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 TGYD-helige/pi --skill image-gengit clone --depth 1 https://github.com/TGYD-helige/piWrote 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/tgyd-helige/pi/image-gen)<a href="https://agentmods.dev/skills/tgyd-helige/pi/image-gen"><img src="https://agentmods.dev/badge/skills/tgyd-helige/pi/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/tgyd-helige/pi/image-gen"><img src="https://agentmods.dev/badge/skills/tgyd-helige/pi/image-gen.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00061 | $0.01638 |
| Opus 5.5 | $0.00024 | $0.00655 |
| Sonnet 5.5 | $0.00012 | $0.00328 |
| Haiku 4.5 | $0.00006 | $0.00164 |
Grade A, and why
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 1mo 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Image generation
This skill guides use of the image_generate tool from @amaster.ai/pi-image-gen. The active model is fixed by pi-image-gen.defaultModel in settings — the tool has no model parameter. Run /image-gen list to see the active model, its provider, and whether its API key is set.
When to use
- A brand-new bitmap image: concept art, product shot, cover, website hero, texture, sprite.
- A new image guided by one or more reference images (style, composition, mood, subject).
- Editing an existing image: inpainting, background replacement, object removal, lighting or weather changes, compositing, style transfer, character preservation.
- Several assets or variants for one task.
When NOT to use
- Extending or matching an existing SVG/vector icon set, logo system, or illustration library in the repo — edit those source files directly.
- Simple shapes, diagrams, wireframes, or icons better produced in SVG, HTML/CSS, or canvas.
- A small project-local asset edit when the source already exists in an editable native format.
- Any task where the user clearly wants deterministic code-native output, not a generated bitmap.
Before every call
Use only parameters and values exposed by the current image_generate schema.
- Intent — generate or edit?
- No
image, orimageentries used only as style/composition/mood references → generate. - Modify an existing image while preserving most of it → edit (pass that image).
- When unsure, assume the user wants a new image unless they clearly ask to change an existing one.
- No
- Strategy — one asset or many?
nproduces variants of ONE prompt, not distinct assets.- For several different assets, make one
image_generatecall per asset, each with its own prompt. Do not raisento cover distinct subjects.
- Inputs — what must the prompt preserve? Collect exact text, constraints/avoid items, and every input image's role. Ask only when a missing detail blocks a usable result; otherwise proceed.
What ships with it
1 file 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.
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.
- 1mo ago Changed · +4 lines d543cb8be260
- 1mo ago Changed · +1 lines 940b0af720aa
- 1mo ago First seen · 95 lines · 61 tokens per session scan A 5d8d08621a35
image-gen is a skill published in the GitHub repository TGYD-helige/pi (84 stars, last pushed today), licensed Apache-2.0. It adds 61 tokens to every session and 1,638 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 2026-08-30.
Other skills, from other repositories
vision-bridge-windows-automation
Drive Windows desktop apps (Win32/WPF/UWP), Electron windows and the browser through the vision-bridge MCP server - read the screen as structured text and click/type by element id. Use when the user asks the agent to operate a Windows GUI app, fill a form in a desktop program, read what is on screen, or automate a…
browser-use
Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work. Also covers hosted cloud browsers for AI agents: the browser-use Python library (Browser(usecloud=True)), Playwright, Puppeteer or any CDP client.
x402
Set up Browser Use Cloud payments with x402 — pay per request from a crypto wallet (USDC on Base mainnet), no signup or API key. Two setups it works out up front — "just use it" (set up a wallet so you or Claude Code can run cloud browser tasks paid from the wallet — Claude writes and runs throwaway scripts, nothing…
remote-browser
Controls an isolated Browser Use Cloud browser from a sandboxed machine with the current Browser Use CLI.
cloud
Documentation reference for using Browser Use Cloud — the hosted API and SDK for browser automation. Use this skill whenever the user needs help with the Cloud REST API (v2, v3, or v4), browser-use-sdk (Python or TypeScript), X-Browser-Use-API-Key authentication, cloud sessions, browser profiles, profile sync, CDP…
open-source
Documentation reference for writing Python code using the browser-use open-source library. Use this skill whenever the user needs help with Agent, Browser, or Tools configuration, is writing code that imports from browseruse, asks about @sandbox deployment, supported LLM models, Actor API, custom tools, lifecycle…