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 pixelab-ch/higgsfield-skills --skill 01-cinematicgit clone --depth 1 https://github.com/pixelab-ch/higgsfield-skillsWrote 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/pixelab-ch/higgsfield-skills/01-cinematic)<a href="https://agentmods.dev/skills/pixelab-ch/higgsfield-skills/01-cinematic"><img src="https://agentmods.dev/badge/skills/pixelab-ch/higgsfield-skills/01-cinematic/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/pixelab-ch/higgsfield-skills/01-cinematic"><img src="https://agentmods.dev/badge/skills/pixelab-ch/higgsfield-skills/01-cinematic.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00134 | $0.01825 |
| Opus 5.5 | $0.00054 | $0.00730 |
| Sonnet 5.5 | $0.00027 | $0.00365 |
| Haiku 4.5 | $0.00013 | $0.00183 |
Grade A, and why
higgsfield-cinematic 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 1mo 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Higgsfield Cinematic Skill
What this skill does
Crafts production-ready cinematic video prompts and routes them to the best
Higgsfield model for film-grade output. On request, it assembles the full
parameter set, surfaces the credit cost, and — after explicit user
confirmation — generates the asset via the opt-in generation flow. The skill
also handles mood-board stills via the cinematic_studio_2_5 image path.
Model routing
Primary and fallback video models
| cinematic_studio_3_0 (primary) | veo3_1 (fallback) | |
|---|---|---|
| Rationale | Dedicated cinematic pipeline; default for all film-grade video | Photorealism + native audio when the studio model is unavailable or voiced output is needed |
| Aspect ratios | 16:9, 9:16, 1:1 |
16:9, 9:16 only — no 1:1 |
| Duration | 4–15 s (continuous range) | 4, 6, 8 s (discrete set only) |
| Tunable params | None — pass only aspect_ratio and duration |
quality {basic, high, ultra}; model {veo-3-1-preview, veo-3-1-fast} |
| Media roles | image, start_image, end_image (optional) |
start_image only (max 1) |
| Native audio | No | Yes |
Routing rule: Use cinematic_studio_3_0 by default. Only fall back to
veo3_1 when (1) the primary model is unavailable, or (2) the user wants
native audio or explicitly photorealistic output and, after being told
what they give up, accepts veo3_1's constraints: no 1:1 aspect ratio,
discrete durations only (4/6/8 s instead of the continuous 4–15 s
range), and start_image only (no end_image). If the user has not been
informed of these trade-offs, stay on cinematic_studio_3_0 and let them
decide — never switch silently.
MODEL-06 directive: If a parameter is rejected at generation time, call
higgsfield:models_explore with the target model name to re-verify the live
schema. The live catalog is the authoritative source — never guess parameter
values. Full parameter tables: references/model-specs.md.
What ships with it
4 files 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.
- 1mo ago First seen · 146 lines · 134 tokens per session scan A 732a45cf664c
higgsfield-cinematic is a skill published in the GitHub repository pixelab-ch/higgsfield-skills (10 stars, last pushed 5mo ago), licensed MIT. It adds 134 tokens to every session and 1,825 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
create-short
Create a short-form vertical video (TikTok, Instagram Reels, YouTube Shorts). Optimized 9:16 pipeline with a live Studio preview, auto-captions, hook-first structure, and background music mood selection; renders to MP4 only when you ask.
create-video
Full video production pipeline — from a text prompt to a live Studio preview with voiceover, music, sound effects, stock footage, and motion graphics, rendered to MP4 when you ask. The flagship command of Remotion Superpowers.
review-video
Review a Remotion video with AI vision. Starts with a cheap local check of rendered still frames, then has TwelveLabs watch the full render and score it against a JSON rubric (pacing, composition, text legibility, audio sync and more) with timestamped fixes, applies the fixes and re-reviews. The feedback loop that…
add-captions
Add TikTok-style, karaoke, YouTube or minimal captions to your Remotion video. Gets word-level captions through the official remotion-captions flow (whisper-webgpu, or ElevenLabs Scribe via @remotion/elevenlabs when there's no GPU), or imports the user's SRT with parseSrt, places one official caption element per clip…
analyze-footage
Analyze existing video files with TwelveLabs AI. Get a timestamped scene map of your footage, ask questions about it, find specific moments across a library, and get the best clips with timestamps for Remotion.
generate-clip
Generate AI video clips for your Remotion project. Create unique footage from text descriptions or animate still images into video — no stock footage needed.