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/render)<a href="https://agentmods.dev/skills/maddexritter-rgb/vibe-editing/render"><img src="https://agentmods.dev/badge/skills/maddexritter-rgb/vibe-editing/render/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/render"><img src="https://agentmods.dev/badge/skills/maddexritter-rgb/vibe-editing/render.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 | $0.00290 | $0.02038 |
| Opus 5 | $0.00145 | $0.01019 |
| Sonnet 5 | $0.00058 | $0.00408 |
| Haiku 4.5 | $0.00029 | $0.00204 |
Grade A, and why
render 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
render — manifest-driven, stage-cached clip rendering
The problem this solves: delivered .mp4s are flat — all the layers (cuts, reframe, grade, captions, music) baked into one file. Any revision = either re-render from scratch (which can change unrelated things) or overlay hack (which is fragile). This skill makes revisions surgical by keeping every stage's output cached and re-running only what changed.
How it works
A clip is a recipe: manifest.json references source files for each layer.
project/
manifest.json # the recipe
00_SOURCE/ # raw masters
10_WORK/
cuts.json # in/out per segment (editable)
captions.ass # caption source (editable)
music.json # music + leveling (editable)
stages/ # cached intermediate renders
cut/<hash>.mp4
reframe/<hash>.mp4
grade/<hash>.mp4
captions/<hash>.mp4
mix/<hash>.mp4
leadfix/<hash>.mp4
20_DELIVER/v<N>/
<Brand-named>.mp4
Engine reads manifest → for each stage in pipeline order:
- Compute hash of (stage config + upstream stage output hash + stage version)
- If
stages/<stage>/<hash>.mp4exists → cache hit, skip render - Else → run stage, write to cached path
- Pass output to next stage
Final stage's output is copied to 20_DELIVER/v<N>/<Brand-named>.mp4.
Usage
# First render of a new clip
python3 ${CLAUDE_PLUGIN_ROOT}/skills/render/engine.py <project_dir>
# Revise — engine auto-detects which source changed and rebuilds from there
python3 ${CLAUDE_PLUGIN_ROOT}/skills/render/engine.py <project_dir>
# Force re-render from a specific stage (skip cache from this stage forward)
python3 ${CLAUDE_PLUGIN_ROOT}/skills/render/engine.py <project_dir> --from captions
# Deliver to a new version folder (default: v1; bumps if --bump)
python3 ${CLAUDE_PLUGIN_ROOT}/skills/render/engine.py <project_dir> --bump
Pipelines
What ships with it
16 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.
- engine.py 15 KB runs code
- pipelines/anthropic-demo.json 295 B
- pipelines/listicle.json 299 B
- pipelines/qa.json 656 B
- pipelines/single.json 528 B
- scripts/init_manifest.py 6.3 KB runs code
- stages/__init__.py 0 B runs code
- stages/_util.py 1.1 KB runs code
- stages/audio_mix.py 2.6 KB runs code
- stages/captions.py 12 KB runs code
- stages/cut.py 7.4 KB runs code
- stages/grade.py 1.1 KB runs code
- stages/leadfix.py 2.9 KB runs code
- stages/mix.py 3.2 KB runs code
- stages/reframe.py 29 KB runs code
- stages/remotion_render.py 5.1 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.
- 9d ago First seen · 138 lines · 0 tokens per session scan A ed23f6efc79b
render is a skill published in the GitHub repository maddexritter-rgb/vibe-editing (7 stars, last pushed 2mo ago), licensed MIT. It adds 290 tokens to every session and 2,038 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.