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 initlabsai/vibekit --skill marketing-contentgit clone --depth 1 https://github.com/initlabsai/vibekitWrote 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/initlabsai/vibekit/marketing-content)<a href="https://agentmods.dev/skills/initlabsai/vibekit/marketing-content"><img src="https://agentmods.dev/badge/skills/initlabsai/vibekit/marketing-content/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/initlabsai/vibekit/marketing-content"><img src="https://agentmods.dev/badge/skills/initlabsai/vibekit/marketing-content.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00117 | $0.01064 |
| Opus 5 | $0.00059 | $0.00532 |
| Sonnet 5 | $0.00023 | $0.00213 |
| Haiku 4.5 | $0.00012 | $0.00106 |
Grade A, and why
marketing-content 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 9d 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
vibekit marketing content
Everything that goes out in public: the copy, the images, the video. One voice across all of it, because a follower sees the tweet and the card in the same scroll — if they sound like different companies, the brand is doing nothing.
Pick your asset
Read the linked file before making the thing; each has the recipe and the failure modes.
| you want | read | make it with |
|---|---|---|
| tweet, thread, dev diary, announcement, reply | references/voice.md |
— |
| promo or demo video of the TUI | references/video.md |
scripts/*.tape + ffmpeg |
| title card between video segments | references/cards.md |
scripts/make-card.sh |
| OG / link-preview image, quote card | references/cards.md |
PNG=1 scripts/make-card.sh |
| lore dossier card (the /lore series) | references/cards.md |
scripts/make-lore-card.sh |
| qt314 animation, GIF loop | references/qt314.md |
scripts/qt314-*.py |
| a still of the TUI | references/cards.md |
a one-line vhs tape |
| colors, fonts, sizes | references/brand.md |
assets/card.css |
Everything visual is HTML → headless chromium → png, then ffmpeg if it moves.
That is one pipeline with different templates, not four pipelines, and it is
why a still and a video card can't drift apart. Never hand-roll an ffmpeg
drawtext card because it looks quicker — it is, and it looks it.
Preflight
Check before starting, not after a failed take:
vhsandttyd— vhs fails every recording with "ttyd is not installed" and the message arrives after you've written the whole tape.chromium,ffmpeg,python3— the card and qt314 renderers.- JetBrains Mono. Resolve the family with
fc-match "JetBrains Mono"and use the name it reports (currentlyJetBrainsMono Nerd Font); an assumed family name silently falls back to sans-serif and the card stops looking like a terminal. - Recording live mainnet also needs the keystore daemon
(
bun run apps/cli/src/index.ts keystore status), and AI segments need the configured agent provider reachable (probe zs-proxy's/v1/models).
What ships with it
18 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.
- assets/card.css 1.4 KB
- assets/lore-portrait.png 202 KB
- references/brand.md 4.1 KB
- references/cards.md 5.1 KB
- references/demos/apps-call.md 3.3 KB
- references/qt314.md 3.1 KB
- references/video.md 6.0 KB
- references/voice.md 7.9 KB
- scripts/add-music.sh 1004 B runs code
- scripts/lore-ascii.py 1.8 KB runs code
- scripts/lore-portrait-prep.py 1.6 KB runs code
- scripts/make-card.sh 4.4 KB runs code
- scripts/make-lore-card.sh 3.8 KB runs code
- scripts/qt314-boot.py 7.3 KB runs code
- scripts/qt314-ecosystem.py 15 KB runs code
- scripts/qt314-loop.py 4.9 KB runs code
- scripts/segA.tape 792 B
- scripts/segB.tape 789 B
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.
- 9d ago First seen · 81 lines · 117 tokens per session scan A dfd1e27294fc
marketing-content is a skill published in the GitHub repository initlabsai/vibekit (27 stars, last pushed 6d ago), licensed MIT. It adds 117 tokens to every session and 1,064 once invoked, about $0.0006 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.