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-recipesWrote 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-recipes)<a href="https://agentmods.dev/skills/osidemedia/higgsfield-ai-prompt-skill/higgsfield-recipes"><img src="https://agentmods.dev/badge/skills/osidemedia/higgsfield-ai-prompt-skill/higgsfield-recipes/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-recipes"><img src="https://agentmods.dev/badge/skills/osidemedia/higgsfield-ai-prompt-skill/higgsfield-recipes.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 | $0.00055 | $0.02858 |
| Opus 5 | $0.00028 | $0.01429 |
| Sonnet 5 | $0.00011 | $0.00572 |
| Haiku 4.5 | $0.00006 | $0.00286 |
Grade A, and why
higgsfield-recipes 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-recipes — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 316 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Higgsfield Genre Recipe Templates
Each recipe is a ready-to-adapt template. Fill in the bracketed fields with your specific details. All examples are compliant — no real names or IPs.
Recipe 1: Action / Chase
Core pattern: Establish → Pursuit → Obstacle → Climax Best models: Kling 2.6, Sora 2 Camera: Action Run, FPV Drone, Crash Zoom In, Bullet Time Style: Cinematic or Anamorphic
Template:
[Subject description — clothing, build, energy] sprints through [environment].
Camera: Action Run — low behind them, matching pace.
[Obstacle appears — what is it]. They [dodge action], barely clearing it.
The camera Whip Pans to [pursuer/threat].
Bullet Time as [climax action — punch, leap, collision].
Style: Cinematic, high contrast, [warm/cold] tones. [Aspect ratio].
Example:
A woman in a tactical jacket sprints through a rain-soaked night market,
weaving between stalls and startled vendors.
Camera: Action Run — low behind her, matching her sprint.
A metal gate drops ahead. She slides under it without breaking stride.
Whip Pan to the two men pursuing her through the crowd.
Bullet Time as she leaps from a loading dock onto a moving truck below.
Style: Cinematic, cold blue shadows, amber market light. 16:9.
Recipe 2: Emotional Drama / Character Moment
Core pattern: Establish space → Reveal character state → Emotional beat Best models: Kling 2.6, Kling 3.0 Camera: Dolly In, Arc, Head Tracking, Focus Change Style: Cinematic, Super 8MM
Template:
[Character — appearance, posture, state] is in [intimate environment].
[What they are doing — quiet action revealing emotion].
Camera: slow Dolly In toward [their face / hands / significant object].
[Something shifts — they react, realize, remember].
Style: [Cinematic / Super 8MM], [lighting — golden / overcast / practical only].
[Color grade — warm/cool, contrast level].
Example:
A man in his 60s sits alone at a kitchen table. An old letter in his hands.
He reads slowly, lips barely moving, eyes growing distant.
Camera: slow Dolly In toward his face.
He looks up at the empty chair across from him.
Style: Cinematic. Warm late-afternoon window light, soft shadows.
Slightly desaturated. 16:9.
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 · 316 lines · 55 tokens per session scan A bae8e7626b02
higgsfield-recipes is a skill published in the GitHub repository OSideMedia/higgsfield-ai-prompt-skill (531 stars, last pushed 20d ago), licensed MIT. It adds 55 tokens to every session and 2,858 once invoked, about $0.0003 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…