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/hal666/vision-mcp/visionnpx skills add hal666/vision-mcp --skill visiongit clone --depth 1 https://github.com/hal666/vision-mcpWhat 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 | $0.00066 | $0.00337 |
| Opus 5 | $0.00033 | $0.00169 |
| Sonnet 5 | $0.00013 | $0.00067 |
| Haiku 4.5 | $0.00007 | $0.00034 |
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 yesterday.
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.
What it actually says
/vision
User-facing command is /vision ... in the agent. That maps 1:1 to CLI vision ....
When this skill is invoked with leftover text (the part after /vision), run that as CLI args. Do not invent flags. Never echo the full apikey.
/vision add <model> <apikey>
/vision delete <name>
/vision switch <name>
/vision enable
/vision disable
/vision status
/vision see
Prefer MCP vision_config / vision_see if those tools exist. Otherwise shell:
vision $ARGUMENTS
Empty /vision → vision status plus the list above.
Images (no slash)
Pasted screenshot / 图片 / 截图 / [Image 1] → vision_see with empty image (clipboard). Do not ask for a file path.
In DeepSeek Harness the plugin captions chat attachments before the text model runs; still use vision_see if the user only copied to the clipboard.
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.
- yesterday First seen · 39 lines · 66 tokens per session scan A 42389b45c04f
vision is a skill published in the GitHub repository hal666/vision-mcp (0 stars, last pushed 12d ago), licensed MIT. It adds 66 tokens to every session and 337 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
embedded-captions
Add captions or subtitles to an existing single-subject talking-head video without editing the footage. Use for plain verbatim captions, cinematic captions embedded behind the subject, VFX captions, “炸/特效/酷炫字幕,” or a named identity from the 35-style catalog. Route by visual identity, not by backend engine. The quiet…
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
chengfeng-check-updates
剪辑环境的唯一管理者：就绪检查（skills 是否最新 → Runtime 是否配套）、Skills 更新激活、Runtime 安装与体检。用户说检查更新、安装剪辑环境、装播放器、检查剪辑环境、剪辑环境就绪了吗、配置转录凭证时使用；业务 Skill（剪口播/字幕/画面/导出）第 0 步也引用本 Skill 的就绪检查。不用于剪辑、字幕、画面、导出本身或项目数据迁移。.
cap_llm_inspect_image
How to inspect a local image with inspectimage.