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 skills add jianchen08/Agent-os-open --skill resource-tool-creategit clone --depth 1 https://github.com/jianchen08/Agent-os-openWrote 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/skills/jianchen08/agent-os-open/resource-tool-create)<a href="https://agentmods.dev/skills/jianchen08/agent-os-open/resource-tool-create"><img src="https://agentmods.dev/badge/skills/jianchen08/agent-os-open/resource-tool-create.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 | $0.00046 | $0.00876 |
| Opus 5 | $0.00023 | $0.00438 |
| Sonnet 5 | $0.00009 | $0.00175 |
| Haiku 4.5 | $0.00005 | $0.00088 |
Grade A, and why
创建工具 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 yesterday.
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
创建工具
本技能是流程指引，不是逐条打勾清单：按场景判断使用，遇不适用情况保持裁量，不机械执行。
工具创建流程（TDD 模式）
1. 需求分析
- 明确工具的名称、描述、核心能力、分类（ToolCategory）
- 明确输入输出接口和使用场景
2. 编写测试（Red 阶段）
- 测试写到
src/tools/builtin/test_{tool_id}.py - 覆盖：核心功能、边界情况、错误处理
- 测试中引用尚未实现的工具类（import {ToolId}Tool）
- 运行测试确认失败（Red）
3. 生成工具代码（Green 阶段）
- 代码写到
src/tools/builtin/{tool_id}.py - 写最少的代码让测试通过，不做过度设计
- 运行测试确认通过（Green）
4. 重构优化（Refactor 阶段）
- 测试通过前提下优化代码
- 运行测试确认无回归
5. 验证提交
- 运行全部测试通过
- yaml_validate 验证配置格式（如有配置）
命名规范
| 对象 | 规范 | 示例 |
|---|---|---|
| 工具 ID | snake_case | web_search |
| 文件名 | snake_case.py | web_search.py |
| 类名 | PascalCase | WebSearchTool |
工具类规范
- 所有工具继承
BuiltinTool基类 - 实现
get_tool_definition()静态方法 - 实现
execute()异步方法 - 中文注释，类型注解，遵循项目现有风格
ToolCategory 枚举（必须使用大写）
| 枚举值 | 说明 |
|---|---|
| FILE | 文件操作 |
| SEARCH | 搜索 |
| WEB | Web 操作 |
| MEMORY | 记忆检索 |
| TASK | 任务管理 |
| SYSTEM | 系统工具 |
| EXECUTION | 命令执行 |
| ANALYSIS | 分析 |
| EVALUATION | 评估 |
| AGENT | Agent 调用 |
| MONITORING | 监控 |
路径规范
| 资源 | 路径 |
|---|---|
| 工具代码 | src/tools/builtin/{tool_id}.py |
| 工具测试 | src/tools/builtin/test_{tool_id}.py |
| 工具配置（可选） | config/tools/ |
| 隔离策略（可选） | config/isolation/isolation_policy.yaml |
注意事项
- 创建工具只需创建
{tool_id}.py，无需修改__init__.py，系统自动发现 - 隔离策略由
config/isolation/isolation_policy.yaml统一管理，代码中不设置隔离属性 - 如需特殊隔离，在该配置文件中添加工具配置
- 为工具设置准确的 category 标签（对应 ToolCategory 枚举）
- 工具名称要能反映功能（名称用于配置匹配）
验证清单
创建工具后逐项核对：
- 工具代码文件
src/tools/builtin/{tool_id}.py存在 - 测试文件
src/tools/builtin/test_{tool_id}.py存在且通过 - 继承 BuiltinTool，实现 get_tool_definition() 和 execute()
- ToolCategory 设置正确
- 命名规范一致（tool_id snake_case / 类名 PascalCase）
- 无需改 init.py
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.
- yesterday Changed · +2 lines 9f4a32f3c24f
- 6d ago First seen · 90 lines · 46 tokens per session scan A 2e8a33472662
创建工具 is a skill published in the GitHub repository jianchen08/Agent-os-open (5 stars, last pushed 2d ago), licensed Apache-2.0. It adds 46 tokens to every session and 876 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
pytest-suite
Write or extend the backend test suite following this project's conventions. Use when adding tests for a new service/route/repository, when coverage is missing, or when asked to test a feature. Knows the mocked-session + httpx AsyncClient setup so tests run with no database.
Pair Programming
AI-assisted pair programming with multiple modes (driver$navigator$switch), real-time verification, quality monitoring, and comprehensive testing. Supports TDD, debugging, refactoring, and learning sessions. Features automatic role switching, continuous code review, security scanning, and performance optimization with…
agent-implementer-sparc-coder
Agent skill for implementer-sparc-coder - invoke with $agent-implementer-sparc-coder.
agent-tdd-london-swarm
Agent skill for tdd-london-swarm - invoke with $agent-tdd-london-swarm.
kotlin-testing
Kotlin testing patterns with Kotest, MockK, coroutine testing, property-based testing, and Kover coverage. Follows TDD methodology with idiomatic Kotlin practices.
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.