ReachAI is an enterprise agent development and runtime platform for connecting AI assistants to existing Java business systems such as OA, ERP, CRM, human resources, procurement, and ticketing applications. It lets employees query data, fill forms, and carry out business tasks through natural language while requiring confirmation for writes, submissions, and approvals.
Borrowing it
Nothing to install: this file belongs to w8123/EnterpriseAgentFramework. 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/w8123/EnterpriseAgentFramework/main/AGENTS.mdgit clone --depth 1 https://github.com/w8123/EnterpriseAgentFrameworkWrote 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/w8123/enterpriseagentframework/agents-md)<a href="https://agentmods.dev/instructions/w8123/enterpriseagentframework/agents-md"><img src="https://agentmods.dev/badge/instructions/w8123/enterpriseagentframework/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/w8123/enterpriseagentframework/agents-md"><img src="https://agentmods.dev/badge/instructions/w8123/enterpriseagentframework/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 | $0.01147 | $0.01147 |
| Opus 5.5 | $0.00459 | $0.00459 |
| Sonnet 5.5 | $0.00229 | $0.00229 |
| Haiku 4.5 | $0.00115 | $0.00115 |
Grade A, and why
EnterpriseAgentFramework 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 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ReachAI Agent Rules
进入仓库先读本文件,再从文档入口选择当前任务相关主题。人和 AI 共用一套文档,不另存项目记忆、历史方案或执行提示词。
工作边界
- 以当前代码、SQL、配置、接口与实际运行结果为事实源;文档中的目标不等于已实现或已验收。
- 只修改当前任务相关内容,保留其他未提交工作;常规实现自主推进,改变已确认产品边界时先明确方案与影响。
- 产品、用户和核心对象以产品说明为准。Capability 是业务资产统称,Tool 是调用投影,Workflow 是 GraphSpec;Skill 仅指标准包或协议字段。
- 不把文档、旧会话或未启动待办当作执行授权。不因整理代码或文档自动提交、推送、部署、改库或调用真实写业务。
- 开发库向开源库同步遵守开源同步规则:官网仅保留在开发库,使用过滤快照生成开源改动,不直接合并开发库历史。
- 搜索优先
rg/rg --files,中文文件使用 UTF-8。 - 帮用户部署、升级或排障 ReachAI 时,以用户指定的方式和现网结构为准,参考部署与运维手册选择操作,不限定于手册命令或
reachai.env。已明确授权的范围内自主推进,不因采用宝塔 MCP、独立 JAR/systemd 等现网方式重复确认;改库前按实际部署方式备份,保留无关服务和数据。
架构与数据
reachai-control-service是公共 API、身份与治理入口;reachai-runtime-service执行 Agent / Workflow。reachai-capability-service拥有项目来源、业务方法/API;reachai-knowledge-service拥有知识与检索投影;reachai-model-service统一模型调用。- 同库不共享表所有权。跨服务通过 internal API、显式 client 或服务自有 read model,不访问对方 Mapper、Entity 或 SQL 表。
- schema、索引、种子和字段语义变更同步
sql/initV2.sql;已有环境需要时新增 upgrade SQL 并更新sql/README.md,执行后回读验证。 - 精确依据:架构、表归属、内部 API、公共路由。
产品实现
- 业务能力改动同时服务 Java 开发者与 Agent / Workflow 实施人员,按U1–U4 验收关联具体任务。
- GraphSpec 保存执行语义,Canvas 只保存布局;Handler、发布校验、Studio 与 AI mutation 保持一致。
- 调用身份只能来自受验证链路;ACL、来源契约、版本 pin 与副作用保护不由浏览器或模型字段绕过。
- 前端先核对路由、MainLayout、共享组件和状态管理;复用公共 liquid-glass 入口与主题 token,规则见DESIGN。
eaf.*、X-EAF-*、Java/Maven/协议技术身份不随品牌文案顺手改名。- 随产品分发的内置 Skill 内容变更必须升级版本和摘要,见Skill 版本规则。
Windows 与 UTF-8
含中文的 Python、Node、JSON、SQL 或请求体优先写入 UTF-8 文件再执行。通过 PowerShell 管道传给原生程序时先设置:
$utf8 = [System.Text.UTF8Encoding]::new($false)
$OutputEncoding = $utf8
[Console]::InputEncoding = $utf8
[Console]::OutputEncoding = $utf8
API 或数据库写入中文后必须回读;出现连续 ? 视为失败,不继续验收。
验证与文档
- 后端运行相关模块的目标测试或编译;前端运行相关行为测试与
npm run build,需要时验证真实浏览器。 - 具体错误须复现或对照同一错误签名后才能声明修复。夹具、构建、制品、运行与业务验收分别说明边界。
- 文档只保留当前核心内容;同一事实维护一次,重复、过时和历史记录直接删除,不留归档。必要的未验条件统一写入 status。
- 移动、合并或删除文档同步引用和检查器,运行
node scripts/check-documentation.mjs、相关检查器测试与git diff --check。
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 · +17 tokens per session 710d43641cc0
- 3d ago Changed · +2 lines · +140 tokens per session 067601c66d37
- 9d ago Changed · -82 lines · -2,610 tokens per session 923eb28a192e
- 12d ago Changed · +2 lines · +135 tokens per session 35a60cbf44e0
- 20d ago Changed · +5 lines · +117 tokens per session 804b37fb5a37
- 1mo ago Changed · +1 lines · +92 tokens per session 4076c62ab83c
- 1mo ago Changed · +8 lines · +327 tokens per session 55ca4c1b58dd
- 2mo ago Changed · +2 lines · +165 tokens per session 00863885d810
- 2mo ago First seen · 115 lines · 2,764 tokens per session scan A 758225948b4b
EnterpriseAgentFramework AGENTS.md is an instructions file published in the GitHub repository w8123/EnterpriseAgentFramework (1,043 stars, last pushed yesterday), licensed MIT. It adds 1,147 tokens to every session, about $0.0046 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.
EnterpriseAgentFramework AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| EnterpriseAgentFramework AGENTS.mdw8123/EnterpriseAgentFramework | Instructions file | 1.0k | yesterday | MIT | A | 1,147 | Codex, OpenCode |
| 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 |