Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/OSideMedia/higgsfield-ai-prompt-skillnpx agentmods add skills/osidemedia/higgsfield-ai-prompt-skill/higgsfield-cinemaWrote 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-cinema)<a href="https://agentmods.dev/skills/osidemedia/higgsfield-ai-prompt-skill/higgsfield-cinema"><img src="https://agentmods.dev/badge/skills/osidemedia/higgsfield-ai-prompt-skill/higgsfield-cinema/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-cinema"><img src="https://agentmods.dev/badge/skills/osidemedia/higgsfield-ai-prompt-skill/higgsfield-cinema.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 | $0.00202 | $0.25711 |
| Opus 5.5 | $0.00081 | $0.10284 |
| Sonnet 5.5 | $0.00040 | $0.05142 |
| Haiku 4.5 | $0.00020 | $0.02571 |
Grade A, and why
higgsfield-cinema 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 29d 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 — 1,726 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Higgsfield Cinema Studio 2.5
QUICK FACTS
Generated-checked block (scripts/build_index.py verifies anchors). Read the linked sections for full context — these lines are routing aids, not the rules themselves.
- Four Cinema Studio versions are on the platform (2.5 / 3.0 / 3.5 / 4.0) — user-selected, no auto-routing; always detect the version first →
- Cinema Studio 4.0 (
cinematic_studio_video_4_0, CLI workflow schema 2026-09-26): the same four modes asseedance_2_5(t2v / omni_reference / video_edit / video_extension), 480p–1080p, start/end image + image/video/audio refs; the 3.5 enum pills are GONE — camera / lens / aperture / era / genre / pacing are free*_idstrings with no published values, so never invent one → - 4.0 vs 3.5 at the API: no
multi_shots/multi_prompt, nogenreenum, noenhance_prompt;promptnow REQUIRED; audio defaults ON; duration default 5s (range unpublished) → - Hard 512-character prompt cap; 2.5 @ Element chips eat ~80–100 hidden chars each →
- Elements System: define @Characters/@Locations/@Props once, call everywhere →
- 3.5 main UI = three pills (Genre / Style / Camera), each Auto by default — override only with a creative reason →
- 7 confirmed 3.5 genres: General · Action · Horror · Comedy · Noir · Drama · Epic — never invent genre names →
- Style presets: 8 Color Palettes · 6 Lighting · 9 Camera Moveset Styles, or free-form Manual Style →
- Camera axes: 3 bodies · 5 lenses · focal 8/14/35/50/75mm · aperture f/1.4–f/4–f/11; two camera vocabularies coexist — vocabulary follows the selected model →
- Output enums: 7 aspect ratios incl. 21:9 · 480p/720p/1080p · duration 4–15s · Sound On/Off →
- Lead every delivered shot with the one-line settings strip (UI presets ≠ prompt text; never restate strip values in the body) →
- The UI shot counter caps internal cuts — "strictly N shots" must keep N within it (observed cap 4; API exposes no max — UI behavior, verify live) →
- Manual Style = saved ≤2,000-char block of project LAWS (grade, lighting law, texture, performance register); it replaces the preset axes →
- 480p drafts validate the prompt, NOT the take — no seed param; transfer a look via Hero Frame + start/end-frame pinning →
- Resolution matrix has two axes: shot physics × delivery context; 4K-finish pipelines master at model max res in std mode →
- Seedance fast mode cannot output 1080p — drafting in fast then "switching up" silently changes mode AND res →
- Big reference blocks live beside this file: 2.5 + 3.0 per-mode output templates in
references/output-formats-2-5-3-0.md; Motion / Outfit / Palette / Product sheet specs inreferences/reference-sheet-types.md→
What ships with it
2 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.
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.
- 29d ago Changed · -309 lines · +49 tokens per session f3045ba3ed58
- 1mo ago First seen · 2,035 lines · 153 tokens per session scan A 5c0d01526818
higgsfield-cinema is a skill published in the GitHub repository OSideMedia/higgsfield-ai-prompt-skill (800 stars, last pushed 2d ago), licensed MIT. It adds 202 tokens to every session and 25,711 once invoked, about $0.0008 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.