Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add MrJPTech/macro-pickle --skill openmontage-video-promptinggit clone --depth 1 https://github.com/MrJPTech/macro-pickleWrote 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/mrjptech/macro-pickle/openmontage-video-prompting)<a href="https://agentmods.dev/skills/mrjptech/macro-pickle/openmontage-video-prompting"><img src="https://agentmods.dev/badge/skills/mrjptech/macro-pickle/openmontage-video-prompting/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/mrjptech/macro-pickle/openmontage-video-prompting"><img src="https://agentmods.dev/badge/skills/mrjptech/macro-pickle/openmontage-video-prompting.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 | $0.00132 | $0.02072 |
| Opus 5 | $0.00066 | $0.01036 |
| Sonnet 5 | $0.00026 | $0.00414 |
| Haiku 4.5 | $0.00013 | $0.00207 |
Grade A, and why
openmontage-video-prompting 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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenMontage Video-Gen Prompting
Distilled from OpenMontage's skills/creative/video-gen-prompting.md and its
per-model guides (from the OpenMontage project).
This is the control layer on top of macro-pickle's existing Director Brief.
The Prompt Engine (buildVideoPrompt in scripts/lib/prompts/video.ts) renders
the structure; this skill teaches you what to put in each slot so the model
actually renders it.
Read this BEFORE hand-writing a video prompt or filling a
VideoBrief. It does not replace/pickle-prompt— it makes the brief you feed it far more precise.
The one rule that matters most
VLM research (CMU/Harvard) shows generation models reliably render subject and scene but routinely fail on motion, spatial, and camera. So the highest-leverage habit is forcing every prompt to fill all five aspects:
[Subject] type + 3–6 disambiguating visual attributes
[Subject Motion] actions in TEMPORAL order; subject↔object & subject↔subject interactions
[Scene] overlays (listed separately!) + POV + setting + time-of-day + dynamics
[Spatial] shot size + position-in-frame + depth (FG/MG/BG) + camera height — and how they CHANGE
[Camera] speed → lens distortion → height → angle → focus/DoF → steadiness → movement
Shorter prompt = more creative freedom. Longer prompt = more control. Match length to the model (below). A prompt is self-contained only if a reader who never saw the shot could picture it from the text alone.
Per-model length sweet spots
| Model | Sweet spot | Notes |
|---|---|---|
| Seedance 2.0 | 200–400 w (hero), 80–150 w (insert) | macro-pickle's premium default; rewards long structured 5-aspect prompts, single-pass synced audio, multi-shot |
| Wan 2.2 | 200–400 w | fine-tuned on long captions |
| Sora 2 / VEO 3.1 | 100–250 w | plateaus past ~250 |
| LTX-2 | ≤ 80 w | degrades past that — keep tight |
| Runway Gen-4 | ≤ 60 w | "focus on motion, not appearance"; one scene per clip |
| Kling 2.6 | 4-part | supports ++emphasis++ syntax |
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 · 154 lines · 132 tokens per session scan A 9cabeec07f80
openmontage-video-prompting is a skill published in the GitHub repository MrJPTech/macro-pickle (2 stars, last pushed 1mo ago), licensed MIT. It adds 132 tokens to every session and 2,072 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
seedance-vocab-en
This skill should be used when an English Seedance 2.0 prompt needs clearer production wording, less generic prose, or precise vocabulary for camera, lighting, motion, VFX, audio, and constraints. Route blocked prompts through seedance-filter for context and boundary review.
seedance-antislop
This skill should be used when a Seedance 2.0 prompt contains generic AI filler, hollow superlatives, vague cinematic language, bloated adjectives, weak verbs, or needs sharper production-specific wording.
seedance-examples-ja
This skill should be used when the user asks for Japanese Seedance 2.0 examples, Japanese prompt patterns, example rewrites, or safe versions of working Japanese video-generation prompts.
seedance-filter
This skill should be used when a Seedance 2.0 prompt is blocked or rejected, when moderation is a suspected cause of a problem, or when the user asks for a content-boundary review or safer alternative. Assess the actual request before offering a clarification.
seedance-prompt-short
This skill should be used when the user asks for a compact Seedance 2.0 prompt, short Chinese prompt, prompt compression, 30-100 word output, or removal of unnecessary prompt language.
seedance-vocab-zh
This skill should be used when the user asks for Chinese Seedance 2.0 prompt wording, Mandarin cinematic vocabulary, Chinese prompt compression, or translation of camera, lighting, action, VFX, audio, and production terms into Chinese.