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 OSideMedia/higgsfield-ai-prompt-skill --skill higgsfield-canvasgit clone --depth 1 https://github.com/OSideMedia/higgsfield-ai-prompt-skillWrote 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-canvas)<a href="https://agentmods.dev/skills/osidemedia/higgsfield-ai-prompt-skill/higgsfield-canvas"><img src="https://agentmods.dev/badge/skills/osidemedia/higgsfield-ai-prompt-skill/higgsfield-canvas/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-canvas"><img src="https://agentmods.dev/badge/skills/osidemedia/higgsfield-ai-prompt-skill/higgsfield-canvas.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 | $0.00143 | $0.02062 |
| Opus 5 | $0.00072 | $0.01031 |
| Sonnet 5 | $0.00029 | $0.00412 |
| Haiku 4.5 | $0.00014 | $0.00206 |
Grade A, and why
higgsfield-canvas 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 13d 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 — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Higgsfield Canvas — Node-Based Production Workspace
Canvas is a node-based editor where prompts, references, and generations from any Higgsfield model live on a single infinite board. Instead of running each generation in isolation, you connect nodes — a prompt feeds an image, an image feeds a video, a style branches into variations — so a whole scene or campaign becomes one continuous, re-runnable pipeline.
Canvas is its own top-level surface in the Higgsfield nav bar (alongside Image, Video, Cinema Studio, Marketing Studio). It is model-agnostic: it hosts the other models rather than being a mode inside any one of them, so this sub-skill routes model-specific craft back to the relevant sibling sub-skill.
Why Canvas matters for this skill. Canvas is another place to deploy the prompts this skill builds inside the Higgsfield workflow — instead of taking a finished prompt straight to the Image/Video generator or Cinema Studio, you drop it into a Prompt node on the board and wire it into a generator. The prompt-craft is identical (MCSLA scene prompts, Seedance prompt modes, GPT Image 2.0 formats — all still apply); Canvas just changes where the prompt is executed and lets one prompt feed a multi-step pipeline. Think of the Prompt node as the on-canvas home for everything the rest of this skill teaches.
Translated from Higgsfield's official Canvas guide (higgsfield.ai/canvas-intro)
plus the in-product Canvas screenshots and a canvas-workflow walkthrough.
1. When to use Canvas
Reach for Canvas when the work is a pipeline, not a single shot:
- A multi-shot scene or episode where one reference set drives several shot prompts.
- An ad campaign that fans one product/brand reference into many variants.
- A storyboard that flows assets → story beats → prompts → image/video generation in columns.
- Any repeatable pipeline you want to save as a template and re-run with swapped inputs.
For a single prompt-and-generate, the standard Image/Video tabs are simpler. Canvas earns its keep when steps connect.
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.
- 13d ago First seen · 177 lines · 143 tokens per session scan A 7d7d6eff7909
higgsfield-canvas is a skill published in the GitHub repository OSideMedia/higgsfield-ai-prompt-skill (531 stars, last pushed 20d ago), licensed MIT. It adds 143 tokens to every session and 2,062 once invoked, about $0.0007 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…
shaka-design-system
A shared design rulebook for Shaka content, covering themes, fonts, components, and visual principles. Other content-making tools read it as their common source of design rules.
reference-board
Build and lock reference boards before asset creation.
zhang-yimou-visual-ritual
Use this skill when the user wants Zhang Yimou-inspired visual symbolism, color systems, ritualized blocking, folk texture, mass choreography, ceremonial composition, visual metaphor, or large-image concept design for AI short drama. Apply public-source-backed principles; do not impersonate Zhang Yimou or copy…
archify
Create polished, validated architecture, workflow, sequence, data-flow, and lifecycle/state diagrams as explorable standalone HTML with inline SVG, dark/light themes, optional trace motion, and PNG/JPEG/WebP/SVG/WebM export. Accept plain-language requirements or pasted Mermaid flowchart, sequenceDiagram, and…
pixel2motion
Turn a raster logo (PNG/JPG/WebP/screenshot) into a clean minimal SVG with edge smoothness as the primary hard gate and IoU optimized as high as reasonably possible without a fixed global threshold, then into a choreographed logo animation delivered as standalone JS-rendered HTML, applying Disney's 12 animation…