Borrowing it
Nothing to install: this file belongs to Wjl1224734792/visual-primitives-mcp. 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/Wjl1224734792/visual-primitives-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/Wjl1224734792/visual-primitives-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/wjl1224734792/visual-primitives-mcp/agents-md)<a href="https://agentmods.dev/instructions/wjl1224734792/visual-primitives-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/wjl1224734792/visual-primitives-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 5.1 | $0.04512 | $0.04512 |
| Opus 5 | $0.02256 | $0.02256 |
| Sonnet 5 | $0.00902 | $0.00902 |
| Haiku 4.5 | $0.00451 | $0.00451 |
Grade A, and why
visual-primitives-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 8d 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 — 353 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Visual Primitives MCP — 架构文档
基于 DeepSeek《Thinking with Visual Primitives》论文的多模态视觉理解 MCP 服务器。核心创新:任务调度 + 两阶段推理——先让模型看清画面(describe),再基于完整上下文追问坐标(locate),每一步专注做好一件事。
1. 项目概述
将视觉模型的场景理解和坐标定位能力封装为 6 个专注 MCP 工具,通过任务调度机制实现两阶段精确空间推理。visual_describe 先理解场景 → visual_locate 再精确定位 → 两者通过共享会话上下文联动。
| 属性 | 值 |
|---|---|
| 运行时 | Node.js >= 22.5.0 |
| 语言 | TypeScript (strict) |
| MCP 协议 | @modelcontextprotocol/sdk v1.x |
| HTTP 层 | Hono(仅 SSE/HTTP Stream) |
| 持久化 | node:sqlite(内置) |
| 校验 | Zod |
| 日志 | pino(敏感字段脱敏) |
| 测试 | vitest(13 文件 176 用例) |
2. 架构分层
┌──────────────────────────────┐
│ 入口层 (src/) │
│ server.ts / config.ts │
│ types.ts │
├──────────────────────────────┤
│ 传输层 (transport/) │
│ factory.ts │
├──────────────────────────────┤
│ 处理器层 (handlers/) │
│ tool-handlers.ts (4 工具) │
│ encodeFileBase64() 读文件 │
├──────────────────────────────┤
│ 核心管道层 (core/) │
│ ┌────────────────────────┐ │
│ │ pipeline.ts (任务调度) │ │
│ │ describe | locate │ │
│ │ ocr | video_analyze │ │
│ │ parser.ts / validator │ │
│ │ normalizer.ts │ │
│ │ prompt-builder.ts │ │
│ │ vision-client.ts │ │
│ │ session-manager.ts │ │
│ └────────────────────────┘ │
├──────────────────────────────┤
│ 工具层 (utils/) │
│ logger.ts / retry.ts │
├──────────────────────────────┤
│ 模板层 (templates/) │
│ describe-structured.txt │
│ locate-system.txt │
│ ocr-system.txt │
└──────────────────────────────┘
3. 各层详解
3.1 入口层 (src/)
server.ts — 服务主入口
- 初始化链:
SessionManager → VisionClient → PipelineOrchestrator → McpServer - 注册 6 个视觉任务工具(describe/locate/ocr/video/compare/diagnose 均支持会话上下文注入)
- 根据
MCP_TRANSPORT环境变量选择传输模式(stdio / sse / http-stream) - Hono 仅在 SSE/HTTP Stream 模式动态加载,stdio 零开销
- 启动 60s 间隔的 TTL 会话清理定时器
- SIGINT/SIGTERM 优雅关闭:清定时器 → 关 SQLite → 退出
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.
- 8d ago First seen · 353 lines · 4,512 tokens per session scan A f2742edc341f
visual-primitives-mcp AGENTS.md is an instructions file published in the GitHub repository Wjl1224734792/visual-primitives-mcp (2 stars, last pushed 1mo ago), licensed MIT. It adds 4,512 tokens to every session, about $0.0226 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.