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.
git clone --depth 1 https://github.com/black-forest-labs/skillsWrote 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/plugins/black-forest-labs/skills/flux-3-video)<a href="https://agentmods.dev/plugins/black-forest-labs/skills/flux-3-video"><img src="https://agentmods.dev/badge/plugins/black-forest-labs/skills/flux-3-video/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/plugins/black-forest-labs/skills/flux-3-video"><img src="https://agentmods.dev/badge/plugins/black-forest-labs/skills/flux-3-video.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
flux-3-video 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 5d 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
{
"name": "flux-3-video",
"description": "BFL skills for FLUX 3 video generation including prompt readiness checks, cinematic shot craft for text-to-video, keyframes and video continuation, synchronized audio and dialogue, period and archival format looks, request construction with async polling and downloads, and finished product ads with voiceover and deterministic assembly",
"source": "./",
"strict": false,
"skills": [
"./skills/flux-3-video",
"./skills/flux-3-prompt-doctor",
"./skills/flux-3-cinematic-inserts",
"./skills/flux-3-keyframes-continuation",
"./skills/flux-3-audio-dialogue",
"./skills/flux-3-generate",
"./skills/flux-3-archival-formats",
"./skills/flux-3-product-ads"
],
"author": {
"name": "Black Forest Labs"
}
}What it installs
The manifest is a name and a version. 8 skills travel with it, and installing the plugin installs all of them — 315 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill flux-3-product-ads A 66 tokens
- Skill flux-3-archival-formats A 41 tokens
- Skill flux-3-keyframes-continuation A 41 tokens
- Skill flux-3-prompt-doctor A 30 tokens
- Skill flux-3-audio-dialogue A 35 tokens
- Skill flux-3-video A 32 tokens
- Skill flux-3-generate A 30 tokens
- Skill flux-3-cinematic-inserts A 40 tokens
What ships with it
1 file beside marketplace.json#flux-3-video in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago First seen · 19 lines scan A ec5f11564cc5
flux-3-video is a plugin published in the GitHub repository black-forest-labs/skills (115 stars, last pushed 3d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-09-03.
Other plugins, from other repositories
higgsfield-brief-to-pipeline
Turns a brief plus a folder of reference images into an optimal, credit-aware Higgsfield pipeline. Shows an HTML process preview as a mandatory approval gate before spending any credits, then executes stage-by-stage with auto-verification, human gates, and zero-credit deterministic text/dimension overlays.
diffusers
Conventions and task skills for contributing to diffusers.
illo
Original editorial illustrations where a recurring mascot performs the idea — fourteen bundled looks, custom characters via a built-in character builder, palettes derived from your own site's colors. Ships the illo Agent Skill and its three-backend image engine: free generation through your Codex or Grok CLI…
runapi
RunAPI model discovery, pricing lookup, media task creation, polling, and balance checks for Claude Code.
codex-image
Generate and edit images from Claude Code by dispatching to Codex CLI's built-in imagegen skill.
media-generation marketplace
Generate images, videos, speech, and transcriptions through 13 AI providers (OpenAI, Google, Azure, ElevenLabs, Deepgram, Fal.ai, Luma, Replicate, Stability, Runway, OpenRouter, MiniMax, Edge TTS). Supports 100+ models with structured JSON output for agent integration.