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 metaspartan/cybara --skill fal-aigit clone --depth 1 https://github.com/metaspartan/cybaraWrote 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/metaspartan/cybara/fal-ai)<a href="https://agentmods.dev/skills/metaspartan/cybara/fal-ai"><img src="https://agentmods.dev/badge/skills/metaspartan/cybara/fal-ai/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/metaspartan/cybara/fal-ai"><img src="https://agentmods.dev/badge/skills/metaspartan/cybara/fal-ai.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 | $0.00045 | $0.00427 |
| Opus 5 | $0.00023 | $0.00214 |
| Sonnet 5 | $0.00009 | $0.00085 |
| Haiku 4.5 | $0.00005 | $0.00043 |
Grade A, and why
fal.ai 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.
What it actually says
fal.ai
Use Cybara's media generation tools instead of calling fal.ai directly:
image_generatefor images and image variationsvideo_generatefor queue-backed video modelsmusic_generatefor music and audio models
The provider accepts either FAL_KEY or FAL_API_KEY. Generated assets are saved under the workspace .cybara/media/ directory and returned as local paths.
Model Guidance
- Fast image drafts:
fal-ai/flux/schnell - Higher-quality image work: pass a specific fal model id in
model - Short videos:
fal-ai/minimax/video-01,fal-ai/kling-video, orfal-ai/veo3 - Music/audio:
fal-ai/minimax-music/v2.6,fal-ai/ace-step/prompt-to-audio, orfal-ai/stable-audio-25/text-to-audio
Examples
{"name":"image_generate","args":{"provider":"fal","model":"fal-ai/flux/schnell","prompt":"product photo of a compact AI workstation on a walnut desk","count":1}}
{"name":"video_generate","args":{"provider":"fal","model":"fal-ai/minimax/video-01","prompt":"a short cinematic orbit around a glassy desktop app icon","durationSeconds":5}}
{"name":"music_generate","args":{"provider":"fal","model":"fal-ai/minimax-music/v2.6","prompt":"focused ambient electronic loop for coding","durationSeconds":30,"format":"mp3"}}
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 · 39 lines · 45 tokens per session scan A 38972e8cea02
fal.ai is a skill published in the GitHub repository metaspartan/cybara (28 stars, last pushed today), licensed MIT. It adds 45 tokens to every session and 427 once invoked, about $0.0002 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
marketing-image
Skill "marketing-image" from KornLabs/truss, covering image, before starting, 1. image goal, 2. production approach and 3. technical context.
marketing-video
Skill "marketing-video" from KornLabs/truss, covering video, before starting, 1. video goal, 2. production approach and 3. technical context.
uiux-banner-design
Skill "uiux-banner-design" from KornLabs/truss, covering banner design - multi-format creative banner system, when to activate, prerequisites, workflow and step 1: gather requirements (askuserquestion).
composio-image-enhancer
Skill "composio-image-enhancer" from KornLabs/truss, covering image enhancer, when to use this skill, what this skill does, how to use and basic enhancement.
uiux-slides
Skill "uiux-slides" from KornLabs/truss, covering slides, when to use, subcommands, references (knowledge base) and routing.
ppt-generation
Use this skill when the user requests to generate, create, or make presentations (PPT/PPTX). Creates visually rich slides by generating images for each slide and composing them into a PowerPoint file.