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-pipelineWrote 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-pipeline)<a href="https://agentmods.dev/skills/osidemedia/higgsfield-ai-prompt-skill/higgsfield-pipeline"><img src="https://agentmods.dev/badge/skills/osidemedia/higgsfield-ai-prompt-skill/higgsfield-pipeline/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-pipeline"><img src="https://agentmods.dev/badge/skills/osidemedia/higgsfield-ai-prompt-skill/higgsfield-pipeline.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 | $0.00082 | $0.11920 |
| Opus 5 | $0.00041 | $0.05960 |
| Sonnet 5 | $0.00016 | $0.02384 |
| Haiku 4.5 | $0.00008 | $0.01192 |
Grade A, and why
higgsfield-pipeline 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 12d 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 — 1,117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Higgsfield Production Pipeline
QUICK FACTS
Generated-checked block (scripts/build_index.py verifies anchors). Read the linked sections for full context — these lines are routing aids, not the rules themselves.
- 8-stage Master Chain: Popcorn → Seedream/Soul → Animate → Recast → Lipsync → Vibe Motion → Upscale → Assemble; most good short-form uses 3–5 stages →
- Lock 9 project fields before touching any tool; "what must stay consistent" is the load-bearing one →
- One job per scene — six scene purposes; a good scene prompt answers six questions →
- 7 reusable prompt-module types: character identity, camera, lighting, style, motion, negative prompt, continuity →
- 80% rule: keep what worked, fix only the mistake; every diagnosed failure becomes a new negative rule →
- Build in 8 passes: Concept → Project script → Scene breakdown → Shot list → Image prompts → Video prompts → Review → Fix →
- Use the EXACT same character description (copy-paste) in every Popcorn prompt — continuity without Soul ID →
- Seedream edits the image, not the video — always edit the Hero Frame before animating, never after →
- Model by scene type: Sora 2 for stunts/epic ("one continuous shot, no cuts"), Kling 2.6 portraits, Seedance quiet interiors →
- Recast swaps identity while preserving motion, camera, and lighting; the "prompt" is the reference image you upload →
- Audio routing: existing video + speech → Lipsync Studio; new content with audio → Kling 3.0; talking head → Kling Avatars 2.0 →
- Higgsfield has no native timeline editor — assemble in DaVinci Resolve / Premiere / CapCut →
- Pipeline E hard rules: 15-second cap per scene, one generation per style, feed the previous scene's video as continuity reference →
- Soul Cinema keyframes: deliberately short 5–15 word prompts with enhancer ON — long prompts starve the enhancer →
- Never describe character age in Seedance prompts; >15s per scene degrades prompt adherence — split the scene →
- No extend button: attach the accepted clip as a video reference + open with "The scene continues." — and match the source's resolution AND duration →
- Cap seamless extension chains at 2 (hard ceiling 3); re-anchor from ORIGINAL canonical refs, break chains with B-roll →
- An attached source clip carries the state — prompt only the delta; motion vectors, camera-move phase, audio phase stay in prose when handing off from a still frame →
- End extension prompts on a camera-angle change so the join reads as coverage; plan transitions ahead (last-channel-on-TV trick) →
- Draw a top-down schema when 2+ characters, a key prop placement, or complex camera geometry — prompt in absolute terms ("A 2m from B") →
- Never animate a "good enough" image; if the character looks wrong in the Hero Frame, Recast is the fix — not the animation prompt →
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.
- 12d ago First seen · 1,117 lines · 82 tokens per session scan A 229d4cba3cb1
higgsfield-pipeline is a skill published in the GitHub repository OSideMedia/higgsfield-ai-prompt-skill (531 stars, last pushed 20d ago), licensed MIT. It adds 82 tokens to every session and 11,920 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.
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"…
dramaclaw
A skill for answering identity and self-introduction questions, and for working with the DramaClaw/NovelVideo pipeline. The description also covers turning novels or stories into short vertical videos.
ai-media-generator
A workflow for turning ideas into prompts for AI-generated images, videos, and music across several media platforms. When needed, it can also send those prompts to the chosen platform through browser automation.
kling-ai
Write and improve prompts for Kling AI video generation, and pick the right Kling model for the job. Covers image-to-video, text-to-video, multi-shot storyboards, talking avatars from one photo plus audio, motion transfer, video editing of an existing clip, Element Reference for character consistency, Voice Control…
minimax-h3
Write, debug and structure prompts for MiniMax H3 video generation (T2VA, I2VA, FL2VA, L2VA, Ref2VA) and configure its ComfyUI workflow. Use when the user mentions MiniMax H3, minimaxh3, fl2va, ref2va, MiniMaxH3ReferenceToVideo, reference-to-video, asks to animate a photo, write a video prompt, pick a model quant, or…