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 skills add yinjs/agyenvoy --skill agy-image-gengit clone --depth 1 https://github.com/yinjs/agyenvoyWrote 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/skills/yinjs/agyenvoy/agy-image-gen)<a href="https://agentmods.dev/skills/yinjs/agyenvoy/agy-image-gen"><img src="https://agentmods.dev/badge/skills/yinjs/agyenvoy/agy-image-gen/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/skills/yinjs/agyenvoy/agy-image-gen"><img src="https://agentmods.dev/badge/skills/yinjs/agyenvoy/agy-image-gen.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 | $0.00057 | $0.00686 |
| Opus 5.5 | $0.00023 | $0.00274 |
| Sonnet 5.5 | $0.00011 | $0.00137 |
| Haiku 4.5 | $0.00006 | $0.00069 |
Grade A, and why
agy-image-gen 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.
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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generating Images with agy
Overview
Claude has no image-generation tool. The agy (Antigravity) CLI wraps Google's
Gemini native image model and can produce real raster images from a text prompt.
This plugin exposes agy as the agy_ask MCP tool. When asked for an image, call
agy_ask instead of refusing.
When to Use
- User wants a generated image/illustration/photo/logo/icon/concept art from a description.
- User wants a placeholder, hero, avatar, or asset image for a site or doc.
- NOT for: charts/plots/diagrams from data (write code — matplotlib/mermaid/SVG), or flat geometric/vector shapes (agy writes code for those too — see Traps).
Recipe
Call agy_ask with the target directory in add_dir and an absolute save path in the prompt:
prompt:Using your native image generation model, create <rich photographic description>. Save the image to <absolute-dir>/<name>.png. Do NOT write a script or use matplotlib/PIL.add_dir:["<absolute-dir>"]← same dir as the save pathtimeout_ms:600000← generation takes ~30–90s; give ≥5 min
Without both add_dir and an absolute save path, agy dumps the image to its own
scratch dir instead of where you want it.
If agy_ask returns "not logged in", call agy_login first, then retry.
Traps
| Symptom | Cause | Fix |
|---|---|---|
| Tiny PNG (few KB), flat shapes | Simple/geometric prompt → agy writes matplotlib/PIL code instead of calling the AI model | Say "Using your native image generation model" and describe a rich, photographic scene |
| Image saved elsewhere | No workspace set | Pass add_dir and an absolute path in the prompt |
| Command hangs / times out | Prompt referenced an input file not in the workspace | Only reference paths that exist; put any input image in the add_dir dir |
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 · 60 lines · 57 tokens per session scan A dc737e7afb8e
agy-image-gen is a skill published in the GitHub repository yinjs/agyenvoy (1 stars, last pushed 3mo ago), licensed MIT. It adds 57 tokens to every session and 686 once invoked, about $0.0002 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 2026-08-31.
agy-image-gen compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| agy-image-genyinjs/agyenvoy | Skill | 1 | 3mo ago | MIT | A | 57 | Claude Code |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | yesterday | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 100k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 314k | 4d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |