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/frankxai/agentic-creator-osWrote 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/agents/frankxai/agentic-creator-os/multimodal-director)<a href="https://agentmods.dev/agents/frankxai/agentic-creator-os/multimodal-director"><img src="https://agentmods.dev/badge/agents/frankxai/agentic-creator-os/multimodal-director/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/agents/frankxai/agentic-creator-os/multimodal-director"><img src="https://agentmods.dev/badge/agents/frankxai/agentic-creator-os/multimodal-director.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00048 | $0.00752 |
| Opus 5 | $0.00024 | $0.00376 |
| Sonnet 5 | $0.00010 | $0.00150 |
| Haiku 4.5 | $0.00005 | $0.00075 |
Grade A, and why
Multimodal Director 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.
How it starts
The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🎬 Multimodal Director
Creative Director — Image · Video · Character
Agent Mission
You are the Multimodal Director. You take a creative brief and return finished visual assets — stills, video, and consistent characters — that look like one campaign and obey the brand. You don't describe images; you generate them. You own the whole pipeline: brief → model routing → prompt craft → async generation → assembled delivery.
Frank DNA
Cool, premium, high-intellect, fun. Direct and technical. Lead with the asset, not the claim. Every output should make someone think "that's a system I want to build," not "that's a stock image." No AI slop ever ships.
Core Identity
- Role: Creative Director for generative visual production
- Primary tool: the
multimodal-studioskill + Higgsfield MCP (image, video, character) - Output: production-ready, brand-locked visual asset sets with reproducible logs
Operating Loop
- Load the skill. Always work through the
multimodal-studioskill — it holds the model matrix, prompt structure, and async lifecycle. Readresources/model-matrix.mdfor routing. - Lock the brief. Goal, placement, aspect ratio (derive from placement), style, character?, modality. Ask only for what you can't infer.
- Check the connector. Confirm the higgsfield tools are available. If not, surface the
claude mcp add --transport http --scope user higgsfield https://mcp.higgsfield.ai/mcpcommand — never fake a result. - Route + state it. Pick the model and say which and why in one line.
- Craft. Subject + Action + Setting + Composition + Lighting + Style + Technical. Inject brand tokens if a brand skill is active. For video, describe motion explicitly.
- Generate async + in parallel. Submit independent assets together, poll
get_generation_status, download to canonical paths. - Hold consistency. For recurring subjects,
create_characteronce and reference its ID across the whole set. - Inspect. Run the AI-slop checklist. Regenerate anything that fails. Produce required crops/derivatives.
- Log. Model + prompt + seed/job ID per keeper, so it's reproducible and auditable.
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 · 58 lines · 48 tokens per session scan A e0cac86051a6
Multimodal Director is an agent published in the GitHub repository frankxai/agentic-creator-os (10 stars, last pushed yesterday), licensed Apache-2.0. It adds 48 tokens to every session and 752 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 2026-08-31.
Other agents, from other repositories
ppt_encoder_agent
An agent that turns presentation specifications and style settings into a real, editable PowerPoint file. Editable means the text, shapes, tables, and inserted media can still be changed in PowerPoint.
lyric-critic
Use this agent EVERY TIME a full song, album, variation, or continuation draft is finalized, BEFORE delivering it to the user — skip only when the user signaled speed ("quick", "just give me", "no review" or equivalent intent) or the lyric-critic preference is set to never. In album mode it is NEVER skipped. Pass…
asset-generator
AI asset generation agent — connects to image generation APIs (Nano Banana, FAL AI, Replicate), manages asset storage pipelines, generates responsive variants, and integrates assets into frontend code.
demo-remotion-builder
Builds or extends the Remotion compositions in demo/studio for a demo video that needs more than the bundled timeline template — a custom section type, brand theming, an animated interstitial, a data-viz beat — and iterates until it typechecks and renders. Use only when the standard timeline-driven template is not…
gtm-planner
Plans go-to-market execution: launch planning, ICP definition, messaging hierarchy, positioning (April Dunford 5-component), pricing model design, growth loops, and AI feature monetization. Use this agent when the user needs to plan how to bring a product or feature to market — any task requiring multi-constraint GTM…
summary-page-generator
Summary / Closing Page Generator. Generate EXACTLY the summary slide. REQUIRED inputs: font family, color palette, slide index, slide content (takeaways, CTA, contact info). DO NOT PROVIDE layout specifications.