vision-mcp AGENTS.md

Project instructions for vision-mcp, a tool that lets text-only coding agents use images through a command-line program and MCP server. It covers the project structure, commands, user flows, and constraints.

In plain words
What is it for?
Use it when developing vision-mcp, especially for its clipboard-based image input, image-to-text chat handling, configuration, commands, and tests.
Why use it?
It gives an agent clear rules for changing and testing the project without adding unrelated features or exposing API keys.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/hal666/vision-mcp/agents-md
Clone the repo
git clone --depth 1 https://github.com/hal666/vision-mcp

Made for: Codex, OpenCode.

Per session 427 This file is loaded in full into every session.
When invoked 427 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00427 $0.00427
Opus 5 $0.00214 $0.00214
Sonnet 5 $0.00085 $0.00085
Haiku 4.5 $0.00043 $0.00043

Measured yesterday against content hash 80c923e944ed, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

vision-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 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.

AGENTS.md · 54 lines

What it actually says

vision

给纯文本模型补视觉。引擎是 Node CLI vision,MCP / Skill / dsh 插件都 spawn 它。

结构

bin/vision.js        # 入口:vision add|see|install|mcp|...
lib/                 # config / engine / install / mcp / cli
dsh/                 # DeepSeek Harness 插件:工具 + 聊天框图片拦截
skills/vision-see/   # 教 agent 何时看图、如何 添加/删除/切换/启用/关闭
tests/               # node --test,不打真实视觉 API
  • 配置只住 ~/.vision-mcp/config.json
  • 视觉请求走 OpenAI-compatible /v1/chat/completions
  • 默认图源是系统剪贴板
  • stdout:CLI 结果或 MCP JSON-RPC;日志打 stderr
  • dsh 聊天框附图:插件在 llm/stream 把图转成文字再交给当前文本模型;会话里仍显示原图
  • 不写 Python。安装用 npm

用户路径

npm i -g github:hal666/vision-mcp
vision install

然后在 agent 里说「添加」给 model + apikey,或直接:

vision add <model> <apikey>

Agent 输入框:/vision add /vision delete /vision switch /vision enable /vision disable /vision see

终端:vision add 等同,没有 /

命令

npm install
npm test
node bin/vision.js doctor

改完必须跑 npm testnode bin/vision.js doctor

约束

  • 不删用户数据、不改系统配置、不装无关全局包
  • 不写 Playwright / HTML / 网页抓取
  • 换规范先改本文件,再改代码
Changes

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.

  1. yesterday First seen · 54 lines · 427 tokens per session scan A 80c923e944ed

Subscribe to this mod's changes

vision-mcp AGENTS.md is an instructions file published in the GitHub repository hal666/vision-mcp (0 stars, last pushed 12d ago), licensed MIT. It adds 427 tokens to every session, about $0.0021 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.

Related

Other instructions, from other repositories

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.

github/spec-kit · 7,104 tokens

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).

microsoft/vscode · 6,785 tokens

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.

openai/codex · 5,182 tokens

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.

langchain-ai/langchain · 4,345 tokens

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).

microsoft/vscode · 5,001 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens