mimo-vision: Instructions file for Codex

AGENTS.md

mimo-vision AGENTS.md is an instructions file for Codex, OpenCode from wulusai2333/mimo-vision. It costs 1,454 tokens per session, scanned A, original, MIT.

Repository instructions for the mimo-vision plugin. They document its image-description tool, project layout, development conventions, and how it connects to vision models.

In plain words
What is it for?
Guiding changes and tests for the plugin that reads an image, sends it to a vision model, and returns a text description.
Why use it?
They help agents understand the plugin’s structure and the boundaries between pure logic, runtime context, image conversion, and model calls.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md.

This is wulusai2333/mimo-vision's own configuration. It tells Codex and OpenCode how to work on mimo-vision itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mimo-vision configures →

Reuse

Borrowing it

Nothing to install: this file belongs to wulusai2333/mimo-vision. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/wulusai2333/mimo-vision/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/wulusai2333/mimo-vision

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for mimo-vision AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/wulusai2333/mimo-vision/agents-md/github.svg)](https://agentmods.dev/instructions/wulusai2333/mimo-vision/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/wulusai2333/mimo-vision/agents-md"><img src="https://agentmods.dev/badge/instructions/wulusai2333/mimo-vision/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for mimo-vision AGENTS.md

Your own site · 80×15
<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="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,454 This file is loaded in full into every session.
When invoked 1,454 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.01454 $0.01454
Opus 5.5 $0.00582 $0.00582
Sonnet 5.5 $0.00291 $0.00291
Haiku 4.5 $0.00145 $0.00145

Measured 2mo ago against content hash f1c9f55ec34e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 2mo 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.

AGENTS.md · 65 lines

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_modules symlink 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。

Read the full file on GitHub · 65 lines

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. 2mo ago First seen · 65 lines · 1,454 tokens per session scan A f1c9f55ec34e

Subscribe to this mod's changes

mimo-vision AGENTS.md is an instructions file published in the GitHub repository wulusai2333/mimo-vision (1 stars, last pushed 2mo ago), licensed MIT. It adds 1,454 tokens to every session, about $0.0058 per session on Opus 5.5. 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

mimo-vision AGENTS.md compared with instructions from other repositories

mimo-vision AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
mimo-vision AGENTS.mdwulusai2333/mimo-visionInstructions file12mo agoMITA1,454Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode