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-cameraWrote 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-camera)<a href="https://agentmods.dev/skills/osidemedia/higgsfield-ai-prompt-skill/higgsfield-camera"><img src="https://agentmods.dev/badge/skills/osidemedia/higgsfield-ai-prompt-skill/higgsfield-camera/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-camera"><img src="https://agentmods.dev/badge/skills/osidemedia/higgsfield-ai-prompt-skill/higgsfield-camera.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 | $0.00047 | $0.06600 |
| Opus 5.5 | $0.00019 | $0.02640 |
| Sonnet 5.5 | $0.00009 | $0.01320 |
| Haiku 4.5 | $0.00005 | $0.00660 |
Grade A, and why
higgsfield-camera 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 — 458 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Higgsfield Camera Controls
Always reference camera controls by their exact preset name in prompts. Higgsfield recognizes these names directly.
QUICK FACTS
Routing aids — read the linked sections for the actual rules.
- Named preset tables by family: dolly / crane / orbit / zoom / follow / specialty / time-based / through-object / vehicle, plus angles and shot sizes — always cite the exact preset name →
- Layer max two compatible moves; sequenced combos get explicit timing; static-pan beats glide for most coverage →
- The camera is the emotional double of the focal character — 7 emotional registers map to camera prescriptions; arcs change the camera in named phases →
- [OFFICIAL] Lens + aperture chosen by shot purpose (85/100mm F1.4 tight emotional CU … 45mm macro F2.8), with standing focus-lock and distortion-forbid clauses →
- [OFFICIAL] Shot duration by type: flash establish 0.3–0.5s · dialogue line 3–7s · wordless reaction 5–10s · full-arc emotional CU 8–15s →
- Micro-moves need exact distances — state total travel + time ("10–15 cm over 7 seconds"); never write
zoomfor a physical move → - Cinema Studio 3.0: One-Move Rule, genre presets, reliable phrasing library, camera transfer via
@Video→ - What a
@Videoreference reads reliably (world, materials, physics, camera character) vs cannot do (frame-accurate continuation, identity) →
Dolly Movements
| Control | What it does | Best for | Prompt phrase |
|---|---|---|---|
| Dolly In | Smooth linear move toward subject | Intimacy, revelation, tension build | "Camera Dolly In toward her face" |
| Dolly Out | Smooth linear move away from subject | Isolation, departure, widening context | "Camera Dolly Out revealing the empty square" |
| Dolly Left | Lateral track to the left | Following horizontal movement, revealing scene | "Camera Dolly Left tracking alongside the runner" |
| Dolly Right | Lateral track to the right | Following horizontal movement, revealing scene | "Camera Dolly Right as the car accelerates" |
| Dolly Zoom In | Dolly forward + zoom out simultaneously | Vertigo, shock, realization (Hitchcock effect) | "Dolly Zoom In — subject stays size as background rushes away" |
| Dolly Zoom Out | Dolly back + zoom in simultaneously | Overwhelm, isolation, world closing in | "Dolly Zoom Out — city swallows the figure" |
| Super Dolly In | Exaggerated fast rush toward subject | Sudden shock, urgent revelation | "Super Dolly In on the handprint on the window" |
| Super Dolly Out | Exaggerated fast pull back | Dramatic reveal of scale, sudden context shift | "Super Dolly Out to reveal the entire burning city" |
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 Changed 072aaf7e30e0
- 1mo ago First seen · 458 lines · 47 tokens per session scan A 7ca41cd588c5
higgsfield-camera is a skill published in the GitHub repository OSideMedia/higgsfield-ai-prompt-skill (800 stars, last pushed 2d ago), licensed MIT. It adds 47 tokens to every session and 6,600 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
seedance-shotlist-director
Generate a director's shotlist as an editable HTML production board for Seedance 2.0. Use whenever the user provides a script, scene breakdown, story idea, or treatment to turn into a numbered shotlist with English Seedance prompts — trigger on "make a shotlist", "director’s shotlist", "break this script into…
vox-director
Turn ONE topic into a finished Vox-style paper-collage explainer / ad video, end to end on the Atlas Cloud API + local ffmpeg — script, collage keyframes, motion, voice-over, music, captions, all automated. Use this whenever the user wants a "Vox style" video, a paper/torn-paper collage animation, a "motion collage"…
sketch-correction-worker
Use when doing single-beat sketch quality control and preparing correction labels from a SuperTale project path and episode number. This skill turns one episode's selected sketches plus local script beat data into selectresult.jsonl, selectsummary.json, tasks.jsonl, and labels.jsonl for edit execution. Prefer using…
freezone
Use when the active chat surface is 虾画/Freezone/canvas, or when the user asks about canvas nodes, visual boards, selections, graph edits, canvas actions, layout, or Freezone short-video workflow work.
dramaclaw-workflows
Create, revise, confirm, run, or resume multi-node DramaClaw Freezone canvas workflows. Use for requests involving a workflow, several connected nodes, grouped production stages, storyboards, or text/image/video/audio pipelines; do not use for one standalone canvas operation.
workflows
Use in Freezone/虾画 chat when the user selects a Skill or asks to create, plan, analyze, or expand a dynamic canvas workflow for short drama, ads, ecommerce, product video, MV, text, image, video, or audio production.