An image-generation tool that uses Google Imagen 4, Nano Banana, and a reference-to-image mode through Google Flow. It needs a Google account and a Chrome extension rather than an API key.

Use it to create illustrations, logos, banners, avatars, portraits, and other images, while choosing a model, image count, aspect ratio, and output folder.

It gives an agent a way to create images from written descriptions or use a reference image for style transfer through the available Flow connection.

whisk-proxy — Skill for Claude Code and Codex by AndyShaman

Install

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.

Any agent

npx skills add AndyShaman/whisk-proxy --skill whisk-proxy

Clone the repo

git clone --depth 1 https://github.com/AndyShaman/whisk-proxy

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/andyshaman/whisk-proxy/whisk-proxy/github.svg)](https://agentmods.dev/skills/andyshaman/whisk-proxy/whisk-proxy)

Your own site

<a href="https://agentmods.dev/skills/andyshaman/whisk-proxy/whisk-proxy"><img src="https://agentmods.dev/badge/skills/andyshaman/whisk-proxy/whisk-proxy/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/andyshaman/whisk-proxy/whisk-proxy"><img src="https://agentmods.dev/badge/skills/andyshaman/whisk-proxy/whisk-proxy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 128 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 931 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00128	$0.00931
Opus 5.5	$0.00051	$0.00372
Sonnet 5.5	$0.00026	$0.00186
Haiku 4.5	$0.00013	$0.00093

Measured 2mo ago against content hash 4732b909b27a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

whisk-proxy 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 2mo ago.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/generate.mjs, scripts/lib/auth.mjs, scripts/status.mjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

SKILL.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Flow Image Generator

Generate images using Google Imagen 4, Nano Banana, and Reference-to-Image for free. No API key — uses Chrome extension for OAuth.

Quick Start

# Generate 4 images (Imagen 4, default)
node {baseDir}/scripts/generate.mjs -p "a cat astronaut floating in space"

# Nano Banana (fast, creative)
node {baseDir}/scripts/generate.mjs -p "abstract painting in neon colors" -m banana

# Reference-to-Image (style transfer)
node {baseDir}/scripts/generate.mjs -p "watercolor portrait" -m r2i

# Portrait format, 1 image
node {baseDir}/scripts/generate.mjs -p "anime girl with headphones" -r 9:16 -c 1

# Save to specific folder
node {baseDir}/scripts/generate.mjs -p "sunset over mountains" -o ./images

Models

Model	Flag	Best for
Imagen 4	`-m imagen4` (default)	Highest quality, photorealistic
Nano Banana	`-m banana`	Fast, creative generation
Reference-to-Image	`-m r2i`	Style transfer

Options

Flag	Short	Default	Description
`--prompt`	`-p`	required	Image description (English works best)
`--model`	`-m`	`imagen4`	Model: imagen4, banana, r2i
`--count`	`-c`	`4`	Number of images (1-4)
`--ratio`	`-r`	`1:1`	Aspect ratio: `1:1`, `16:9`, `9:16`, `4:3`, `3:4`
`--output`	`-o`	`.`	Output directory
`--seed`	`-s`	random	Seed for reproducibility

Aspect Ratios

1:1 (1024x1024) — avatars, icons, social posts
16:9 (1365x768) — banners, covers, YouTube thumbnails
9:16 (768x1365) — stories, reels, vertical posters
4:3 — classic landscape
3:4 — classic portrait

Authentication

Token stored in ~/.flow-proxy/token.json. The Chrome extension handles auth automatically.

Check token status

node {baseDir}/scripts/status.mjs

First-time setup

Install the Chrome extension from {baseDir}/extension/ (load unpacked)
Open https://labs.google/fx/tools/flow
Sign in with Google
Click the Flow Proxy extension icon → "Connect"

Read the full file on GitHub · 93 lines

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

2mo ago First seen · 93 lines · 128 tokens per session scan A 4732b909b27a

Subscribe to this mod's changes

whisk-proxy is a skill published in the GitHub repository AndyShaman/whisk-proxy (20 stars, last pushed 8mo ago), licensed MIT. It adds 128 tokens to every session and 931 once invoked, about $0.0005 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 2026-08-30.

Claude Code Creative and media ai-art google-whisk image-generation imagen

whisk-proxy next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
whisk-proxyAndyShaman/whisk-proxy	Skill	20	8mo ago	MIT	A	128	Claude Code, Codex
byted-seedream-image-generatebytedance/agentkit-samples	Skill	484	yesterday	Apache-2.0	A	65	Claude Code, Codex
tag1756141021/tag-skill	Skill	20	19d ago	MIT	A	43	Claude Code, Codex
zernio-social-postingfajrisilmi12-cyber/hermes-socmed-function	Skill	21	2mo ago	MIT	A	22	Claude Code, Codex
social-media-schedulingfajrisilmi12-cyber/hermes-socmed-function	Skill	21	2mo ago	MIT	A	18	Claude Code, Codex
image-gen-9routerfajrisilmi12-cyber/hermes-socmed-function	Skill	21	2mo ago	MIT	A	24	Claude Code, Codex
crayon-flat-naiveVieeeeeee/wibi-style	Skill	184	2d ago	none	A	146	Codex