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/highlight)<a href="https://agentmods.dev/skills/maddexritter-rgb/vibe-editing/highlight"><img src="https://agentmods.dev/badge/skills/maddexritter-rgb/vibe-editing/highlight/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/highlight"><img src="https://agentmods.dev/badge/skills/maddexritter-rgb/vibe-editing/highlight.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 | $0.00271 | $0.02875 |
| Opus 5 | $0.00135 | $0.01437 |
| Sonnet 5 | $0.00054 | $0.00575 |
| Haiku 4.5 | $0.00027 | $0.00287 |
Grade A, and why
highlight scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/highlight — highlights-channel clipper
Turn a long recording (Q&A / hotline / podcast) into ranked, postable HORIZONTAL 16:9 "mid" videos for a highlights / clips channel whose goal is subscriber growth. Three modes: MINE (recording → finished mids), POST (uploaded drafts → titled + scheduled), and FILL (Mode C — auto-queue finished 9:16 shorts to your channel via Buffer).
Mids are 16:9 horizontal, ~3–10 min — regular videos, not 9:16 shorts. (For shorts use
/edit.) This skill self-locates via${CLAUDE_PLUGIN_ROOT}(the plugin install dir); every script finds the plugin root automatically, so nothing is hardcoded to a home folder.
🔒 NON-NEGOTIABLES — verify before EVERY delivery, never silently skip
- Optimize selection + titles for subscribers (
subs_per_1k_views), never raw CTR. The whole point of a highlights channel is to convert the right viewer into a subscriber. - 16:9 horizontal; the cut ends the instant the payoff lands — nothing trails.
- CTA outro is OPTIONAL and user-supplied. If you drop your own outro clip at
brand/cta/outro.mp4(repo root),highlight_cut.pyappends it to every mid. No file → it skips gracefully. (--cta <path>overrides the location;--no-ctaforces skip.)
KPI = subscribers (subs_per_1k_views), not views/CTR. Mids are 16:9, ~3–10 min.
Three modes — detect which from what the user says
- MINE — they give a link/file to a raw recording / say "mine these". → produce finished mids, deliver locally. STOP there — they upload them as drafts themselves.
- POST — they say "post & schedule these" / "schedule these out" (the mids are already uploaded as YouTube drafts on their channel). → title + schedule them.
- FILL (Mode C) — they say "fill my queue" / "auto-post my shorts". → queue finished 9:16 shorts from a folder to their channel via Buffer (see Mode C below).
The full loop: MINE → (you upload drafts) → POST → (Studio re-export feeds back to sharpen).
What ships with it
28 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.
- buffer/buffer_api.py 5.3 KB runs code
- buffer/captions.py 2.6 KB runs code
- buffer/config.py 6.0 KB runs code
- buffer/fill_queue.py 13 KB runs code
- buffer/README.md 3.1 KB
- buffer/requirements.txt 84 B
- buffer/slots.py 1.6 KB runs code
- buffer/storage.py 2.1 KB runs code
- config/patterns.json 1.7 KB
- references/clipper_hookmeatpayoff.ts 29 KB runs code
- references/cutting_prompts.md 2.7 KB
- references/feedback_loop.md 2.2 KB
- references/research_findings.md 3.4 KB
- references/segmenter_prompt.ts 2.4 KB runs code
- references/selection_rules.md 2.9 KB
- references/title_rules.md 3.6 KB
- scripts/highlight_asd.py 7.4 KB runs code
- scripts/highlight_cta.py 5.1 KB runs code
- scripts/highlight_cut.py 6.9 KB runs code
- scripts/highlight_diarize.py 4.5 KB runs code
- scripts/highlight_miner.py 8.3 KB runs code
- scripts/highlight_multicam.py 10 KB runs code
- scripts/highlight_post.py 9.7 KB runs code
- scripts/highlight_publish_bridge.py 6.1 KB runs code
- scripts/highlight_reframe16.py 6.3 KB runs code
- scripts/highlight_source_match.py 4.4 KB runs code
- scripts/highlight_studio_import.py 6.5 KB runs code
- scripts/title_sop.py 5.5 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 · 171 lines · 271 tokens per session scan A 753314e94ec1
highlight is a skill published in the GitHub repository maddexritter-rgb/vibe-editing (7 stars, last pushed 2mo ago), licensed MIT. It adds 271 tokens to every session and 2,875 once invoked, about $0.0014 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.