caption-clips

caption-clips is a skill for Claude Code from maddexritter-rgb/vibe-editing. It costs 139 tokens per session (2,873 once invoked), scanned A, original, MIT.

A caption-burning skill that adds one consistent styled caption format to short-form videos. The captions are placed directly onto the video rather than kept as a separate subtitle track.

In plain words
What is it for?
Use it when adding on-screen captions to short clips. It formats spoken text for display and checks the caption text for known wording issues.
Why use it?
It removes the need to format captions by hand and helps catch common transcript-to-caption mistakes, such as wrong words or invented speech tags.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: positional $N argument.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the vibe-editing plugin — 18 skills shipped together

Good fit Use it when adding on-screen captions to short clips. It formats spoken text for display and checks the caption text for known wording issues.

Compare 6 skills from other repositories ↓
Install

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.

Claude Code
/plugin marketplace add maddexritter-rgb/vibe-editing
Claude Code
/plugin install vibe-editing

Made for: Claude Code.

Or install vibe-editing, the plugin that ships this one along with the rest of its 18 skills.

Wrote 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.

agentmods badge for caption-clips

README.md
[![agentmods](https://agentmods.dev/badge/skills/maddexritter-rgb/vibe-editing/caption-clips/github.svg)](https://agentmods.dev/skills/maddexritter-rgb/vibe-editing/caption-clips)
Your own site
<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.

agentmods 80×15 button for caption-clips

Your own site · 80×15
<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>
Per session 139 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,873 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 10d ago against content hash bf014f395dec, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

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.

plugins/vibe-editing/skills/caption-clips/SKILL.md · 158 lines

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.ass text or OCR'ing frames — never assumed clean.

  1. "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.py numeralizes 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").
  2. 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).
  3. --corrections {"heard":"burned"} for reviewer-flagged single-word mis-hears (e.g. "quadruple"→ "quadrupled") without re-cutting. Applied to the transcription before formatting.
  4. The render captions stage 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).

Read the full file on GitHub · 158 lines

Files

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.

Changes

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.

  1. 10d ago First seen · 158 lines · 139 tokens per session scan A bf014f395dec

Subscribe to this mod's changes

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.

Related

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.

nexu-io/open-design · 41 tokens

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…

heygen-com/hyperframes · 92 tokens

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.

nexu-io/open-design · 53 tokens

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).

nexu-io/open-design · 78 tokens

diagnostic-stem-delivery

Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.

HKUDS/OpenSpace · 23 tokens

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.

Agentchengfeng/chengfeng-videocut-skills · 120 tokens