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 skills/phyagentos/phyagentos-core/imagenpx skills add PhyAgentOS/PhyAgentOS-core --skill imagegit clone --depth 1 https://github.com/PhyAgentOS/PhyAgentOS-coreWhat 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 | $0.00016 | $0.00842 |
| Opus 5 | $0.00008 | $0.00421 |
| Sonnet 5 | $0.00003 | $0.00168 |
| Haiku 4.5 | $0.00002 | $0.00084 |
Grade A, and why
image 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Image Tool
Unified tool for analyzing and displaying images. Supports two modes: vision analysis using multimodal LLM models and displaying images to users through the frontend.
Features
- Analyze images using multimodal LLM models (OCR, description, visual QA)
- Display images to users by sending them to the frontend
- Generate images from text prompts using AI models
- Support multiple image formats: PNG, JPG, JPEG, GIF, WEBP, BMP
- Base64 encoding for image processing and transmission
Tools
This skill provides the following tool:
image
Unified tool for image analysis, display, and generation.
Parameters:
mode(string, required): The operation mode -visionfor image analysis,displayfor showing images to users,generatefor creating images from text promptsimage_path(string, required):- In vision/display mode: Absolute path to the image file (e.g., "/Users/photo.png")
- In generate mode: File name where the generated image will be saved. This parameter should contain few words which generalize the
text
text(string, optional):- In vision mode: User's request or question about the image (e.g., "Describe this image", "Extract text from this image")
- In display mode: Caption to display with the image (appears above the image in the message box)
- In generate mode: Text prompt describing the desired image content, style, and composition (supports Chinese and English, max 800 characters)
Examples
Example for vision - Describe an image at image.png:
<tool>image</tool>
<parameter name="mode">vision</parameter>
<parameter name="text">Describe this image</parameter>
<parameter name="image_path">image.png</parameter>
Example for vision - Extract text from image image.jpeg:
<tool>image</tool>
<parameter name="mode">vision</parameter>
<parameter name="text">Get words in this image</parameter>
<parameter name="image_path">image.jpeg</parameter>
Example for vision - How many birds in image image.png:
<tool>image</tool>
<parameter name="mode">vision</parameter>
<parameter name="text">How many birds in image?</parameter>
<parameter name="image_path">image.png</parameter>
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 · 99 lines · 16 tokens per session scan A e374b69396ae
image is a skill published in the GitHub repository PhyAgentOS/PhyAgentOS-core (1,981 stars, last pushed 2d ago), licensed MIT. It adds 16 tokens to every session and 842 once invoked, about $0.0001 per session on Opus 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
bento-slides
Create and edit Bento presentations — self-contained .bento.html decks whose document is JSON. Use whenever the user wants a slide deck or presentation: from scratch, from source material, or by improving an existing file.
openloomi-pet
OpenLoomi Pet sprite & state helper for Claude Code. Use when the user wants to change their Loomi Pet state, switch theme, drop in a custom character, override individual sprites, or ask Claude to mirror its lifecycle onto the pet. Triggers: pet state, /openloomi:pet, set pet, loomi pet, pet to happy, pet to working…
openloomi-lifestyle-image
Identify whether a user is asking OpenLoomi to generate a lifestyle image, portrait, personal visual, or lifestyle scene. Use this skill for chat messages that may request image generation for a user's lifestyle, identity, persona, personal brand, social profile, memories, interests, or real-life scene; distinguish…
demo
Record a short demo VIDEO of a PR or feature — drive the repo's web UI in a real headless browser, capture the session, and composite a titled, size-capped mp4 with ffmpeg. Use on the docker QA image when the deliverable is a playable demo clip (single walkthrough or before/after comparison), not a text/screenshot…
image_generate
Skill "image_generate" from limecloud/lime, covering 工作目标, 执行规则 and 输出规则（固定）.
novel-technique-character-card-workshop
重量级角色写卡、人物塑造、人设整理与角色理解流程。用于用户要从模糊角色印象、萌点、标签、OC、人设草稿或角色卡想法整理成可写角色，进行 20/24/80/200 问循环问答，设计或校验基础信息、调色盘、三面性、混色、核心人格层、二次解释、意象，或防止 AI 把角色写成标签化人设；适合作为 novel-setup 角色设计阶段的深挖前置或参考技法。用户明确要求批量出候选答案再逐题挑选时，可走可选的批量候选模式。.