Borrowing it
Nothing to install: this file belongs to Dellety/vision-mcp-for-ds. 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/Dellety/vision-mcp-for-ds/main/AGENTS.mdgit clone --depth 1 https://github.com/Dellety/vision-mcp-for-dsWrote 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/dellety/vision-mcp-for-ds/agents-md)<a href="https://agentmods.dev/instructions/dellety/vision-mcp-for-ds/agents-md"><img src="https://agentmods.dev/badge/instructions/dellety/vision-mcp-for-ds/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 | $0.02836 | $0.02836 |
| Opus 5 | $0.01418 | $0.01418 |
| Sonnet 5 | $0.00567 | $0.00567 |
| Haiku 4.5 | $0.00284 | $0.00284 |
Grade A, and why
vision-mcp-for-ds 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — 项目修改记录
本文件记录 vision-mcp-for-ds 项目的重要改动，供后续 AI agent / 开发者快速了解项目状态。
2026-08-08: 完善多客户端配置指南 (v1.3.0 文档)
背景：原 README 用一个「通用 JSON」示例覆盖所有客户端，但三个客户端格式各异（Reasonix 用 TOML、ZCode 用 JSON、OpenCode 用 JSONC），尤其 OpenCode 不允许在 mcp 配置里写 API key，一刀切示例会误导。
调研结论：
- Reasonix：
~/.reasonix/config.toml，[[plugins]]段，TOML 格式，key 在 env 里 - ZCode：
~/.zcode/cli/config.json，mcp.servers下，JSON 格式，key 在 env 里 - OpenCode：
~/.config/opencode/opencode.jsonc，mcp字段，JSONC 格式，不支持在配置里写 key（写了被拒/清除）。解决：用cwd字段指向部署目录，server 通过config.json读 key（config.ts 的process.cwd()查找逻辑正好满足，无需改代码）
改动（纯文档，无代码改动）：
- README「接入客户端」章节重写：按客户端分列（折叠式），各给从真实配置提取的准确格式
- OpenCode 单独说明 key 走 config.json 的两步操作（配 cwd + 建 config.json）
- mcp-config.example.json 重写为配置速查表（按客户端分段）
- README 部署章节补 OpenCode 需额外建 config.json 的提示
- 修 README 版本号残留（v1.2.0 → v1.3.0）
2026-08-08: 剔除 WorkBuddy 兼容 + 清理调试代码 (v1.3.0)
背景：端到端测试发现 WorkBuddy（v5.3.8）存在工具触发不稳定的问题——其「图片输入」开关与 MCP 工具路由冲突：
- 勾选图片输入 → WorkBuddy 把原图直接塞进 messages 发给 DS V4（纯文本模型）→ 报
unknown variant image_url - 取消图片输入 + 直接发图 → 前置拦截「当前模型暂不支持图片」
- 纯文字+路径 → DS V4 不主动调工具（工具未可靠注入 tools 声明）
- 仅「勾选→报错→取消→说继续」特定顺序能触发一次 MCP 调用（副作用，不可复现）
诊断证据：vision server 加调试日志后，/tmp/vision-mcp-debug.log 始终为空——证明 WorkBuddy 从未把请求发给我们的 stdio server。问题在 WorkBuddy 客户端层面，非本 server 代码问题。Reasonix 配置正确时可正常调用。
改动：
- 从 v1.3.0 支持列表中剔除 WorkBuddy，README/METHODOLOGY/mcp-config.example.json/pack.sh 同步改为「Reasonix / ZCode」
- README 增加客户端兼容性说明，指向
workbuddy-compat分支 - 清理 index.ts 的临时调试日志（debugLog / appendFileSync / wrapTool 的 name 参数）
- 版本号 1.2.0 → 1.3.0
后续：在 workbuddy-compat 分支研究 WorkBuddy 的 connector-proxy 机制与工具注入策略，待找到稳定 trigger 或 WorkBuddy 修复后再合并。
2026-08-08: 重定位为通用视觉桥 + 新增 opencode profile (v1.2.0)
目标：项目从「专为 Reasonix」转为「给 DS V4 等纯文本模型补视觉的通用 MCP 桥」，跨 Reasonix / ZCode / WorkBuddy；接入 OpenCode Go 套餐的视觉模型（MiMo-V2.5 / GLM-5.2 / Kimi K3 等）。
背景调研：动手前对比了社区竞品（ghbalf/llm-vision-mcp、farhanic017/opencode-vision、Capetlevrai/clipboard-vision-mcp），确认 MCP 视觉桥模式正确、本项目的 profile 多预设 + 部署脚本是差异化优势，予以保留并增强。
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 · 137 lines · 2,836 tokens per session scan A 311a85d7c79b
vision-mcp-for-ds AGENTS.md is an instructions file published in the GitHub repository Dellety/vision-mcp-for-ds (7 stars, last pushed 1mo ago), licensed MIT. It adds 2,836 tokens to every session, about $0.0142 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.