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 calesthio/generative-media-skills --skill higgsfield-videogit clone --depth 1 https://github.com/calesthio/generative-media-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/calesthio/generative-media-skills/higgsfield-video)<a href="https://agentmods.dev/skills/calesthio/generative-media-skills/higgsfield-video"><img src="https://agentmods.dev/badge/skills/calesthio/generative-media-skills/higgsfield-video/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/calesthio/generative-media-skills/higgsfield-video"><img src="https://agentmods.dev/badge/skills/calesthio/generative-media-skills/higgsfield-video.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 155 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00183 | $0.06018 |
| Opus 5 | $0.00092 | $0.03009 |
| Sonnet 5 | $0.00037 | $0.01204 |
| Haiku 4.5 | $0.00018 | $0.00602 |
Grade A, and why
higgsfield-video 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 9d 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 — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Higgsfield video
What Higgsfield is, and the one fact that governs everything
Higgsfield (higgsfield.ai) is an aggregator plus a control layer. It is not a single model. It is a workspace that:
- Fronts third-party video models you could otherwise reach directly (Kling, Veo, Seedance, Wan, MiniMax, and — until its shutdown — Sora), and
- Adds its own in-house layer on top:
Soul(image generation +Soul IDcharacter identity),DoP(an image-to-video engine built around 100+ camera-motion presets),Popcorn(editing/inpaint), andCinema Studio(a multi-shot filmmaking environment that orchestrates all of the above).
The governing fact (documented): an aggregator inherits its models' limits. Any claim about duration, resolution, physics, audio, or content moderation applies to the specific underlying model, not to "Higgsfield." When you reason about a task, first decide which model runs the shot, then apply that model's constraints. A statement like "Higgsfield does 4K with native audio" is only true for the models that do (Veo, Seedance) and false for the ones that don't. Track the model, not the brand.
Verified 2026-07-10. Model lineups, versions, and prices below are volatile — re-verify the live in-app model picker and pricing page before committing credits or quoting a client.
When Higgsfield is the right tool (and when it isn't)
Route through Higgsfield when:
- You want to compare several models on the same prompt without holding accounts and billing at Kling, Google, ByteDance, etc. — side-by-side model switching in one workspace is the core value. (First-party claim.)
- You need Higgsfield's distinctive control layer —
Soul IDcharacter consistency, theDoPcamera-preset library, orCinema Studio's multi-shot rig controls — which do not exist at the raw model providers. - You want one credit wallet and one content policy across a mixed-model shoot.
- The user explicitly names Higgsfield, Soul, DoP, or Cinema Studio.
What ships with it
1 file 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.
- 9d ago First seen · 212 lines · 183 tokens per session scan A 61c755e405ee
higgsfield-video is a skill published in the GitHub repository calesthio/generative-media-skills (171 stars, last pushed 2mo ago), licensed MIT. It adds 183 tokens to every session and 6,018 once invoked, about $0.0009 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 2026-09-03.
Other skills, from other repositories
cliptalk-cover-director
Produces evidence-backed cover candidates and reviewable cover variants for a ClipTalk video. Use when the user asks for a cover, poster frame, thumbnail, or multiple cover directions; do not use for timeline editing or social-video reframing.
cliptalk-smart-reframe
Creates a subject-aware, time-varying crop track and a review-only social-format preview from an accepted ClipTalk cut. Use for automatic vertical, square, or portrait reframing; do not use for a fixed manual crop or before content editing is accepted.
cliptalk-content-extractor
Locates and assembles source passages matching a semantic request. Use for extracting explanations, topics, quotes, demonstrations, or other specifically described content.
cliptalk-interview-editor
Produces a coherent interview edit by combining speaker discovery, topic selection, dialogue context, cleanup, subtitles, and preview. Use for interviews, podcasts, testimonials, or question-and-answer recordings.
cliptalk-shortform-hook-director
Finds and assembles a reviewable short-form cut with a strong opening hook. Use for Shorts, Reels, social clips, talking-head cutdowns, or requests for a punchier opening.
cliptalk-social-reframe-exporter
Creates a review-only 9:16, 4:5, 1:1, or 16:9 version from an existing accepted ClipTalk cut, then checks the rendered preview. Use only when a cut already exists and the user asks to adapt it for Shorts, Reels, Douyin, Xiaohongshu, WeChat Channels, or square feeds; do not use when the user still needs content found…