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/acnlabs/openpersona/visionnpx skills add acnlabs/OpenPersona --skill visiongit clone --depth 1 https://github.com/acnlabs/OpenPersonaWrote 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/acnlabs/openpersona/vision)<a href="https://agentmods.dev/skills/acnlabs/openpersona/vision"><img src="https://agentmods.dev/badge/skills/acnlabs/openpersona/vision.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.00719 |
| Opus 5 | $0.00000 | $0.00360 |
| Sonnet 5 | $0.00000 | $0.00144 |
| Haiku 4.5 | $0.00000 | $0.00072 |
Grade A, and why
vision 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 4d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vision Faculty — Sense
Perceive and interpret visual content natively through your model's vision capability. You can receive images, screenshots, diagrams, charts, and video frames as part of a conversation — treat them as a natural input channel, not an exception.
When to Engage Vision
Always engage when the user shares an image — do not ask for a text description if you can perceive the image directly.
Proactively describe relevant visual content when it materially affects your response:
- A screenshot showing an error → identify the error, not just acknowledge the image
- A diagram of a system → explain what the diagram shows before answering questions about it
- A photo of a person or scene → describe what you perceive, then respond to the user's actual question
Do not narrate your own perception process ("I am now analyzing the image..."). Engage with the content directly.
Perception Principles
Accuracy over confidence
- Describe what you can see clearly. Acknowledge ambiguity when present ("the text in the bottom-right is partially cut off").
- Do not fabricate details that are not visible. If something is unclear, say so.
Context-first interpretation
- Read the image in context of the conversation. A photo in a health conversation has different weight than the same photo in a creative writing session.
- Align visual interpretation with your persona's role and domain.
Privacy by default
- Do not retain, memorize, or reference image content in future conversations unless the user explicitly asks you to remember it.
- If an image contains identifiable faces or personal data, engage with the user's actual question — do not gratuitously describe personal identifying details beyond what the task requires.
- If an image appears to contain sensitive personal, medical, or financial information, acknowledge what the user is asking about without quoting sensitive data back verbatim.
Graceful Degradation
When vision is unavailable (model does not support vision, image failed to load, or no image was shared):
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.
- 4d ago First seen · 67 lines · 0 tokens per session scan A 44a7c75a2c09
vision is a skill published in the GitHub repository acnlabs/OpenPersona (48 stars, last pushed 24d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 719 tokens. 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
morph-ppt
Use this skill when the user wants a .pptx with smooth cross-slide animation — PowerPoint Morph transitions, Keynote-style continuous motion, shapes that grow / move / rotate as the slide advances. Trigger on: 'morph', 'morph transition', 'smooth transition', 'continuous animation across slides', 'Keynote-style…
xiaoai-tts
Control Xiaoai speaker via OpenXiaoAI Voice API for high-quality TTS playback. Use when the user wants to play voice notifications, announcements, or TTS through the Xiaoai speaker using the OpenXiaoAI HTTP API. Supports Doubao (ByteDance) TTS with emotions, voice types, and speed control. Triggers on queries like…
songsee
Generate spectrograms and audio feature visualizations (mel, chroma, MFCC, tempogram, etc.) from audio files via CLI. Useful for audio analysis, music production debugging, and visual documentation.
algorithmic-art
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright…
canvas-design
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.
slack-gif-creator
Knowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack.".