Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add maddexritter-rgb/vibe-editing/plugin install vibe-editingWrote 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/maddexritter-rgb/vibe-editing/caption-clips)<a href="https://agentmods.dev/skills/maddexritter-rgb/vibe-editing/caption-clips"><img src="https://agentmods.dev/badge/skills/maddexritter-rgb/vibe-editing/caption-clips/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/maddexritter-rgb/vibe-editing/caption-clips"><img src="https://agentmods.dev/badge/skills/maddexritter-rgb/vibe-editing/caption-clips.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 | $0.00139 | $0.02873 |
| Opus 5 | $0.00069 | $0.01437 |
| Sonnet 5 | $0.00028 | $0.00575 |
| Haiku 4.5 | $0.00014 | $0.00287 |
Grade A, and why
caption-clips 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 — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
caption-clips — ONE caption style for everything
🔒 LOCKED CAPTION LESSONS (2026-06-12) — every one shipped a wrong burnt caption; do not regress
Caption-text errors are INVISIBLE to audio QC (the audio is fine; the wrong word is only on screen). They must be caught by scanning the
.ass/subs.asstext or OCR'ing frames — never assumed clean.
- "one" defaults to the WORD, never the digit "1". In conversational speech "one" is almost always
the pronoun/article ("no one", "one of the most", "the one thing", "is one of").
spice_format.pynumeralizes to "1" ONLY via positive signals: money, an adjacent number, or listicle "number/step/day one" → "#1" (handled downstream on the WORD form, so keeping the word never breaks "#1"). Defaulting to "1" shipped "no 1 will care" AND "judgment is 1" in one batch. If you touch number rules, re-run the probe set (pronoun forms: "no one", "the one", "one of"; listicle: "number one", "step one"; money: "one hundred million"). - ASR hallucinates rhetorical tags ("right?") that were never spoken — and the chain BURNS them.
Whisper pattern-completes a tag from the clip's parallel structure ("take the risk, right? … shake off
the losses…" → invents a second "right?"). It appears in BOTH the QC re-transcript and the caption
transcription. To DISPROVE: isolate the exact source region (
ffmpeg -ss X -t 0.5 -af volume=12dB) and transcribe it ALONE — context-free boosted audio can't be pattern-completed. To FIX: pin a hand-corrected word list and pass--words(skips per-render ASR → deterministic captions across re-renders too). --corrections {"heard":"burned"}for reviewer-flagged single-word mis-hears (e.g. "quadruple"→ "quadrupled") without re-cutting. Applied to the transcription before formatting.- The render
captionsstage content-hashes these scripts (spice_format / spice_caption / generate_spice / caption_director) into its cache VERSION (render/stages/captions.py). So editing ANY of them auto-invalidates every caption cache — a script fix re-renders instead of silently serving a stale burn (which it used to: the "no 1"→"no one" fix appeared to do nothing until this was added).
What ships with it
60 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.
- --out 23 KB
- assets/spice_base_text.mogrt 18 KB
- fonts_README.md 949 B
- fonts/AlfaSlabOne.ttf 95 KB
- fonts/Anton.ttf 167 KB
- fonts/ArchivoBlack.ttf 89 KB
- fonts/Bangers.ttf 91 KB
- fonts/Barlow-Bold.ttf 106 KB
- fonts/Barlow-ExtraBold.ttf 108 KB
- fonts/BarlowCondensed-Bold.ttf 107 KB
- fonts/BebasNeue.ttf 60 KB
- fonts/Bitter.ttf 321 KB
- fonts/BlackOpsOne.ttf 163 KB
- fonts/BowlbyOneSC.ttf 54 KB
- fonts/Caveat.ttf 394 KB
- fonts/Chivo.ttf 157 KB
- fonts/Comfortaa.ttf 197 KB
- fonts/DancingScript.ttf 131 KB
- fonts/DMSans.ttf 235 KB
- fonts/DMSerifDisplay.ttf 75 KB
- fonts/Figtree.ttf 61 KB
- fonts/FONTS.md 847 B
- fonts/free_font/Montserrat-Black.otf 296 KB
- fonts/free_font/Montserrat-Bold.otf 318 KB
- fonts/free_font/Montserrat-ExtraBold.otf 318 KB
- fonts/free_font/Montserrat-Medium.otf 310 KB
- fonts/free_font/Montserrat-Regular.otf 312 KB
- fonts/free_font/Montserrat-SemiBold.otf 316 KB
- fonts/free_font/MontserratBlack.otf 296 KB
- fonts/Heebo.ttf 119 KB
- fonts/Inter.ttf 856 KB
- fonts/JosefinSans.ttf 116 KB
- fonts/Jost.ttf 132 KB
- fonts/Kanit-Bold.ttf 172 KB
- fonts/Kanit-ExtraBold.ttf 174 KB
- fonts/Lato-Black.ttf 649 KB
- fonts/Lato-Bold.ttf 641 KB
- fonts/Lora.ttf 207 KB
- fonts/Manrope.ttf 162 KB
- fonts/Montserrat-ExtraBold.ttf 445 KB
- fonts/Montserrat-Regular.ttf 435 KB
- fonts/Montserrat-SemiBold.ttf 444 KB
- fonts/Nunito.ttf 270 KB
- fonts/Oswald.ttf 168 KB
- fonts/Outfit.ttf 108 KB
- fonts/Pacifico.ttf 322 KB
- fonts/PassionOne-Bold.ttf 24 KB
- fonts/PlayfairDisplay.ttf 294 KB
- fonts/PlusJakartaSans.ttf 172 KB
- fonts/Poppins-Black.ttf 150 KB
- fonts/Poppins-Bold.ttf 152 KB
- fonts/Poppins-ExtraBold.ttf 151 KB
- fonts/Poppins-Regular.ttf 157 KB
- fonts/Prompt-Bold.ttf 175 KB
- fonts/Quicksand.ttf 122 KB
- fonts/Raleway.ttf 305 KB
- fonts/Rubik.ttf 351 KB
- fonts/RussoOne.ttf 38 KB
- fonts/Sora.ttf 109 KB
- fonts/SpaceGrotesk.ttf 133 KB
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 · 158 lines · 139 tokens per session scan A bf014f395dec
caption-clips is a skill published in the GitHub repository maddexritter-rgb/vibe-editing (7 stars, last pushed 2mo ago), licensed MIT. It adds 139 tokens to every session and 2,873 once invoked, about $0.0007 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 2026-08-31.
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.