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 instructions/alierq/image-analyzer-mcp/agents-mdgit clone --depth 1 https://github.com/AlierQ/image-analyzer-mcpWrote 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/alierq/image-analyzer-mcp/agents-md)<a href="https://agentmods.dev/instructions/alierq/image-analyzer-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/alierq/image-analyzer-mcp/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 | $0.00873 | $0.00873 |
| Opus 5 | $0.00436 | $0.00436 |
| Sonnet 5 | $0.00175 | $0.00175 |
| Haiku 4.5 | $0.00087 | $0.00087 |
Grade A, and why
image-analyzer-mcp 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 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.
What it actually says
图片分析使用规则
使用前提(先判断,再调用)
本工具不是“只要粘贴图片就调用”的通用工具。只有当当前主模型不支持图片输入时,才使用本工具:
- 当前主模型支持图片输入(例如 Codex 内置的 ChatGPT 视觉模型):直接由主模型分析图片,不要调用
analyze_image/compare_images/analyze_clipboard_image。 - 当前主模型不支持图片输入(例如通过 CC Switch 切换到 DeepSeek 等不支持多模态图片输入的文本模型,图片在会话中显示为
[Unsupported Image]):才调用本工具。
判断方法:先确认当前会话主模型是否支持视觉/图片输入。支持就直接分析;只有不支持(或图片显示为 [Unsupported Image])时才调用本工具,不要因为用户粘贴了图片就无条件调用。
什么时候必须调用 analyze_image
只有确认主模型不支持图片输入后,当任务中出现以下情况时,自动调用 analyze_image,不要凭文字描述猜测:
- 用户引用
.png、.jpg、.jpeg、.webp截图或设计图 - 任务包含 screenshot、mockup、wireframe、design、Figma 导出图等视觉参考
- 需要根据图片实现页面、组件或复刻设计细节
- 需要确认颜色、间距、字体、布局、组件结构
调用方式:
analyze_image(path="图片路径", prompt="需要重点分析的内容,可选")
工具会返回结构化 JSON,包含 layout、sections、components、colors、typography、spacing_system、issues、conversion_to_code 等字段。实现时应直接使用这些字段。
什么时候必须调用 compare_images
只有确认主模型不支持图片输入后,当任务是“按参考图修改当前实现”或“验证还原度”时,自动调用:
compare_images(
referencePath="参考图路径",
currentPath="当前实现截图路径",
prompt="需要重点对比的部分,可选"
)
然后按返回的 differences 和 fix_plan 处理:
- 先修复
high严重度和P0优先级的问题 - 再处理
medium/P1 - 最后处理
low/P2 - 修复完成后重新截屏并再次调用
compare_images验证
硬性规则
- 调用前先确认当前主模型是否支持图片输入:支持则由主模型直接分析,不要调用本工具
- 只有主模型不支持图片输入(例如通过 CC Switch 切换到 DeepSeek 等文本模型)时,才调用本工具;不要因为用户粘贴了图片就无条件调用
- 不要用文字描述猜测图片里的颜色、间距、布局和组件细节
- 不要告诉用户“请先手动运行视觉分析”,直接调用工具
- 相对路径可以直接传给工具,服务端会按
VISION_BASE_DIR或进程目录解析 - 如果用户粘贴或复制了图片(即使界面提示“此模型不支持图片输入”),不要回复“看不到图片”;优先调用
analyze_clipboard_image,如果消息里有图片文件路径则调用analyze_image(path) - 视觉模型只作为识图工具,它们返回的 JSON 只是分析素材;最终解释、回答、判断和代码决策必须由主模型(例如 DeepSeek)完成,不要直接把视觉模型的原始输出当作最终回答
- 如果工具返回
error字段,先修复配置错误(API key、base URL、模型),再继续任务 - 如果模型没有返回可用 JSON,按
raw_output内容谨慎处理,并考虑重试一次
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 · 59 lines · 873 tokens per session scan A 9a5c3db3764b
image-analyzer-mcp AGENTS.md is an instructions file published in the GitHub repository AlierQ/image-analyzer-mcp (0 stars, last pushed 24d ago), licensed MIT. It adds 873 tokens to every session, about $0.0044 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
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).
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.
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.
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.
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).