Borrowing it
Nothing to install: this file belongs to RunhuaHuang/VisionPower. 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/RunhuaHuang/VisionPower/main/AGENTS.mdgit clone --depth 1 https://github.com/RunhuaHuang/VisionPowerWrote 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/runhuahuang/visionpower/agents-md)<a href="https://agentmods.dev/instructions/runhuahuang/visionpower/agents-md"><img src="https://agentmods.dev/badge/instructions/runhuahuang/visionpower/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.
<a href="https://agentmods.dev/instructions/runhuahuang/visionpower/agents-md"><img src="https://agentmods.dev/badge/instructions/runhuahuang/visionpower/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00484 | $0.00484 |
| Opus 5.5 | $0.00194 | $0.00194 |
| Sonnet 5.5 | $0.00097 | $0.00097 |
| Haiku 4.5 | $0.00048 | $0.00048 |
Grade A, and why
VisionPower 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 1mo 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.
What it actually says
VisionPower — Agent 快速通道
如果你正在 Kimi Code 中访问本仓库
本仓库自带 kimi.plugin.json 插件清单，首选用 Kimi Code 插件方式安装，不要走 MCP 手动配置或 Skill 拷贝的路：
/plugins install https://github.com/RunhuaHuang/VisionPower
然后 /reload（或开新会话）激活。插件同时声明 Skill 与 MCP server，两种方式都可用。本机调试时也可 /plugins install /path/to/local/VisionPower。
dsh（DeepSeek Harness）
当任务是在 dsh（DeepSeek Harness）上安装 / 配置 / 修复 / 验证 VisionPower（拖图识图插件）时，不要手动拼装安装步骤，直接运行一键安装器（幂等，可反复执行）：
npx -y visionpower@latest setup-dsh --launch
# 或本仓库内：node scripts/setup-dsh.mjs --launch
安装器自动完成：装插件 → 挂载 cordis → 打「拖图不拒绝」补丁 → 启动并自动弹出配置控制台（http://127.0.0.1:17900，CONFIG 页选视觉模型 + 粘贴 API Key + 保存）→ 验证 → 启动 dsh web。等待用户在控制台完成配置（最长 180 秒，可 --wait-secs 调整），配置好后安装器会继续走完验证。若插件已装好，也可以直接调用 setup_visionpower 工具完成同样的事。
严格禁止：不要手动安装 @deepseek-ai/cordis、@deepseek-ai/dsh-tools、@deepseek-ai/dsh-llm、@deepseek-ai/schemastery，也不要开启 autoInstallPeers——它们是可选 peer 依赖，必须经 dsh 内置软链回退解析，否则会遮蔽内置副本，导致所有工具调用报 Cannot read properties of undefined (reading 'prepare')。
其余说明见 README「作为 dsh (DeepSeek Harness) Cordis 插件使用」章节。
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.
- 1mo ago Changed · +12 lines · +126 tokens per session 237d7e22bc50
- 2mo ago First seen · 15 lines · 358 tokens per session scan A ea1c37114df4
VisionPower AGENTS.md is an instructions file published in the GitHub repository RunhuaHuang/VisionPower (68 stars, last pushed 1mo ago), licensed MIT. It adds 484 tokens to every session, about $0.0019 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 2026-08-30.
VisionPower AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| VisionPower AGENTS.mdRunhuaHuang/VisionPower | Instructions file | 68 | 1mo ago | MIT | A | 484 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode model-prompts.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 2,022 | GitHub Copilot |