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/dsm5e/aso-trackernpx agentmods add skills/dsm5e/aso-tracker/higgsfield-cinemaWrote 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/dsm5e/aso-tracker/higgsfield-cinema)<a href="https://agentmods.dev/skills/dsm5e/aso-tracker/higgsfield-cinema"><img src="https://agentmods.dev/badge/skills/dsm5e/aso-tracker/higgsfield-cinema/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/dsm5e/aso-tracker/higgsfield-cinema"><img src="https://agentmods.dev/badge/skills/dsm5e/aso-tracker/higgsfield-cinema.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 | $0.00153 | $0.22231 |
| Opus 5 | $0.00077 | $0.11116 |
| Sonnet 5 | $0.00031 | $0.04446 |
| Haiku 4.5 | $0.00015 | $0.02223 |
Grade A, and why
higgsfield-cinema 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.
How it starts
The opening of the file, as written. The whole thing — 1,770 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Higgsfield Cinema Studio 2.5
Cinema Studio is Higgsfield's professional filmmaking environment — a full production workflow for multi-shot, character-consistent cinematic content. It's fundamentally different from single-clip generation: you're building sequences, not individual videos.
Cinema Studio vs Standard Generation
| Standard Generation | Cinema Studio 2.5 | Cinema Studio 3.0 (Business/Team Plan) | Cinema Studio 3.5 | |
|---|---|---|---|---|
| Output | Single clip | Multi-shot sequence | Multi-shot sequence | Multi-shot sequence |
| Character consistency | Manual / Soul ID only | Reference Anchor system | @ reference system (up to 9 images) | @ reference system (extends 3.0) |
| AI actor generation | Not available | Soul Cast — generate actors from parameters (no photos) | Soul Cast — General (2K) / Character (4K) / Location (4K) modes, 0.125 credits | Same Soul Cast surface — see 3.0 |
| Camera control | Named presets | Director Panel (18 movements) | Director Panel + Smart (auto camera planning) | Camera Settings 4-axis panel (Camera Body / Lens / Focal Length / Aperture) — see Cinema Studio 3.5 section |
| Optical physics | Not available | Full camera body + lens stack | Not available | Available — restored via Camera Settings panel (different vocabulary from 2.5 — see Cinema Studio 3.5 section) |
| Color grading | Not available | Built-in suite (temp, contrast, grain, bloom, etc.) | Not available | Available — Color Palette axis in Style Settings panel (8 named palettes) |
| Shot structure | One prompt = one clip | Up to 6 scenes, 12s total max, per-scene config | Smart (auto) + Custom multi-shot (up to 6 scenes, 15s) | Multi-shot supported — Duration 4s–15s |
| 3D exploration | Not available | Gaussian splatting — move inside any generated image | Not available | Same as 3.0 (not available) |
| Batch generation | Not available | Grid generation — up to 16 variations per credit | Not available | Configurable Batch Size (exploration multiplier) |
| Storyboard | Not available | Higgsfield Popcorn integration | Not available | Same as 3.0 |
| Speed control | Not available | Speed Ramp (6 modes) | Speed Ramp (7 modes + Bullet Time, Hero Moment) | Not separately tested in this release — see UI for 3.5-specific surface |
| Genre | Style descriptions | 8 named genres | 7 genres (General, Action, Horror, Comedy, Noir, Drama, Epic) | Manual catalog (General, Action, Horror, Comedy, Noir, Drama, Epic + others surfaced in UI) |
| Audio | Model-dependent | On/Off | On/Off (native dual-channel stereo) | On/Off (generated alongside video) |
| Video resolution | Model-dependent | Up to 1080p | Up to 720p (may increase) | 480p / 720p / 1080p (three-tier) |
| Image resolution | Model-dependent | Up to 4K | Up to 4K (Character/Location) · Up to 2K (General) | Not separately tested in this release |
| Max video duration | Model-dependent | 12s | 15s | 15s |
| Aspect ratios | Model-dependent | 6 options | 7 options (+ 21:9 ultrawide) | 7 options (Auto, 16:9, 9:16, 4:3, 3:4, 1:1, 21:9) |
| Plan requirement | All plans | All plans | Business/Team plan only | Plan availability not separately verified in this release — see Higgsfield plan documentation |
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.
- 11d ago First seen · 1,770 lines · 153 tokens per session scan A 1fc73265ff12
higgsfield-cinema is a skill published in the GitHub repository dsm5e/aso-tracker (137 stars, last pushed 24d ago), licensed MIT. It adds 153 tokens to every session and 22,231 once invoked, about $0.0008 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
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.
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…
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.
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).
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
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.