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 instructions/alisunstar/opensunstar/agents-mdgit clone --depth 1 https://github.com/alisunstar/OpenSunstarWrote 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/alisunstar/opensunstar/agents-md)<a href="https://agentmods.dev/instructions/alisunstar/opensunstar/agents-md"><img src="https://agentmods.dev/badge/instructions/alisunstar/opensunstar/agents-md.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 | $0.01063 | $0.01063 |
| Opus 5 | $0.00531 | $0.00531 |
| Sonnet 5 | $0.00213 | $0.00213 |
| Haiku 4.5 | $0.00106 | $0.00106 |
Grade A, and why
OpenSunstar 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 3d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — AI Agent Integration Guide
商业控制面隔离与发版边界
账号、订阅与计费、多租户团队服务及云端运维属于独立维护的私有商业控制面,是 OpenSunstar 核心商业化许可边界。本公开仓库仅包含 Apache-2.0 授权的公共客户端、os CLI、本地配置与工作流能力,以及展示或调用可选控制面能力的客户端侧集成。
发版、README/website 同步、tag、GitHub Release、npm 发布与远程推送时,必须保持以下隔离:
- 私有商业控制面源码、服务端实现、计费系统、多租户服务、云端运维配置与部署脚本,必须保留在独立私有远程仓库和本地私有仓库。
- 本仓库发版内容不得包含
opensunstar-control-plane、control-plane私有目录、@opensunstar/control-plane包,或E:\projects\opensunstar-control-plane本地路径内容。 - 若商业控制面有更新,必须独立安排私有仓库提交、推送、部署与发版,不与本公开仓库发版混合。
- 公共客户端中保留的订阅账号、团队配置等 UI / API 适配仅代表客户端入口,不等同于私有商业控制面源码授权。
CLI 治理与编排工具 (os)
当检测到 AI 编程工具配置异常时,可运行以下命令诊断:
os drift check --json # 检查配置漂移
os readiness score --json # Agent 就绪度评分
os doctor --json # 环境诊断
os flow validate --json # 阶段门禁校验
os flow validate --strict --json # 跨模块治理门禁(检查设计合约/Recipe/Specs 就位)
os project status --json # 项目全景状态(聚合编排+资产+漂移)
退出码约定: 0=正常, 1=有发现(如漂移/门禁阻断), 2=治理门禁阻断(strict), 3=错误
所有命令支持 --json 输出机器可读格式。
写操作支持 --dry-run 预览和 --yes 跳过确认。
全局选项
| 选项 | 说明 |
|---|---|
--json |
输出 JSON 格式(机器消费) |
--timeout <seconds> |
操作超时(秒),防止 Agent 会话无限挂起 |
错误输出格式
JSON 模式下错误输出包含 code、message、hint 三字段,便于 Agent 自动诊断:
{
"error": true,
"code": "error",
"message": "数据库不存在: ...",
"hint": "运行 os config bootstrap --yes 初始化,或检查 ~/.OpenSunstar 目录权限"
}
常用诊断流程
# 0. 首次使用(无 GUI 时)
os config bootstrap --yes
# 1. 环境健康检查
os doctor --json
# 2. 配置漂移扫描(强制刷新缓存)
os drift check --refresh --json
# 3. 就绪度评分
os readiness score --json
# 4. 漂移修复(预演)
os drift repair --dry-run --json
# 5. 漂移修复(执行)
os drift repair --yes --json
项目编排闭环
# 项目全景状态(聚合 DB 资产 + 文件系统编排状态)
os project status --project-path /path/to/project --json
# 阶段门禁(标准:检查 .specs/ 工件)
os flow validate --project-path . --project-type web --change-id CHG-001 --target-stage implementation --json
# 阶段门禁(严格:额外检查设计合约/Recipe/FlowConfig 就位)
os flow validate --project-path . --project-type web --change-id CHG-001 --target-stage implementation --strict --json
# 导出 CI 门禁配置
os flow config --project-path . --project-type web --json
# Recipe 安装预检
os recipe plan --project-path . --name my-recipe --json
# Recipe 安装到项目
os recipe install --project-path . --name my-recipe --yes --json
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.
- 3d ago First seen · 100 lines · 1,063 tokens per session scan A 9bd70d3c084f
OpenSunstar AGENTS.md is an instructions file published in the GitHub repository alisunstar/OpenSunstar (40 stars, last pushed 20d ago), licensed Apache-2.0. It adds 1,063 tokens to every session, about $0.0053 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 2026-08-30.
Other instructions, from other repositories
momo-code AGENTS.md
AGENTS.md instructions for momozi1996/momo-code, covering agents.md -- project agent instructions, how to work with this codebase, getting started, making changes and quality gates (enforced).
cli copilot-instructions.md
Instructions for semanticash/cli: Review pull requests for correctness, regressions, and missing tests before style concerns.
momo-code CLAUDE.md
Claude Code instructions for momozi1996/momo-code, covering claude.md -- agent working agreement, project context, code patterns, testing and commit style.
dsh-TUI AGENTS.md
AGENTS.md instructions for ccch1mneyyy/dsh-TUI, covering agents.md, 仓库布局, 命令, 上游边界与契约 and 约定与红线.
aider-desk AGENTS.md
AGENTS.md instructions for hotovo/aider-desk, covering agents.md, common commands, development, type checking and linting and formatting.
sortie copilot-instructions.md
Instructions for sortie-ai/sortie, covering sortie coding & review standards, 1. layered imports (downward only; violation is critical), 2. concurrency safety, 3. workspace path safety (critical: security boundary) and 4. persistence (sqlite).