Yuxi is a self-hosted, multi-tenant knowledge-agent platform that combines document retrieval, knowledge graphs, multi-agent workflows, tools, sandboxes, and access controls in one workspace. Teams use it to build source-backed question answering and multi-step agents while managing their data, models, and permissions. The catalogue entries provide agents, skills, and instructions for Yuxi workflows.
Borrowing it
Nothing to install: this file belongs to xerrors/Yuxi. 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/xerrors/Yuxi/main/AGENTS.mdgit clone --depth 1 https://github.com/xerrors/YuxiWrote 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/xerrors/yuxi/agents-md)<a href="https://agentmods.dev/instructions/xerrors/yuxi/agents-md"><img src="https://agentmods.dev/badge/instructions/xerrors/yuxi/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/xerrors/yuxi/agents-md"><img src="https://agentmods.dev/badge/instructions/xerrors/yuxi/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 | $0.02296 | $0.02296 |
| Opus 5.5 | $0.00918 | $0.00918 |
| Sonnet 5.5 | $0.00459 | $0.00459 |
| Haiku 4.5 | $0.00230 | $0.00230 |
Grade A, and why
Yuxi 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 2d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Yuxi Agent 开发约定
Yuxi 是基于 LangGraph、FastAPI、Vue 和多种持久化服务构建的知识库与多智能体平台。Docker Compose 是开发拓扑的事实来源;用符号搜索确认模块的真实实现。
按任务范围加载
- 始终以本文件为准;修改
backend/、frontend/或docs/时,同时读取该子树的AGENTS.md。子树规则只补充本目录,不复制回根文件。 - 改一个文案、修一个小 bug、机械重命名或等价清理:只读根与适用子树指令及直接相关源码或文档;架构和开发指南按下一条的任务条件加载。
- 跨模块设计或实现、改变状态/权限/持久化/外部副作用,或需要选择架构方案:先读 ARCHITECTURE.md;非平凡变更再读 Yuxi Spec Loop 和工程信任系统,涉及测试时读测试规范。
- 提交或创建 PR 前读取贡献指南。只有同时运行多个分支、复用长期数据或处理 Schema 不兼容时,才读取并行工作树与隔离运行环境。
- 用户在当前任务中的明确要求优先于本文件。
任务与决策
- 开始实现前,把请求压缩为可验证的目标、非目标和验收主张;多步任务先给出每步带验证方式的简短计划。
- 设计前先从原始需求描述最小完整流程,区分用户明确要求、已有系统约束和自行添加的保证,并检查现有能力能否直接完成。按能力的业务语义确定归属,不能仅因某个调用者使用它就归入该调用者模块。新增机制须说明:删除它会破坏哪个真实需求、消费者或已有承诺;无法说明时,先尝试复用或删除。复用接口或新增条件分支前,按语义边界检查核对事实 Owner、接口承诺、调用者专属规则和其他调用路径。
- 假设显式记录后继续;只有当不同解释会改变验收结果、数据、安全或外部状态时才阻塞询问,并把候选解释一并列出而不是默默选择其一。存在明显更简单的方案时,先说明取舍再动手。
- 把"可以""也可以""类似这样""例如"当作简单方向,不是设计更大机制、配置项或兼容层的许可。
- 在真实语义 Owner 处闭合受影响的工程主张:源码、数据约束或当前契约拥有事实;独立 oracle 与负向案例证明它;实际 workflow 或可问责 Reviewer 产生拒绝后果。不要建立可独立编辑的中央主张清单或 claim ID 体系。
- 非平凡变更必须新增或更新一份 tracked 决策记录。记录问题、当前决定、真实替代项、后果和验证,不保存推理流水账或实现过程叙事。
docs/vibe/只用于本地临时计划,被 Git 忽略,不是组织记忆,也不能作为已完成事实的唯一来源。- 只修改验收标准需要的范围;不顺手重构、格式化或添加想象中的配置、兼容层和扩展点。
不能破坏的系统事实
- HTTP 路由保持薄;用例流程属于 各业务域的
services,持久化查询属于 各业务域的repositories。 - 普通输入先在 PostgreSQL 中持久化 Input 原始消息和 Receipt;消费事务创建正式 Message 并绑定 Turn/Run、附件,提交后才投递 ARQ。Redis 负责投递、短期事件、取消和缓存,不拥有最终业务状态。
- 每次提交拥有独立 Input;同一用户、APP、Agent、Thread 的 follow-up 按 FIFO 单条派发,steer 优先并在消费时合并连续就绪前缀,运行中在安全边界接管。等待回答或审批时禁止普通消息;协作等待只接收 FIFO 输入。取消与转引导只操作指定 pending Input。
- Turn 的最终输出必须来自 result_run_id 指向的顶层 Run;Run 的输出、事件、artifact 和错误绑定同一 Turn/Run,禁止从相邻 Run 猜测结果。
- 非终态 Run 必须有明确执行 Owner、lease/heartbeat 或等价机制,以及崩溃后的可观察结局。
/api/system/health只表达进程 liveness;接流量前置条件由/api/system/ready证明,业务正确性仍由真实链路测试证明。- LangGraph checkpoint 只使用 PostgreSQL;API、worker 与 Agent 不提供本地后端选择或静默降级。
- 权限在后端依赖与 repository 可见性查询处最终执行;前端守卫、prompt、schema omission 和 UI 隐藏不是授权边界。
- 默认部署包含知识库、图谱与评估能力;显式关闭 Knowledge 时,启动、路由、能力发现与 worker 装配保持一致,保留代码和数据。Agent 知识库访问经 MCP,后端复核当前用户权限与会话选择交集;附件 parser 按需加载。
- 沙盒虚拟路径、对象 URL 和宿主机路径不可混用;所有用户路径必须在 owning filesystem boundary 校验。
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.
- 2d ago Changed · +55 tokens per session d105c240399d
- 3d ago Changed · +3 lines · +177 tokens per session d9fe7fc12c52
- 7d ago Changed · +4 tokens per session 17051d30a29e
- 11d ago Changed · -2 lines · +155 tokens per session 9bb74d219a50
- 1mo ago Changed · -12 tokens per session 40e1f3b4f632
- 2mo ago Changed · +1 lines · +44 tokens per session 9093682c476f
- 2mo ago First seen · 78 lines · 1,873 tokens per session scan A 70fc05bf1261
Yuxi AGENTS.md is an instructions file published in the GitHub repository xerrors/Yuxi (7,613 stars, last pushed yesterday), licensed MIT. It adds 2,296 tokens to every session, about $0.0092 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.
Yuxi AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| Yuxi AGENTS.mdxerrors/Yuxi | Instructions file | 7.6k | yesterday | MIT | A | 2,296 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | 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 | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |