Borrowing it
Nothing to install: this file belongs to TIanle-art/agent-vision-skill. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/TIanle-art/agent-vision-skill/main/AGENTS.mdgit clone --depth 1 https://github.com/TIanle-art/agent-vision-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/instructions/tianle-art/agent-vision-skill/agents-md)<a href="https://agentmods.dev/instructions/tianle-art/agent-vision-skill/agents-md"><img src="https://agentmods.dev/badge/instructions/tianle-art/agent-vision-skill/agents-md.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 5.1 | $0.01852 | $0.01852 |
| Opus 5 | $0.00926 | $0.00926 |
| Sonnet 5 | $0.00370 | $0.00370 |
| Haiku 4.5 | $0.00185 | $0.00185 |
Grade A, and why
agent-vision-skill AGENTS.md 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 6d 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
给配置助手的强制指令(收到本仓库链接/路径的 AI 必读)
用户把本仓库发给你,意图是让你帮他配置识图能力(或回答他关于本项目的问题)。
第一步永远是提问,不是动手
执行任何安装、下载、写文件的操作之前,必须先向用户提问,顺序如下:
- 问路线:默认路线(阿里云百炼 + 千问视觉模型,新用户有免费 token 额度)还是用户已有自己的平台/Key(任何 OpenAI 兼容格式均可)?
- 问 Key:用户没有 Key 时,引导去 https://bailian.console.aliyun.com/ 注册申请(新用户有免费额度),拿到 Key 才继续。
- 问模型:
qwen3-vl-flash(默认,便宜)/qwen3-vl-plus(更强)/ 用户指定。
硬性规则:
- 提问后必须主动要 Key,并给用户两条路,不得甩锅:
- 用户有 Key 或愿意去注册:引导去 https://bailian.console.aliyun.com/ 注册申请(新用户有免费额度),拿到 Key 后由你配好并验证;
- 用户不想给 Key / 想自己配:提供逐步指引——复制
.env.example为.env、填入DASHSCOPE_API_KEY(自有平台还填DASHSCOPE_BASE_URL、VISION_MODEL)、运行node vision.js --help验证。不得只甩一句"自己配"而不给步骤。
- 用户没给 Key 之前:不得替用户填 Key、不得编造/猜测 Key;不涉及 Key 的安装(拷贝脚本、放规则文件)可以先做。
- 用户选择了自有平台时,必须问全三项:API Base URL、API Key、模型名,按用户给的写,不得替用户猜测默认值。
拿到信息后
按 README「如果你是 AI」分区的「场景 A」执行(拷贝模式),或引导用户安装 Skill 形态(vision/ 目录,README 有各 agent 安装命令)。
- Key 一律写进
.env(复制.env.example),禁止把 Key 写进vision.js代码。 - 配置完成后运行
node vision.js --help验证可用,再告诉用户"以后直接发图片即可"。
本仓库文件角色
| 文件 | 角色 |
|---|---|
AGENTS.md |
本文件:上半是配置助手指令(收到仓库链接/路径时生效),下半是识图规则(拷入用户项目后生效) |
vision/SKILL.md |
识图规则(Skill 形态,装 skill 的 agent 用;正文与本文件识图段一致,CI 校验) |
vision.js |
核心脚本(与 vision/scripts/vision.js 同一代码双形态分发,CI 校验完全一致) |
README.md |
详细配置流程与人类说明 |
识图能力
底层模型不具备原生识图能力。遇到图片时,不要用 Read 工具,改用本项目脚本 vision.js:
node vision.js "<图片路径>" "用中文描述这张图片"
触发场景
- 用户分享图片路径(本地或网络 URL)
- 消息中出现 "Saved attachments:" 并列出图片
- 用户要求分析、描述、识别图片内容
多图
用户一次发多张图片时,必须逐张处理全部图片,拿到所有描述后再回复:
node vision.js "图片1路径" "图片2路径" "用中文描述每张图片"
拿到全部描述后再组织回复,不得只处理第一张。
网络图片
用户发来的是图片 URL 时,直接传即可(自动识别,也可用 --url 显式指定):
node vision.js "https://example.com/a.png" "用中文描述这张图片"
切换模型
用户说"换增强视觉模型"或"换 plus"时:把视觉模型改为 qwen3-vl-plus。
用户说"换回 flash"时:改回 qwen3-vl-flash。
用户指定其他模型名时,按其要求填写。
改哪里:先看 vision.js 同目录有没有 .env 文件——有就改 .env 里的 VISION_MODEL(环境变量优先级高于代码),没有 .env 才改 vision.js 顶部模型配置区的 MODEL。(skill 安装形态下 .env 放在 skill 根目录,同样优先改它)
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.
- 6d ago First seen · 124 lines · 1,852 tokens per session scan A c1036e1525ec
agent-vision-skill AGENTS.md is an instructions file published in the GitHub repository TIanle-art/agent-vision-skill (2 stars, last pushed 1mo ago), licensed MIT. It adds 1,852 tokens to every session, about $0.0093 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 instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.