Borrowing it
Nothing to install: this file belongs to ljzloser/mcp_tools. 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/ljzloser/mcp_tools/master/.github/instructions/plugins.instructions.mdgit clone --depth 1 https://github.com/ljzloser/mcp_toolsWrote 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/ljzloser/mcp_tools/plugins)<a href="https://agentmods.dev/instructions/ljzloser/mcp_tools/plugins"><img src="https://agentmods.dev/badge/instructions/ljzloser/mcp_tools/plugins/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/ljzloser/mcp_tools/plugins"><img src="https://agentmods.dev/badge/instructions/ljzloser/mcp_tools/plugins.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 | $0.01539 | $0.01539 |
| Opus 5.5 | $0.00616 | $0.00616 |
| Sonnet 5.5 | $0.00308 | $0.00308 |
| Haiku 4.5 | $0.00154 | $0.00154 |
Grade A, and why
plugin-development 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.
How it starts
The opening of the file, as written. The whole thing — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP Tool Hub 插件开发指南
插件结构
每个插件目录包含:
__init__.py— 导出PLUGIN_CLASS和WIDGET_CLASS(可选)backend.py— 插件后端逻辑widget.py— 可选的 PySide6 UI 组件README.md— 插件文档(必须)
目录名不能以 _ 或 . 开头。
后端模式
基本结构
from api.base_plugin import BasePlugin
from api.tool import ToolDef, MCPToolResult
from api.config import ConfigModel, StringField
from pydantic import BaseModel, Field
# 可选:配置模型
class MyPluginConfig(ConfigModel):
api_key = StringField(default="", label="API 密钥", description="...")
# 工具参数模型
class MyToolArgs(BaseModel):
input_text: str = Field(description="输入文本")
# 插件类
class MyPlugin(BasePlugin[MyPluginConfig]):
config_class = MyPluginConfig
# 工具声明 — 使用类属性 ToolDef
my_tool = ToolDef(
name="my_tool",
args_model=MyToolArgs,
description="工具描述"
)
@property
def meta(self) -> PluginMeta:
return PluginMeta(
name="my_plugin",
display_name="我的插件",
version="1.0.0",
description="插件功能描述",
author="MCP Tool Hub",
icon="🔧"
)
async def handle_my_tool(self, args: MyToolArgs) -> MCPToolResult:
try:
result = f"处理: {args.input_text}"
return MCPToolResult(content=[{"type": "text", "text": result}])
except Exception as e:
return MCPToolResult(
content=[{"type": "text", "text": f"错误: {e}"}],
is_error=True
)
工具声明规范
- 使用
ToolDef类属性(非装饰器) name: 工具唯一名称,全局唯一args_model: Pydantic BaseModel,用于参数验证和 JSON Schema 生成description: 工具功能描述,供 AI 客户端使用
返回格式
统一使用 MCPToolResult:
# 成功
MCPToolResult(content=[{"type": "text", "text": "结果"}])
# 错误
MCPToolResult(content=[{"type": "text", "text": "错误信息"}], is_error=True)
访问配置
class MyPlugin(BasePlugin[MyPluginConfig]):
async def handle_my_tool(self, args):
# 直接通过 self.config 访问配置字段
api_key = self.config.api_key
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.
- 2mo ago First seen · 228 lines · 1,539 tokens per session scan A 4ea0bbe8d682
plugin-development is an instructions file published in the GitHub repository ljzloser/mcp_tools (4 stars, last pushed 4mo ago), licensed MIT. It adds 1,539 tokens to every session, about $0.0062 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.
plugin-development compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| plugin-developmentljzloser/mcp_tools | Instructions file | 4 | 4mo ago | MIT | A | 1,539 | GitHub Copilot |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |