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 OSideMedia/higgsfield-ai-prompt-skill --skill higgsfield-scene-enginegit clone --depth 1 https://github.com/OSideMedia/higgsfield-ai-prompt-skillWrote 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/osidemedia/higgsfield-ai-prompt-skill/higgsfield-scene-engine)<a href="https://agentmods.dev/skills/osidemedia/higgsfield-ai-prompt-skill/higgsfield-scene-engine"><img src="https://agentmods.dev/badge/skills/osidemedia/higgsfield-ai-prompt-skill/higgsfield-scene-engine/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/osidemedia/higgsfield-ai-prompt-skill/higgsfield-scene-engine"><img src="https://agentmods.dev/badge/skills/osidemedia/higgsfield-ai-prompt-skill/higgsfield-scene-engine.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00167 | $0.02937 |
| Opus 5.5 | $0.00067 | $0.01175 |
| Sonnet 5.5 | $0.00033 | $0.00587 |
| Haiku 4.5 | $0.00017 | $0.00294 |
Grade A, and why
higgsfield-scene-engine 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 3d 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 — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Higgsfield Scene Engine — is this scene worth generating?
Contents
- The five-element engine
- The causal chain
- Audit procedure
- Where this sits before prompting
- Related Skills
[EMPIRICAL — Tigran's tig-scene-engine skill (2026-06-26), re-derived 2026-08-22] These definitions are
bespoke and deliberately not the textbook ones. Apply them as written; do not substitute
standard screenwriting glosses, which are looser and will pass scenes this engine fails.
Why a prompter carries this. Every shot costs credits and iterations. A structurally dead scene generates just as cleanly as a live one — the model has no opinion about whether a beat earns its place — so the failure surfaces only after the footage exists and the cut does not build. This skill is the cheapest pass in the repo: it runs on text, before any generation, and its whole job is to stop you paying to render a scene that cannot work.
It decides which shots deserve the spend. higgsfield-shotlist-director turns the
settled scene into shots; higgsfield-acting writes the performance inside them.
The five-element engine
1. Goal
The single, unchanging thing the hero is fighting for: to fix what has already been established and reach, as fast as possible, the result that resolves it. "Already established" means anything set up earlier — deep backstory, a few scenes ago, or one minute ago.
- The major goal never changes, and the hero is never wrong about it. He can be wrong about tactics, never about the goal.
- Every scene goal must be a causal link toward the story goal. Test: if you can remove the scene and the chain still holds, the scene fails. No orphan scenes.
- "What he ought to do" is not a separate thing to test — the right move is dictated by Obstacle + Stakes. A hero taking a tactic the stakes would not justify (showering while the building burns) is a flaggable inconsistency: name it as bad writing or as deliberate self-sabotage.
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.
- 3d ago Changed · +18 lines d1b35e1e88f1
- 1mo ago Changed · +15 lines 52e2d9c34fb2
- 1mo ago First seen · 181 lines · 167 tokens per session scan A d53dfe53db5b
higgsfield-scene-engine is a skill published in the GitHub repository OSideMedia/higgsfield-ai-prompt-skill (800 stars, last pushed 2d ago), licensed MIT. It adds 167 tokens to every session and 2,937 once invoked, about $0.0007 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
seedance-shotlist-director
Generate a director's shotlist as an editable HTML production board for Seedance 2.0. Use whenever the user provides a script, scene breakdown, story idea, or treatment to turn into a numbered shotlist with English Seedance prompts — trigger on "make a shotlist", "director’s shotlist", "break this script into…
vox-director
Turn ONE topic into a finished Vox-style paper-collage explainer / ad video, end to end on the Atlas Cloud API + local ffmpeg — script, collage keyframes, motion, voice-over, music, captions, all automated. Use this whenever the user wants a "Vox style" video, a paper/torn-paper collage animation, a "motion collage"…
sketch-correction-worker
Use when doing single-beat sketch quality control and preparing correction labels from a SuperTale project path and episode number. This skill turns one episode's selected sketches plus local script beat data into selectresult.jsonl, selectsummary.json, tasks.jsonl, and labels.jsonl for edit execution. Prefer using…
freezone
Use when the active chat surface is 虾画/Freezone/canvas, or when the user asks about canvas nodes, visual boards, selections, graph edits, canvas actions, layout, or Freezone short-video workflow work.
dramaclaw-workflows
Create, revise, confirm, run, or resume multi-node DramaClaw Freezone canvas workflows. Use for requests involving a workflow, several connected nodes, grouped production stages, storyboards, or text/image/video/audio pipelines; do not use for one standalone canvas operation.
workflows
Use in Freezone/虾画 chat when the user selects a Skill or asks to create, plan, analyze, or expand a dynamic canvas workflow for short drama, ads, ecommerce, product video, MV, text, image, video, or audio production.