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-modelsgit 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-models)<a href="https://agentmods.dev/skills/osidemedia/higgsfield-ai-prompt-skill/higgsfield-models"><img src="https://agentmods.dev/badge/skills/osidemedia/higgsfield-ai-prompt-skill/higgsfield-models/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-models"><img src="https://agentmods.dev/badge/skills/osidemedia/higgsfield-ai-prompt-skill/higgsfield-models.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 | $0.00139 | $0.09136 |
| Opus 5.5 | $0.00056 | $0.03654 |
| Sonnet 5.5 | $0.00028 | $0.01827 |
| Haiku 4.5 | $0.00014 | $0.00914 |
Grade A, and why
higgsfield-models 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- higgsfield-models — 92% identical, 271 lines differ
How it starts
The opening of the file, as written. The whole thing — 371 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Higgsfield Model Selection Guide
Contents
- Quick Decision Flowchart
- Video Models — Comparison
- Decision Flowchart
- Image Models — Quick Selection
- Budget Tiers
- Unique Feature Matrix
- Key Model Notes
- Cinema Studio 3.0 (Business/Team Plan)
- Related skills
Choosing the right model is the single biggest factor in output quality after the prompt.
This file handles most selection questions. For deep per-model documentation (prompting
specifics, parameters, edge cases, API details) → read MODELS-DEEP-REFERENCE.md.
The canonical comparison tables, the Edit-Lane Chooser, the Long-Take Chooser, and
the Motion Transfer table live in ../../model-guide.md — this file agrees with them.
Star ratings are written only from real generations. A — in a star column means not
yet field-rated; platform facts for those rows are [OFFICIAL — platform, snapshot 2026-09-26].
Quick Decision Flowchart
Fast lookup — for detailed comparisons see the full tables below.
| Need | Recommended Model | Tier |
|---|---|---|
| Top-tier cinematic video + audio | Kling 3.0 | Premium |
| Epic scale / spectacle | Seedance 2.0 or Minimax Hailuo 2.3 (Sora 2 is retired — OpenAI shut its API down 2026-09-24) | Premium |
| Nature / landscapes | Veo 3.1 | Premium |
| Artistic / stylized video | Wan 2.6 | Mid |
| One clip longer than 15s | Seedance 2.5 · Wan 3.0 / Prime · FLUX 3 Video (to 20s) → model-guide.md § Long-Take Chooser |
— |
| Edit / extend / multiply existing footage | → model-guide.md § Edit-Lane Chooser |
— |
| Motion transfer from a reference video | Kling 3.0 Motion Control or Genjutsu → model-guide.md § Motion Transfer |
— |
| Fast video iteration | Seedance 2.0 Fast / Mini | Mid |
| VFX / fluid motion | Minimax Hailuo 2.3 | Mid |
| Budget-friendly video | Kling 3.0 Turbo — the catalog's budget Kling (Kling 2.5 Turbo / Higgsfield DoP Lite: not in the API catalog, 2026-09-26 — verify in the live UI) | Mid |
| Fashion / aesthetic images | Soul 2.0 | Free |
| Photorealistic sharp images | Nano Banana Pro | Low |
| AI actor generation | Soul Cast | Low |
| Native 4K images | Nano Banana Pro (resolution to 4k) — Kling Image 3.0 is not in the API catalog, 2026-09-26 — verify in the live UI |
— (NB Pro's listed price is for 1K; verify the 4K price) |
| Transparent-background image | GPT Image 2.5 (background: transparent) |
— |
| Photo style transformation | Photodump (29 presets) | Low |
What ships with it
1 file 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.
- 3d ago Changed · +15 lines b6a0b7b319d8
- 1mo ago Changed · +76 lines · +77 tokens per session 406a9ea8390d
- 1mo ago First seen · 280 lines · 62 tokens per session scan A 404deea47b5e
higgsfield-models is a skill published in the GitHub repository OSideMedia/higgsfield-ai-prompt-skill (800 stars, last pushed 2d ago), licensed MIT. It adds 139 tokens to every session and 9,136 once invoked, about $0.0006 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.