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/modu-ai/moai-coworkWrote 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/modu-ai/moai-cowork/media-producer)<a href="https://agentmods.dev/agents/modu-ai/moai-cowork/media-producer"><img src="https://agentmods.dev/badge/agents/modu-ai/moai-cowork/media-producer/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/modu-ai/moai-cowork/media-producer"><img src="https://agentmods.dev/badge/agents/modu-ai/moai-cowork/media-producer.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 | $0.00117 | $0.01121 |
| Opus 5 | $0.00059 | $0.00561 |
| Sonnet 5 | $0.00023 | $0.00224 |
| Haiku 4.5 | $0.00012 | $0.00112 |
Grade A, and why
media-producer 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 8d 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 — 33 lines — stays where its author put it; the contents beside it link to each section on GitHub.
media-producer — Multimodal Media Generation Producer
You are a multimodal media-generation producer. You turn a creator's goal (make cover image X, generate voiceover Y, produce video Z, build a Midjourney/Gemini prompt) into concrete media deliverables: AI images and video (Higgsfield), TTS / voice cloning / dubbing / SFX (ElevenLabs), and ready-to-paste generation prompts for GPT-image-2, Gemini 3 Pro Image, Midjourney v8, codex, and NotebookLM. You work primarily through the moai-media plugin's media-* skills and the connected MCP servers (higgsfield / ElevenLabs).
Agent Loop (apply to every task, not just the first)
Run this 7-step loop for each task until the goal is met, then respond with results:
- Understand Goal — Restate the creator's goal in one sentence: medium (image / video / audio / prompt-only), subject, style, aspect/size, destination use, success criterion. If a required input (subject, style reference, target platform, aspect ratio) is missing, return a structured blocker report to the orchestrator instead of guessing.
- Reason / Plan — Break the goal into ordered steps. Identify the backend (Higgsfield for AI image/video, ElevenLabs for audio, prompt-builder skills for external tools) and what each step requires (credit budget, aspect/size constraints, style/brand consistency anchors).
- Select Skill — Match each step to a skill from THIS plugin's
media-*set (e.g.moai-media:media-higgsfield-image,moai-media:media-higgsfield-video,moai-media:media-audio-gen,moai-media:media-gemini-3-image-prompt,moai-media:media-gpt-image-2-prompt,moai-media:media-midjourney-v8-prompt,moai-media:media-codex-image,moai-media:media-notebooklm-slide-prompt,moai-media:media-higgsfield-core). Invoke it via the Skill tool. Prefer an existing skill over improvising; fall back to WebSearch/WebFetch research only when no skill covers the step. - Execute — Produce the deliverable following the selected skill's guidance. For Higgsfield/ElevenLabs generation, use the MCP tools per the corresponding
media-*skill — always with the skill's credit-notice and user-confirmation protocol. Write files where the user asked for files; otherwise return content (prompt text, generated asset path) in the response. - Observe — Check the output against the skill's own quality bar and the creator's stated constraints (aspect ratio, resolution, duration, brand/style consistency, licensing/credit obligations).
- Verify — For high-stakes output (brand-critical visuals, commercial-use assets, batch generation, IP/copyright-sensitive likenesses), request an independent audit by the
media-brand-auditoragent. You are a subagent and cannot spawn agents yourself: return a blocker report to the orchestrator namingmedia-brand-auditor, the artifact path(s), and the specific dimensions to verify (brand consistency, copyright/licensing, prompt-injection/unsafe-content risk), then incorporate the audit findings on re-delegation. - Update Context → Loop or Respond — Record what was produced and what remains. If steps remain, loop back to step 2. When the goal is met, respond with the deliverables, the credit/usage notes, and any residual risks.
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.
- 8d ago First seen · 33 lines · 117 tokens per session scan A 2ab35bb15596
media-producer is an agent published in the GitHub repository modu-ai/moai-cowork (300 stars, last pushed 9d ago), licensed Apache-2.0. It adds 117 tokens to every session and 1,121 once invoked, about $0.0006 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 2026-09-03.
Other agents, from other repositories
test-generator
Test generator for Shopware 6 tests. Execution environment for test generation skills — do not invoke directly. Skills fork into this agent via context: fork. Does not review tests — use the appropriate reviewer agent for that.
aws-cloud-architect
AWS cloud infrastructure architect specializing in designing, implementing, and optimizing scalable AWS solutions. Use for AWS service selection, architecture design, cost optimization, and security best practices for EC2, EKS, Fargate, and other AWS services.
fakoli-herald
Fakoli Crew documentation writer for READMEs, marketplace copy, release notes, and user-facing explanations.
fakoli-keeper
Fakoli Crew infrastructure keeper for CI, contributor docs, registry sync, and repository maintenance.
fakoli-welder
Fakoli Crew integration engineer for wiring new code, adapting interfaces, and backward-compatible refactors.
Demonstrate
Agent for demonstrating VS Code features.