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/horizontal-to-vertical)<a href="https://agentmods.dev/skills/maddexritter-rgb/vibe-editing/horizontal-to-vertical"><img src="https://agentmods.dev/badge/skills/maddexritter-rgb/vibe-editing/horizontal-to-vertical/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/horizontal-to-vertical"><img src="https://agentmods.dev/badge/skills/maddexritter-rgb/vibe-editing/horizontal-to-vertical.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 | $0.00394 | $0.04727 |
| Opus 5 | $0.00197 | $0.02364 |
| Sonnet 5 | $0.00079 | $0.00945 |
| Haiku 4.5 | $0.00039 | $0.00473 |
Grade A, and why
horizontal-to-vertical 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 11d 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 — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.
horizontal-to-vertical — THE face-tracking skill (2 cases, locked house style)
Locked 2026-06-08, updated 2026-06-10. One tool for face-tracking. One tool for split-screen stacking. Five locked presets. That's it.
The locked house style: Y is FIXED at the clip's median eyeline (no Y bob), X tracks the face-BOX center (not the nose tip — steadier on a moving subject). Per-frame X keyframes follow the subject so the face stays pinned at one output X coordinate while Y never moves. This is what makes the AC clips look the way they do, and what every prior attempt was missing.
🛑 SHAKY, MULTI-PERSON footage (testimonial ADS) → 2D FACE-PIN, NOT these presets (2026-06-16)
The locked presets above assume a STABLE camera (Y-LOCK to median can't cancel a shaking camera) and
a SINGLE clear face. For handheld testimonial-ad footage (camera shakes, background attendees in frame),
qa_reframe_v2 locks onto the wrong/background face and the Y-lock leaves the vertical shake in. Use
_shared/testimonial_reframe.py instead: per-frame LARGEST-face detection (= foreground guest), crop
follows the face on X AND Y every frame → guest pinned dead-centre, shake cancelled. 🛑 NEVER vidstab
these (it rubber-bands/"swims" the frame). Verify by extracting CONSECUTIVE frames — the face must hold
the same screen position. (NOTE: YuNet's detector threshold is --score, not --face-conf.) Full SOP:
edit/references/testimonial_ads.md.
🔒 HARD RULE — Reframe BEFORE merge, NEVER after (2026-06-11)
For assembly cuts (multi-segment clips built from separate sources), ALWAYS reframe each segment individually FIRST, then concatenate the reframed segments. Never concatenate raw segments into one file and then try to reframe the whole thing.
Why: Each segment may come from a different camera, a different angle, a different speaker. The face tracker needs to lock onto the correct face in each segment independently — with its own Y-LOCK median, its own X smoothing window, its own zoom. If you reframe after merging:
- The tracker sees a camera switch as the face jumping across the frame and tries to smoothly pan to the new position (visible slide instead of a clean cut)
- Y-LOCK uses a single median across all segments (wrong eyeline for at least one speaker)
- Smoothing bleeds across segment boundaries (first frames after a cut show the old speaker's position fading out)
What ships with it
10 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/seam_shadow.png 947 B
- scripts/detect_face_dense.py 3.7 KB runs code
- scripts/guest_panel_render.py 11 KB runs code
- scripts/make_splitscreen.py 7.7 KB runs code
- scripts/qa_reframe_v2.py 20 KB runs code
- scripts/reframe_h2v.py 9.9 KB runs code
- scripts/reframe_yunet.py 8.8 KB runs code
- scripts/reframe.sh 3.0 KB runs code
- scripts/split_facetracked.py 4.9 KB runs code
- scripts/yunet.onnx 227 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.
- 11d ago First seen · 215 lines · 394 tokens per session scan A c74855e1a3a6
horizontal-to-vertical is a skill published in the GitHub repository maddexritter-rgb/vibe-editing (7 stars, last pushed 2mo ago), licensed MIT. It adds 394 tokens to every session and 4,727 once invoked, about $0.0020 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).
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.
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.