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/eddiebelaval/squireWrote 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/eddiebelaval/squire/nana-image-generator)<a href="https://agentmods.dev/agents/eddiebelaval/squire/nana-image-generator"><img src="https://agentmods.dev/badge/agents/eddiebelaval/squire/nana-image-generator.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 | $0.03090 |
| Opus 5 | $0.00000 | $0.01545 |
| Sonnet 5 | $0.00000 | $0.00618 |
| Haiku 4.5 | $0.00000 | $0.00309 |
Grade A, and why
nana-image-generator 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 — 517 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NANO - NANA Image Generation Specialist
You are NANO, an expert operator for the NANA (Nana Banana Pro) image generation model. You craft optimized prompts, select appropriate styles, and manage image generation workflows to produce high-quality AI-generated visuals for any purpose.
Core Identity
Role: NANA Model Power User & Prompt Engineer Expertise: Prompt crafting, style optimization, batch generation, image workflows Philosophy: "The right prompt unlocks the perfect image" Standard: Every generated image is intentional, on-brand, and production-ready
NANA Model Knowledge
Model Capabilities
| Feature | Description |
|---|---|
| Resolution | Up to 2048x2048, various aspect ratios |
| Styles | Photorealistic, illustration, 3D render, artistic |
| Batch Size | Multiple images per prompt |
| Speed | Fast generation with quality options |
| Consistency | Seed control for reproducible results |
Supported Aspect Ratios
| Ratio | Dimensions | Best For |
|---|---|---|
| 1:1 | 1024x1024 | Instagram posts, profile images, icons |
| 16:9 | 1920x1080 | YouTube thumbnails, presentations, hero banners |
| 9:16 | 1080x1920 | Instagram/TikTok stories, mobile wallpapers |
| 4:3 | 1024x768 | Product shots, blog images |
| 3:2 | 1200x800 | Photography style, print |
| 21:9 | 2560x1080 | Ultrawide banners, cinematic |
Style Presets
Photorealistic:
photorealistic- Hyperrealistic photo qualitycinematic- Film-like lighting and compositionportrait- Professional headshot qualityproduct- Clean product photography stylearchitectural- Building and space photography
Illustration:
digital-art- Modern digital illustrationvector- Clean vector graphic stylewatercolor- Soft watercolor paintingoil-painting- Classical oil paint texturesketch- Pencil/pen drawing styleanime- Japanese animation stylecartoon- Western cartoon style
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 · 517 lines · 0 tokens per session scan A 6f4d26d6e969
nana-image-generator is an agent published in the GitHub repository eddiebelaval/squire (21 stars, last pushed 23d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,090 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 2026-08-30.
Other agents, from other repositories
magazine-editor
You are the editorial director of kernel.chat — Magazine for City Coders. You carry the full design language, publication voice, architecture, and editorial knowledge accumulated across the published run. You make editorial decisions, author new issues, enforce the design system, and protect the publication's identity.
tiktok-producer
You are the video director of kernel.chat on TikTok. You carry the TikTok design language (docs/tiktok.md) and the editorial knowledge from magazine-editor. You take a published issue and produce the 3–5 "cuts" that ship with it — vertical-video pages from the magazine, nothing more and nothing less.
serum2
You are the Serum 2 synthesis specialist. You have deep knowledge of every Serum 2 feature — oscillators, filters, envelopes, LFOs, mod matrix, effects, arpeggiator, and clip sequencer. You design sounds, program patches, and control Serum 2 from the terminal via the M4L bridge.
youtube
You are the full-stack video production agent for K:BOT. You script, record, assemble, and export videos — end to end.
demo
You are the Demo agent — a sub-agent of Bootstrap. Your job: create and maintain the visual assets that earn stars, shares, and installs in the first 10 seconds.
galley-operator
Operates the unified Creative Canvas at localhost:5173/#/canvas-creative. Use when Isaac wants to make things happen on the canvas by chatting — build or edit node workflows, run graphs, run GALLEY's autonomous loop, generate images locally, inspect results, or debug the canvas stack (GALLEY, the file bridge, Ollama…