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 agents/xerrors/yuxi/tools-systemgit clone --depth 1 https://github.com/xerrors/YuxiWhat 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 | $0.00000 | $0.01300 |
| Opus 5 | $0.00000 | $0.00650 |
| Sonnet 5 | $0.00000 | $0.00260 |
| Haiku 4.5 | $0.00000 | $0.00130 |
Grade A, and why
tools-system 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.
How it starts
The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
工具系统
Yuxi 的工具分成三层：内置工具、知识库工具和 MCP 工具。Graph 创建时准备可执行工具，运行时再根据用户权限、Agent 配置和 Skill 激活状态决定模型能看到什么。
注册一个内置工具
普通内置工具使用 @tool 注册：
from yuxi.agents.toolkits.registry import tool
@tool(category="buildin", tags=["示例"], display_name="示例工具")
def example_tool(text: str) -> str:
"""返回处理后的文本。"""
return text
category用于前端分组，常见值是buildin、knowledge和debug；tags用于展示和筛选；display_name是给用户看的名称，工具 ID 是给代码和模型协议使用的稳定名称；- 工具模块需要被
toolkits包导入，装饰器才会执行注册。
工具的注册不等于授权。产生文件、网络或数据库副作用的工具必须在执行边界再次校验当前用户和目标资源。
当前内置能力
常用内置工具包括：
| 工具 | 作用 |
|---|---|
ask_user_question |
等待用户回答交互式问题 |
ocr_parse_file |
把工作区中受支持的 PDF、Office 或图片转换为 Markdown |
present_artifacts |
展示当前用户可见的文件产物 |
install_skill |
从允许的沙盒路径或 Git 来源安装个人 Skill；子智能体不可用 |
web_search |
使用已配置的豆包或 Tavily 搜索网页 |
文件读写和命令执行由 Agent 的 Sandbox backend 提供。present_artifacts 推荐展示当前 Project 的 outputs/ 文件；large_tool_results 和会话摘要等内部文件不会作为交付物展示。
图片生成能力由内置 image-gen Skill 提供，不再作为独立的 Python 工具注册。具体依赖和文件位置由该 Skill 说明。
知识库工具
知识库工具以 @tool(category="knowledge") 注册，但不默认出现在模型工具列表。Agent 激活内置 knowledge-base Skill 后，Skills middleware 才会向模型开放：
| 工具 | 作用 |
|---|---|
list_kbs |
列出当前运行可见的知识库 |
query_kb |
按 kb_id 检索片段，返回 kb_id、file_id 和内容 |
find_kb_document |
在指定文件中按关键词或正则定位内容 |
open_kb_document |
按 file_id 分段读取解析后的文档 |
get_mindmap |
读取知识导图 |
search_file |
按文件名搜索可见知识库中的文件 |
download_kb_file |
把有权限的原始文件下载到当前 Project 的 outputs/ |
工具参数中的 kb_id、file_id 和文件名都会在工具执行处重新检查，不能用模型提示词或 Agent 配置绕过知识库权限。知识库不会挂载为沙盒目录，读取方式见知识库机制详解。
需要在 Python 中直接取得知识库工具时：
from yuxi.agents.toolkits.kbs import get_common_kb_tools
kb_tools = get_common_kb_tools()
返回的具体顺序由函数实现维护，不要把顺序当作协议。
工具组装流程
内置 Agent 创建 Graph 时执行：
prepare_agent_runtime_context按当前用户权限过滤工具、知识库、MCP、Skills 和子智能体。resolve_configured_runtime_tools(context)注册 Agent 配置和可见 Skill 依赖的可执行本地工具，并加载配置的 MCP 工具。SkillsMiddleware根据当前已预加载或已激活的 Skill，向模型请求开放相应工具 schema。- 工具执行器再次检查具体文件、知识库、MCP 和用户身份。
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 First seen · 108 lines · 0 tokens per session scan A c2d5fc17b84e
tools-system is an agent published in the GitHub repository xerrors/Yuxi (6,591 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,300 tokens. 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.
Other agents, from other repositories
txtify-qa
QA gatekeeper for Txtify. Use to run the full verification ladder on the current tree and report evidence — before merging, releasing, or when asked "does everything still work?".
agents
Agent 模块是系统的执行引擎，基于 LangGraph StateGraph 实现单个 Agent 的完整执行生命周期管理。.
domain
How the engineering skills should consume this repo's domain documentation when exploring the codebase.
2026-04-20-relay-handoff
Demo Agent Ada found that Relay parser failures were caused by missing fenced-code terminators in synthetic notes.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.