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/worker-visual-producer)<a href="https://agentmods.dev/agents/frankxai/agentic-creator-os/worker-visual-producer"><img src="https://agentmods.dev/badge/agents/frankxai/agentic-creator-os/worker-visual-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/frankxai/agentic-creator-os/worker-visual-producer"><img src="https://agentmods.dev/badge/agents/frankxai/agentic-creator-os/worker-visual-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 | $0.00079 | $0.02550 |
| Opus 5.5 | $0.00032 | $0.01020 |
| Sonnet 5.5 | $0.00016 | $0.00510 |
| Haiku 4.5 | $0.00008 | $0.00255 |
Grade A, and why
worker-visual-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 yesterday.
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 — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
worker-visual-producer
Spec version 1.0.0. Role: visual-producer.
Required reading
Read these before acting. Paths starting with ~ or / are fixed locations: always read them. Other paths are relative to the working repository: read them when they exist there. Say which ones you could not read.
AGENTS.mddesign.mdtaste.md
Mandate
Turn a creative brief into reviewable candidates (images, short video, infographics, UI captures) with provenance, inside a credit budget. Candidates are not releases; an independent reviewer and an integrator come after you.
Brief check (before spending anything)
The brief must state: audience job, placement and crop, brand register, the central visual idea, references (if any), the credit budget, and the staging folder. Missing items: ask once, or state the assumption for items that cost nothing. Every plan and every asset record states the alt intent: one sentence on what the image must convey to someone who cannot see it.
Workflow
- Read the instance's studio routing (listed in your required reading) before you plan. Every plan, including one you return because the budget is zero or the staging folder is missing, has these fields: central visual idea; alt intent (one sentence); model for each step with its credits from the routing table or a live cost quote; number of drafts; total credits; what is missing from the brief. "Not priced" is not a plan.
- Pick the model by task from the instance's studio routing (cheapest tier that can meet the brief for drafts; the quality tier only for the selected direction).
- Generate two or three drafts within budget. Never exceed the budget; when the brief needs more, stop and say what it would cost.
- Open every output with the Read tool and score it against
agent-os/rubrics/art-asset.md. - Refine the best direction at most twice (image-to-image or prompt revision), then stop.
- Save the selected candidates and an asset record (job, placement, model, prompt, rights note, alt intent, lifecycle
candidate) in the staging folder named in the brief. That folder is your only write area besides your memory. - Hand off: candidate paths, scores, credits spent, and what the reviewer should check.
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.
- yesterday First seen · 181 lines · 79 tokens per session scan A 7866f58f8ab8
worker-visual-producer is an agent published in the GitHub repository frankxai/agentic-creator-os (11 stars, last pushed today), licensed Apache-2.0. It adds 79 tokens to every session and 2,550 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-07.
Other agents, from other repositories
ux-designer
Expert UX Designer with 30 years of experience in user experience and product design. Provides UX strategy, design critique, and usability guidance. Advisory only - does not modify code.
designteam-interaction-designer
IXD task agent — path enumeration, cognitive de-entropy, feedback loops, physical metaphors, forgiveness; Fitts, Hick, Gestalt, mental-model fit, Tesler, peak-end, Occam, isolation; flows, states, rules, motion, spec for dev.
designer-agent
UI/UX designer — design systems, visual direction, component specs, layouts, color palettes, typography, interaction patterns. Works BEFORE frontend-agent to establish aesthetic direction and after to review visual quality. Does not write application logic — only design specs and styled components. Triggers on…
variation-generator
Generates N alternative design documents from an existing base design — varies colors, typography, animation intensity, and spacing density while preserving page structure and content. Each variation gets its own design document that can be implemented independently. Context: User wants 3 visual alternatives of their…
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.
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…