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-workspacesWrote 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-workspaces)<a href="https://agentmods.dev/skills/osidemedia/higgsfield-ai-prompt-skill/higgsfield-workspaces"><img src="https://agentmods.dev/badge/skills/osidemedia/higgsfield-ai-prompt-skill/higgsfield-workspaces/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-workspaces"><img src="https://agentmods.dev/badge/skills/osidemedia/higgsfield-ai-prompt-skill/higgsfield-workspaces.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 | $0.00075 | $0.03652 |
| Opus 5 | $0.00037 | $0.01826 |
| Sonnet 5 | $0.00015 | $0.00730 |
| Haiku 4.5 | $0.00007 | $0.00365 |
Grade A, and why
higgsfield-workspaces 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 12d 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-workspaces — 92% identical, 49 lines differ
How it starts
The opening of the file, as written. The whole thing — 322 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Higgsfield Workspaces — Task-First Decision Layer
Introduction
Higgsfield is organized around workspaces, each one tuned for a specific kind of production work. The right starting question is not "which model should I use?" but "what am I actually trying to make?" Inside a workspace, model choice still matters — it shapes quality, speed, and cost — but a workspace mismatch costs more time than a suboptimal model. Pick the workspace by the task, then pick the model by the result you want.
The Decision Matrix
| Your production problem | Start with workspace |
|---|---|
| Cinematic scene with deliberate camera direction | Cinema Studio |
| Speaking character, dubbing, or avatar video | Lipsync Studio |
| Rough idea, sketch, or storyboard test | Draw to Video / Sketch to Video |
| Fast short-form or viral-style content | Sora 2 Trends |
| Product ad or ecommerce variation | Click to Ad |
| Narration, voice swap, or translation | Higgsfield Audio |
If the user's task matches more than one row, pick the workspace whose output most closely resembles the final deliverable — you can always chain into another workspace for polish or audio later.
Workspace Descriptions
Cinema Studio
The professional filmmaking environment on Higgsfield. Built for multi-shot,
character-consistent sequences where camera direction, genre framing, and visual
cohesion matter. Cinema Studio 2.5 offers optical physics (camera body + lens
stack) and built-in color grading; Cinema Studio 3.0 (Business/Team plan) adds
native audio, Smart camera planning, and longer durations. Choose this workspace
when the work needs to feel like a film. For prompt construction, Director Panel
use, optical stack selection, and multi-shot planning, see higgsfield-cinema.
Lipsync Studio
The workspace for putting words into a character's mouth. It pairs an image,
video, or generated face with an audio track and synchronizes the lip movement
to the speech. Use it for dubbed performances, talking-head avatars, character
dialogue, and lipsync work layered on top of existing video generations. For
audio layer design (dialogue, SFX, ambient, BGM) that feeds into Lipsync Studio,
see higgsfield-audio. For character reference management and Soul Cast avatar
generation that commonly sits upstream, see higgsfield-soul.
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.
- 12d ago First seen · 322 lines · 75 tokens per session scan A 88a43939d84e
higgsfield-workspaces is a skill published in the GitHub repository OSideMedia/higgsfield-ai-prompt-skill (531 stars, last pushed 20d ago), licensed MIT. It adds 75 tokens to every session and 3,652 once invoked, about $0.0004 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 2026-08-30.
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"…
dramaclaw
A skill for answering identity and self-introduction questions, and for working with the DramaClaw/NovelVideo pipeline. The description also covers turning novels or stories into short vertical videos.
ai-media-generator
A workflow for turning ideas into prompts for AI-generated images, videos, and music across several media platforms. When needed, it can also send those prompts to the chosen platform through browser automation.
kling-ai
Write and improve prompts for Kling AI video generation, and pick the right Kling model for the job. Covers image-to-video, text-to-video, multi-shot storyboards, talking avatars from one photo plus audio, motion transfer, video editing of an existing clip, Element Reference for character consistency, Voice Control…
minimax-h3
Write, debug and structure prompts for MiniMax H3 video generation (T2VA, I2VA, FL2VA, L2VA, Ref2VA) and configure its ComfyUI workflow. Use when the user mentions MiniMax H3, minimaxh3, fl2va, ref2va, MiniMaxH3ReferenceToVideo, reference-to-video, asks to animate a photo, write a video prompt, pick a model quant, or…