-kit is a skill published in the GitHub repository crealwork/ai-marketing-kit (18 stars, last pushed 1mo ago), licensed MIT. It adds 100 tokens to every session and 1,217 once invoked, about $0.0005 per session on Opus 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 2026-08-30.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.