Borrowing it
Nothing to install: this file belongs to wentf9/xops-cli. 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/wentf9/xops-cli/master/AGENTS.mdgit clone --depth 1 https://github.com/wentf9/xops-cliWrote 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/wentf9/xops-cli/agents-md)<a href="https://agentmods.dev/instructions/wentf9/xops-cli/agents-md"><img src="https://agentmods.dev/badge/instructions/wentf9/xops-cli/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/wentf9/xops-cli/agents-md"><img src="https://agentmods.dev/badge/instructions/wentf9/xops-cli/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 | $0.01624 | $0.01624 |
| Opus 5.5 | $0.00650 | $0.00650 |
| Sonnet 5.5 | $0.00325 | $0.00325 |
| Haiku 4.5 | $0.00162 | $0.00162 |
Grade A, and why
xops-cli 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 15d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI 助手开发协作指南 (AGENTS.md)
0. 优先级与工作模式
- 接受任何开发任务前，先说明：用户目标、相关模块、已定位的源文件、预计更改范围、验证方法、仍需确认的事实。
- 调查 / 文档生成：默认只读，不修改源码/配置，不运行可能创建凭据、执行远程命令或修改主机的操作。
- 开发：先提交简短影响分析；跨越两个以上子系统（
core/ssh,core/mcp,pkg/config,pkg/credential,internal/mcphost,pkg/playbook,cmd）或触及持久化/授权/协议/兼容性时，先给方案并明确验收门槛。 - 禁止凭名称猜测模块职责、编造函数、编造测试结果；重要事实附
路径:符号，必要时附准确行号。无法确认时写「待验证」。 - 先阅读
docs/development/governance/architecture-map.md的导航与与任务有关的已有设计，再精确阅读被修改代码；不强制每次通读全部文档。
1. 不可破坏的包边界
cmd/：Cobra 命令注册、参数解析、表现层与 CLI 组合根；不在此创建第二套 SSH/SFTP、配置持久化或 MCP 策略引擎。pkg/config/：配置Repository是持久变更边界，Provider提供版本一致的读取视图；已有事务/冲突/持久性语义不可绕过。pkg/credential/与internal/credentialfile/：凭据服务、引用和离线凭据持久化；禁止将明文写回遗留字段、日志或错误。pkg/adapter/、internal/sshenv/、internal/mcphost/：将应用配置、认证、运行环境和策略装配到core/；不得在 core 中重新引入 CLI 依赖。core/ssh/、core/sftp/：唯一共享 SSH/SFTP 执行与传输能力；新能力优先在现有入口中扩展。core/mcp/{ports,sshexec,state,guardrail,runtime,transfer,tunnel}：协议契约、执行后端、状态准入、护栏、运行时与任务生命周期各有边界；不可因为“调用更简单”绕开 permit、binding、policy 或 snapshot。pkg/playbook/：编排、步骤结果、重试政策；不能自行再实现一套 SSH 远程执行器。core/**的所有代码、测试与 fixture 不得 importcmd/**、pkg/**或根internal/**；不得依赖外部xops-mcp消费者。参见core/README.md和docs/development/shared-core-decoupling.md。
2. 开发底线
- Go 1.26+；保留 Go 缩写规范（ID、URL、SSH、CLI、SFTP、TCP）；遵守 gofmt 与仓库 golangci-lint v2。
- 任何连接、文件、租约、会话、goroutine 和取消函数必须标明谁拥有、何时释放；优先用
defer，但借用资源不应随意Close。不要关闭调用方持有的输入输出流。 - 网络与并发操作必须有有界生命周期；取消需要使等待/子协程最终终止。需要同步的共享状态明确采用何种锁/通道/不可变快照策略，禁止数据竞争和锁反转。
- 错误用
%w/errors.Is/errors.As保留语义；远程命令执行区分not_started、completed、unknown；未知结果不自动重试。 - 禁止隐式放宽 SSH 主机信任、鉴权、MCP 风险分级、HTTP Token/Origin/Host 校验、路径保护、审批、审计或传输任务授权绑定。
- 不为解决局部问题新增与既有实现平行的管理器、wrapper 或类型别名。确需新抽象时，说明替代什么、消除什么复杂性、何处调用、如何验证。
- 不顺带做无关格式化/重命名/大范围移动。历史文档与协议 fixture 不得因“看起来旧”而直接覆盖。
3. 每次变更的固定交付
- 变更前：目标与非目标；具体源码/符号；拥有职责的包；受影响调用方；兼容与安全风险；拟执行的测试。
- 变更后：修改摘要；行为对照；实际运行的测试及结果；未运行项目及理由；剩余风险。只有当变更影响 CLI/MCP 对外契约或实际设计时更新相关文档（中英文公开文档均需同步）。
- 修复 bug 原则上添加能复现旧问题的回归测试；修改高风险路径需要边界情况与取消/错误路径测试。若确不能测，明确记录原因及替代证据。
- 不将
go build ./...、go test ./...、lint、交叉编译、native 平台执行等同。构建≠原生平台测试，lint≠回归测试。不要宣称未执行的步骤通过。
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.
- 15d ago Changed · +11 lines · +682 tokens per session b431e777ce7b
- 2mo ago First seen · 50 lines · 942 tokens per session scan A c6ceb0f01004
xops-cli AGENTS.md is an instructions file published in the GitHub repository wentf9/xops-cli (21 stars, last pushed yesterday), licensed MIT. It adds 1,624 tokens to every session, about $0.0065 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 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.