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 agentmods add commands/frankxai/agentic-creator-os/infogeniusgit 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/commands/frankxai/agentic-creator-os/infogenius)<a href="https://agentmods.dev/commands/frankxai/agentic-creator-os/infogenius"><img src="https://agentmods.dev/badge/commands/frankxai/agentic-creator-os/infogenius.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.02154 |
| Opus 5 | $0.00000 | $0.01077 |
| Sonnet 5 | $0.00000 | $0.00431 |
| Haiku 4.5 | $0.00000 | $0.00215 |
Grade A, and why
infogenius 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 2d 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 — 255 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/infogenius - Grounded Visual Knowledge Generation
Research-First Image Generation - Facts → Visual Prompt → High-Quality Image
Pipeline Overview
╔═══════════════════════════════════════════════════════════════════════════╗
║ INFOGENIUS VISUAL PIPELINE ║
║ "Ground in Research, Render with Precision" ║
╠═══════════════════════════════════════════════════════════════════════════╣
║ Step 1: Research → Step 2: Craft Prompt → Step 3: Generate Image ║
║ (Web Search) (Style + Audience) (Nano Banana MCP) ║
╚═══════════════════════════════════════════════════════════════════════════╝
Step 1: GATHER REQUIREMENTS
Ask the user or parse from their request:
Required:
- Topic: What to visualize (e.g., "how photosynthesis works", "quantum entanglement")
Options (with defaults): 2. Visual Style (default: Standard):
standard- Clean scientific illustrationminimalist- Bauhaus, flat vector, 2-3 colors, negative spacephotorealistic- Cinematic lighting, 8K, detailed textures3d- 3D Isometric, claymorphism, studio lightingtechnical- Technical Blueprint, ink sketch, annotationsfuturistic- Cyberpunk HUD, neon lines, holographicvintage- 19th century lithograph, sepia, engraving stylecartoon- Educational comic, vibrant, cel-shaded
-
Audience Level (default: general):
elementary- Ages 6-10, bright, simple, fun iconshighschool- Standard textbook, clean, accuratecollege- Academic journal, high detail, data-richexpert- Technical schematic, extremely dense, precise
-
Aspect Ratio (default: 16:9):
16:9- Widescreen (infographics, presentations)1:1- Square (social media)9:16- Vertical (mobile, stories)
Step 2: RESEARCH WITH WEB GROUNDING
Use WebSearch to gather accurate, up-to-date facts:
WebSearch: "{topic} facts key information {current year}"
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.
- 2d ago First seen · 255 lines · 0 tokens per session scan A eb1d0bbf948f
infogenius is a command published in the GitHub repository frankxai/agentic-creator-os (10 stars, last pushed 2d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 2,154 tokens. 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 commands, from other repositories
document-app
Reverse-engineer an AI-built codebase into the system documents reviewers and auditors need — a core set (architecture, flows, permissions, variables) plus conditional docs (emails, cron, SEO, automation) when they apply.
write-stories
Break a feature into backlog items — user stories, job stories, or WWA format with acceptance criteria.
stakeholder-map
Build a political stakeholder map for a launch or GTM initiative.
meta-synthesis
Detect cross-skill patterns and propose brain updates.
meta-verify
Run a second-pass quality check on skill output before delivery.
brief
Build a GACCS campaign brief (Goals, Audience, Creative, Channels, Stakeholders).