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/wulusai2333/mimo-vision/agents-mdgit clone --depth 1 https://github.com/wulusai2333/mimo-visionWrote 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/wulusai2333/mimo-vision/agents-md)<a href="https://agentmods.dev/instructions/wulusai2333/mimo-vision/agents-md"><img src="https://agentmods.dev/badge/instructions/wulusai2333/mimo-vision/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 | $0.01454 | $0.01454 |
| Opus 5 | $0.00727 | $0.00727 |
| Sonnet 5 | $0.00291 | $0.00291 |
| Haiku 4.5 | $0.00145 | $0.00145 |
Grade A, and why
mimo-vision 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 3d 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Overview
mimo-vision 是一个 DSH 原生工具插件(mimo-vision),注册唯一工具 describe_image(path, question?):把图片经 ctx.fs 读入、key 经 ctx.credentials 发现、发往 mimo-v2.5 视觉模型(免费线路优先、付费兜底)、返回文字描述。它体现 DSH 的核心范式:一切皆插件、注册即效果、inject 声明依赖、能力走接缝。
Project Structure & Module Organization
mimo-vision/
├── src/
│ ├── index.ts # 插件入口:name/inject/Config/apply + describe_image
│ ├── invariant.ts # 空 invariant 伴生(仓库测试门禁约定)
│ ├── key.ts # 纯逻辑:OPENCODE_GO_API_KEY → OPENCODE_API_KEY 解析
│ ├── routes.ts # 纯逻辑:免费→付费线路解析
│ ├── transcode.ts # 非原生格式经 ctx.subprocess→ImageMagick 转 PNG
│ ├── vision.ts # HTTP 调用 + payload/提取(纯 helper 可单测)
│ └── types.ts # 类型 only
├── lib/ # 提交的预构建产物(tsdown 输出),GitHub 源安装直接加载
├── tests/ # vitest(纯逻辑 + 真 Context 集成)
├── adr/ # ADR-0002 记录本改造决策
├── cordis.patch.yml # bundle patch(package.json 的 dsh.bundle 声明它,自动挂载)
├── package.json / tsconfig.json
└── CONTEXT.md / README.md / AGENTS.md
- 纯逻辑(
key.ts/routes.ts/vision.ts的 helper)零@deepseek-ai/*运行时依赖,可独立单测。 - 只有
index.ts直接触碰接缝(ctx.tools/ctx.fs/ctx.credentials);transcode.ts经ctx.subprocess调 ImageMagick,但转码中间文件用node:fs写系统临时目录(见 README「Known Limitations」)。 lib/是提交的预构建产物(lib/index.js即 loader 的main入口),供 GitHub 源安装直接加载;改src/后需按下方命令重建并同步lib/。package.json的peerDependencies用"*"(不用workspace:^):全部@deepseek-ai/*接缝(含@deepseek-ai/schemastery)由 DSH 的依赖闭包(~/.dsh/profiles/node_modulessymlink 到 dsh 安装树)在运行时统一提供并保证单例。同时每个 peer 在peerDependenciesMeta里标记为optional,避免 pnpm/npm 在 DSH 闭包之外独立安装时去 registry 解析未发布的内部包链而失败;绝不要把@deepseek-ai/*挪进dependencies(workspace:^在 profile 的独立 workspace 里无法解析、会导致安装失败,且会 pnpm 独立复制破坏单例接缝)。monorepo 内的devDependencies仍用workspace:^无妨。cordis.patch.yml用- insert:+id: tool-vision(对齐插件导出的name),并由package.json的dsh.bundle字段声明。mimo-vision 是 bundle:dsh plugin add github:...会自动 reconcile 成 profile 层并激活工具,无需手改 patch。
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.
- 3d ago First seen · 65 lines · 1,454 tokens per session scan A f1c9f55ec34e
mimo-vision AGENTS.md is an instructions file published in the GitHub repository wulusai2333/mimo-vision (2 stars, last pushed 18d ago), licensed MIT. It adds 1,454 tokens to every session, about $0.0073 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
PixelRAG CLAUDE.md
Instructions for StarTrail-org/PixelRAG, covering pixelrag, layout and conventions.
agentsys CLAUDE.md
Claude Code instructions for agent-sh/agentsys, covering agentsys, critical rules, model selection, core priorities and dev commands.
dsh-auto-review AGENTS.md
Instructions for PerryLink/dsh-auto-review, covering agents.md, layout, hard rules applied here, build and docs.
dsh-codex-sync AGENTS.md
Instructions for Walvez/dsh-codex-sync, covering agents.md — dsh-codex-sync, 定位, 怎么跑, 技术栈 and 目录与约定.
dsh-industry-research AGENTS.md
Instructions for PerryLink/dsh-industry-research, covering agents.md, layout, hard rules applied here, checks and release.
omdp AGENTS.md
Instructions for XJungit/omdp, covering agents.md — omdp 仓库开发规范, 工作前提(先读再做), 规范 1:文档随插件同步更新, 规范 2:教训经验主动沉淀为文档笔记 and 笔记索引.