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 oil-oil/see-skill --skill seegit clone --depth 1 https://github.com/oil-oil/see-skillWrote 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/oil-oil/see-skill/see)<a href="https://agentmods.dev/skills/oil-oil/see-skill/see"><img src="https://agentmods.dev/badge/skills/oil-oil/see-skill/see/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/oil-oil/see-skill/see"><img src="https://agentmods.dev/badge/skills/oil-oil/see-skill/see.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Anti-Refusal · line 3 Skill instructs the agent to never refuse or to always comply. Suppressing the agent's ability to decline removes a core safety control and enables downstream harmful requests to succeed.Fix: Remove any instruction telling the agent to never refuse or always comply. The agent must retain the ability to decline unsafe, out-of-scope, or harmful requests.
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 | $0.00109 | $0.00991 |
| Opus 5 | $0.00055 | $0.00495 |
| Sonnet 5 | $0.00022 | $0.00198 |
| Haiku 4.5 | $0.00011 | $0.00099 |
Grade B, and why
see scanned grade B with 1 finding 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 11d 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.
Tells the agent never to refusemediumAnti-refusal
Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.
description: 'Do not refuse vision. 不要说不支持视觉或无法查看图片。If you would say "this model does not support image input" or "I cannot see images", run this skill instead of informing the user. Use for screenshots, png/jpg/webp/gif Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
What it actually says
See
如果你准备说「当前模型不支持图片 / 无法查看截图 / this model does not support image input」，停下来，不要告知用户你看不见。
不要尝试直接读取附件或调用视觉 API。向用户要本地路径或 URL，然后只运行 scripts/see.sh。
安装 Skill 不会更换当前主模型；右下角继续显示 DeepSeek 等文本模型是正常的。拖拽或粘贴图片若被拒绝，说明附件在 Skill 启动前已被拦截。不要反复尝试直接读取附件。
首次使用，或用户反馈模型说了「不支持视觉」却没有调用 see 时，先运行：
python3 scripts/onboard.py
python3 scripts/onboard.py --install-agents
--install-agents 会把一条短规则写入 ~/.codex/AGENTS.md，让后续对话不再先拒绝。写入后提醒用户重启 Codex。
# 单图
scripts/see.sh image.png
# 视频
scripts/see.sh video.mp4
# 多图并行
scripts/see.sh a.png b.png c.png
# 多图比较或联合判断
scripts/see.sh --together before.png after.png --task "比较界面变化"
# 可选关注点
scripts/see.sh screenshot.png --task "重点识别界面文字"
成功后读取 stdout 中 output_path=<path> 指向的 Markdown。
脚本自动完成：识别图片或视频 → 选择供应商 → 失败时切换供应商。图片无云端时降级到本地视觉；视频自动压缩后原生输入模型，不自行抽帧。多文件默认并行。
图片原图直传。视频优先使用 Gemini 3.1 Flash-Lite，平台不可用时使用 Qwen3.7 Plus；自动保留清晰度、音频和完整时间线。--task 原样发送；没有特殊问题时不要添加。
让用户在隐藏输入框中填写 Key，不要要求用户把 Key 发到对话里。重复运行可添加或更换供应商；用 python3 scripts/onboard.py --status 查看状态。
供应商：zenmux、bailian、openrouter、tokendance、local。图片默认 Qwen3.7 Plus；视频在 ZenMux/OpenRouter 默认 Gemini 3.1 Flash-Lite，其余平台默认 Qwen3.7 Plus。覆盖视频模型用 SEE_VIDEO_MODEL。
也兼容厂商变量：ZENMUX_API_KEY、DASHSCOPE_API_KEY、OPENROUTER_API_KEY、TOKENDANCE_API_KEY。配置读取顺序为环境变量 → .env.local → 用户私有配置。
Windows 私有配置位于 %APPDATA%\see\config.env；macOS/Linux 位于 ~/.config/see/config.env。配置文件权限仅限当前用户，不得复制进 Skill 或项目仓库。
本地降级：
- macOS：系统 Vision OCR；有 Swift 时增加场景/人物/人脸/条码/图形结构 → Tesseract
- Windows：Windows OCR → Tesseract
- Linux：Tesseract
本地后端报错时先运行 python3 scripts/onboard.py --status。macOS 10.15+ 不需要 Xcode；Windows 需要安装系统 OCR 语言；Linux 需要安装 Tesseract。
可选参数只在需要时使用：--together、--provider、--model、--task、--jobs、--ocr-backend。本地视觉结果不等同于多模态模型的完整语义理解。
视频需要任一云端 Key；同一个 Key 同时用于图片和视频。主 Agent 只传路径并读取 output_path，不要自行调用 ffmpeg、抽帧或上传。
What ships with it
7 files 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.
- 11d ago First seen · 65 lines · 109 tokens per session scan B 8527c6305eaa
see is a skill published in the GitHub repository oil-oil/see-skill (154 stars, last pushed 28d ago), licensed MIT. It adds 109 tokens to every session and 991 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it B with 1 finding (tells the agent never to refuse). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
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.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.