higgsfield

higgsfield is a skill for Claude Code from coleam00/ai-content-factory. It costs 73 tokens per session (970 once invoked), scanned A, original, MIT.

A command-line tool for generating images, videos, and user-generated-content-style video ads with Higgsfield models.

In plain words
What is it for?
Use it to create product images, product-pan videos, talking-head ads, and voice or video jobs, then wait for and download the results.
Why use it?
It gives you one terminal interface for creating media and checking available models, voices, and model-specific options.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use it to create product images, product-pan videos, talking-head ads, and voice or video jobs, then wait for and download the results.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/coleam00/ai-content-factory/higgsfield
Install

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.

Any agent
npx skills add coleam00/ai-content-factory --skill higgsfield
Clone the repo
git clone --depth 1 https://github.com/coleam00/ai-content-factory

Made for: Claude Code.

Wrote 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.

agentmods badge for higgsfield

README.md
[![agentmods](https://agentmods.dev/badge/skills/coleam00/ai-content-factory/higgsfield/github.svg)](https://agentmods.dev/skills/coleam00/ai-content-factory/higgsfield)
Your own site
<a href="https://agentmods.dev/skills/coleam00/ai-content-factory/higgsfield"><img src="https://agentmods.dev/badge/skills/coleam00/ai-content-factory/higgsfield/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.

agentmods 80×15 button for higgsfield

Your own site · 80×15
<a href="https://agentmods.dev/skills/coleam00/ai-content-factory/higgsfield"><img src="https://agentmods.dev/badge/skills/coleam00/ai-content-factory/higgsfield.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 73 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 970 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00073 $0.00970
Opus 5 $0.00036 $0.00485
Sonnet 5 $0.00015 $0.00194
Haiku 4.5 $0.00007 $0.00097

Measured 11d ago against content hash 1c4f9a7257a0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

higgsfield 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 11d 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.

.claude/skills/higgsfield/SKILL.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Higgsfield CLI

Higgsfield is ONE CLI that drives frontier image + video models from the terminal. It is self-documenting — when you're unsure of a model or a flag, ask the CLI itself:

higgsfield --help                 # top-level commands (generate, model, voices, upload...)
higgsfield model list             # every model (add --video or --image to filter)
higgsfield model get <model>      # the EXACT params for a model: duration caps, flags, defaults
higgsfield voices list            # TTS voices (for text2speech_v2)

Every generate create job takes --wait (block until done) and prints a result_url — download that URL to get the file. Aliases: higgs, hf. On Windows, if higgsfield isn't on PATH, call %APPDATA%\npm\higgsfield.cmd.

Models you'll actually use

Job Model Notes
Product image / plate nano_banana_pro ~0.15 cr. --image-references <img> to keep/edit a real product (e.g. add branding).
Product pan (video, no person) kling3_0_turbo image→video. --start-image <img> --duration 10 --resolution 1080p.
UGC talking-head (video + native voice) gemini_omni 10s max, generates its own audio + lipsync. --image-references <product.jpg>.

Make a UGC ad (the main recipe)

One command → a ~10s vertical ad of a person holding a product and reviewing it in their own voice:

higgsfield generate create gemini_omni \
  --prompt "A friendly <man|woman> in a bright modern kitchen holding up this <product> toward the camera, casual selfie UGC review, looking right at the camera and speaking warmly in one continuous take: '<~25-word spoken line>' Deliver the line exactly once at a natural, unhurried pace; do NOT repeat, stutter, or loop any word or phrase, and if it finishes before the clip ends, just hold a natural smile in silence. Keep any product logo facing the camera, crisp and legible. Natural handheld vlog style, real skin texture. No on-screen text, no captions, no phone visible in frame." \
  --image-references <path/to/branded-product.jpg> \
  --duration 10 --aspect_ratio 9:16 --resolution 720p --wait

Read the full file on GitHub · 60 lines

Changes

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.

  1. 11d ago First seen · 60 lines · 73 tokens per session scan A 1c4f9a7257a0

Subscribe to this mod's changes

higgsfield is a skill published in the GitHub repository coleam00/ai-content-factory (23 stars, last pushed 2mo ago), licensed MIT. It adds 73 tokens to every session and 970 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.

Related

Other skills, from other repositories

webgl-holographic-foil

A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.

nexu-io/open-design · 41 tokens

general-video

Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…

heygen-com/hyperframes · 92 tokens

html-ppt-hermes-cyber-terminal

OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.

nexu-io/open-design · 53 tokens

html-ppt-taste-brutalist

16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).

nexu-io/open-design · 78 tokens

chengfeng-check-updates

An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.

Agentchengfeng/chengfeng-videocut-skills · 120 tokens

diagnostic-stem-delivery

Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.

HKUDS/OpenSpace · 23 tokens