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-promptWrote 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-prompt)<a href="https://agentmods.dev/skills/osidemedia/higgsfield-ai-prompt-skill/higgsfield-prompt"><img src="https://agentmods.dev/badge/skills/osidemedia/higgsfield-ai-prompt-skill/higgsfield-prompt/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-prompt"><img src="https://agentmods.dev/badge/skills/osidemedia/higgsfield-ai-prompt-skill/higgsfield-prompt.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 | $0.00056 | $0.09725 |
| Opus 5 | $0.00028 | $0.04862 |
| Sonnet 5 | $0.00011 | $0.01945 |
| Haiku 4.5 | $0.00006 | $0.00972 |
Grade A, and why
higgsfield-prompt 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.
How it starts
The opening of the file, as written. The whole thing — 744 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Higgsfield Prompt Engineering
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.
- MCSLA = Model, Camera, Subject, Look, Action — the five layers of every prompt →
- I2V: describe ONLY what moves or changes, never what's already in the image →
- Keep prompts under 200 words — short-form MCSLA regime only; block-scaffold production prompts replace the cap with structural lint (HARD RULE 8 carve-out); Cinema Studio has a hard 512-character cap →
- 1 primary action per clip, 1–2 secondary max; Fast Motion Trick: render in Slow Mo, speed up in post →
- Never leave a generic emotion ("sad"/"angry") in a prompt — decompose into muscle movements, breath, eyes, skin →
- Soul ID / recurring characters: split every prompt into Identity Block + Motion Block — never mix them →
- Conflict order when sub-skills disagree: explicit user direction > scene archetype > emotion-sync →
- Aspect ratio is a per-model enum set in the UI/header, never in the prompt body — verify via
../../specs/model-specs.yaml→ - Never combine Dolly In + Dolly Out in one shot; @ Elements for static scenes, plain text for action →
- Iterate by changing exactly ONE variable per regeneration →
- 6-Pass Diagnostic order: Subject → Action → Camera → Style → Audio → Output; most failures land on Pass 1–2 →
- Seedance short-form: 30–100 words win; Subject + Action in the first 20–30 words. Block-scaffold production briefs run 218–2,059-word medians by register — see
../higgsfield-seedance/SKILL.md§ Official Prompt Architecture → - Genre length targets: Product 30–50w, Lifestyle 40–60w, Drama 60–100w, Music Video 50–80w, Anime 50–90w →
- Kill slop words (beautiful, stunning, epic, amazing) — replace with concrete visuals/physics →
- Seedance/CS 3.0 has NO negative-prompt syntax — phrase as positive constraints →
- Dialogue cap: ~25–30 spoken words fit in 15 seconds — keep the power-shift line, convert the rest to behavior →
- Engine limits: ≤3 characters tracked across cuts; exit-frame = gone; off-screen = nonexistent; avoid reflections →
- Every cut must change BOTH shot size AND camera character →
- Age-blind rule: never boy/girl/child/kid/young/teen/little — describe by role, clothing, action →
- Scenes start already in progress unless the user says "starts with…" or "ends with…" →
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 · 744 lines · 56 tokens per session scan A 612dc278e441
higgsfield-prompt is a skill published in the GitHub repository OSideMedia/higgsfield-ai-prompt-skill (531 stars, last pushed 20d ago), licensed MIT. It adds 56 tokens to every session and 9,725 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
vibe-creating-prompt
Judges whether a user's input suits the Vibe Creating style of video-prompt writing, and when it does, distills single-scene prompts, multi-shot descriptions, emotional imagery, or mixed input into prompts that are easier for a video model to generate from — while preserving any user-specified dialogue, voiceover…
seedance-cinematic-film
Write photorealistic live-action cinematic Seedance 2.0 prompts for Higgsfield, built on five grounding pillars that stop AI drift and floaty motion. Use for "cinematic film prompt", "shot like a movie", realistic body movement, grounded motion, restrained emotional close-ups, driving scenes, fight choreography…
director-cinematography
Virtual director and cinematographer for AI-generated short videos using Higgsfield. Takes a script, scene, or creative idea and produces a shot-by-shot visual direction plan with ready-to-paste Higgsfield prompts — camera presets, lenses, lighting, color grading, and motion directives for every shot. Channels 11…
seedance-prompt-builder
Write production-ready Seedance 2.0 prompts (image, video, and motion/edit) for Higgsfield. Use this skill whenever the user wants a single Seedance prompt rather than a full shotlist — e.g. "make a Seedance prompt for X", "write me a video prompt", "restyle this clip", "turn my photo into a character sheet"…
down-skilling
Distill Opus-level reasoning into optimized instructions for Haiku 4.5 (and Sonnet). Generates explicit, procedural prompts with n-shot examples that maximize smaller model performance on a given task. Use when user says "down-skill", "distill for Haiku", "optimize for Haiku", "make this work on Haiku", "generate…
reviewing-ai-papers
Analyzes an AI/ML publication — paper, preprint, article, technical blog post — and extracts what an enterprise AI engineer should do about it. Use when someone supplies a URL or document on RAG, embeddings, fine-tuning, prompt engineering, agents, or LLM deployment and asks "review this paper", "what do you make of…