PhyAgentOS-core is an agent framework for physical, or embodied, tasks in which software agents plan tool calls, observe what happened, and verify whether a real-world goal was achieved. It is intended for systems that operate physical agents through governed execution, recovery, evidence collection, and task-level verification. The catalogue add-ons provide workflows for working with this framework.
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 PhyAgentOS/PhyAgentOS-core --skill imagegit clone --depth 1 https://github.com/PhyAgentOS/PhyAgentOS-coreWrote 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/phyagentos/phyagentos-core/image)<a href="https://agentmods.dev/skills/phyagentos/phyagentos-core/image"><img src="https://agentmods.dev/badge/skills/phyagentos/phyagentos-core/image/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/phyagentos/phyagentos-core/image"><img src="https://agentmods.dev/badge/skills/phyagentos/phyagentos-core/image.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 | $0.00016 | $0.00842 |
| Opus 5.5 | $0.00006 | $0.00337 |
| Sonnet 5.5 | $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 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 — 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.
- 1mo ago First seen · 99 lines · 16 tokens per session scan A e374b69396ae
image is a skill published in the GitHub repository PhyAgentOS/PhyAgentOS-core (2,961 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 5.5. 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
open-code-review
Performs AI-powered code review on Git changes using the ocr CLI from alibaba/open-code-review. Use when the user asks to review code, review a pull request, review staged/unstaged changes, review a commit, or compare branches for code quality issues. Produces line-level review comments and can automatically apply…
lookup-agent-run
Find an eve Agent Run from a run ID, project, request reference, or approximate time using authorized evidence available to the consumer.
dashboard-chat-best-practices
Apply dashboard-grade chat UX patterns in the Eve chat template. Use when changing Next.js Cache Components/PPR behavior, static shell layout, Suspense bootstrap boundaries, theme hydration, auth display hydration, signed-in/signed-out static shell behavior, optimistic messages, streaming row identity…
company-employee
The protocol every employee of a PenguinHarness organization follows — read the handbook first, act on [orgtrigger] work runs, schedule tickets from the desk session and do the work in ticket sessions, block instead of idling, ask the board in the all-hands channel before anything heavy, costly, irreversible or…
company-ceo
Run a PenguinHarness organization as its CEO — turn the mission into a ticket tree, hire HR and finance first, partition the shared workspace, schedule the calendar, open a channel per stream, review tickets and report to the board in the all-hands channel.
investigate
Investigate a specific issue report with strict, evidence-driven diagnosis.