cloud-agent: Instructions file for Codex

AGENTS.md

cloud-agent AGENTS.md is an instructions file for Codex, OpenCode from seekskyworld/cloud-agent. It costs 938 tokens per session, scanned A, original, Apache-2.0.

Repository instructions for a cloud-agent codebase covering architecture boundaries, permissions, retries, cancellation, migrations, testing, and delivery checks. A cloud agent is software that performs work through services and external tools.

In plain words
What is it for?
Use them when changing TypeScript modules, adapters, workflows, authorization, task retries, migrations, packaging, or release checks in the cloud-agent project.
Why use it?
They define safety rules for identities, authorization, repeated actions, data changes, and external side effects so changes do not bypass important safeguards.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is seekskyworld/cloud-agent's own configuration. It tells Codex and OpenCode how to work on cloud-agent itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything cloud-agent configures →

Reuse

Borrowing it

Nothing to install: this file belongs to seekskyworld/cloud-agent. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/seekskyworld/cloud-agent/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/seekskyworld/cloud-agent

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for cloud-agent AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/seekskyworld/cloud-agent/agents-md/github.svg)](https://agentmods.dev/instructions/seekskyworld/cloud-agent/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/seekskyworld/cloud-agent/agents-md"><img src="https://agentmods.dev/badge/instructions/seekskyworld/cloud-agent/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.

agentmods 80×15 button for cloud-agent AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/seekskyworld/cloud-agent/agents-md"><img src="https://agentmods.dev/badge/instructions/seekskyworld/cloud-agent/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 938 This file is loaded in full into every session.
When invoked 938 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00938 $0.00938
Opus 5.5 $0.00375 $0.00375
Sonnet 5.5 $0.00188 $0.00188
Haiku 4.5 $0.00094 $0.00094

Measured 13d ago against content hash a3d634905102, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

cloud-agent 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 13d 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.

AGENTS.md · 38 lines

What it actually says

Coding agent guide

公共开发约定,不依赖本机技能或私有协作系统。修改前阅读 README、架构 和相关源码,检查 git status --short,保留他人改动。接业务先看 业务复用指南,再看 模块与适配器。优先复用现有任务、确认、身份和投递机制;领域 SQL 与框架同库组合时使用宿主事务端口,不在业务中复制第二套通用状态机。

边界与不变量

  • packages/ 不导入 apps/、modules/、adapters/ 或模型 SDK;业务在模块,外部协议在适配器,通过 apps/container.ts 装配。默认集合在 modules/catalog.ts,Worker 不按业务名分支。

  • Module.next(input, steps) 必须纯净:不访问网络、数据库、时钟或随机数。每个逻辑步骤 key 稳定,重试复用 context.idempotencyKey。

  • 声明工具副作用;未知写入不能直接重发,reconcilable_write 必须实现 reconcile。确认绑定参数,拒绝、过期、改参不得被 retry 绕过。

  • 身份、工作区和凭据来自可信服务端,不来自模型或客户端。角色不产生业务通配能力;授权变更须有版本检查、原因、幂等和审计。

  • 旧租约或已取消任务不得提交结果;取消不撤销远端动作。模块通过 validateContext / authorizeRead 复核领域权限,核心不猜测步骤数据形状。

  • 修改编排、协议、工具或授权语义时升级模块版本;迁移只能追加,不编辑已应用文件。模块为可信部署代码,不动态求值用户代码。

  • 通用发行版不内置领域业务;新业务通过独立包和端口装配。架构测试夹具放在 tests/fixtures/,不得被生产入口导入;本地 project/ 参考仓库不纳入 Git 或镜像。

代码与文档

TypeScript 严格模式,不用显式 any;优先短函数和显式参数,复杂约束与并发逻辑用简洁中文注释。改动聚焦目标,配置、API 和文档与实际行为同步,说明错误及恢复语义。

不提交 .env、凭据、备份、本机协作资料;公开文档不引用私人路径或会话。不要打印完整连接串、降低隔离检查或清空用户数据库来通过测试。

验证与交付

环境准备见 开发指南,按变更范围执行:

变更 验证
交付工具、发布或公开边界 另跑 pnpm test:tooling、pnpm secrets:check;候选包只从干净提交生成并校验
仅文档 pnpm docs:check、git diff --check
代码 pnpm format:check、pnpm check
页面 另跑 pnpm test:browser,检查桌面和手机截图
部署、迁移或授权存储 构建镜像,另跑 pnpm test:compose
SDK、公共 API、业务包 另跑 pnpm sdk:verify、pnpm contracts:check、pnpm evaluate;基线变更须解释兼容性
数据生命周期/联合恢复 另跑 pnpm test:recovery,只使用新建测试库
依赖 pnpm licenses:generate、pnpm licenses:check,检查锁文件与许可

覆盖率仅统计 packages/**,不能当作整仓覆盖率。交付说明变化、实测结果和未验证范围。提交使用 feat: / fix: / docs: 等前缀,推送和发布须有维护者授权。

Changes

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.

  1. 13d ago First seen · 38 lines · 938 tokens per session scan A a3d634905102

Subscribe to this mod's changes

cloud-agent AGENTS.md is an instructions file published in the GitHub repository seekskyworld/cloud-agent (18 stars, last pushed yesterday), licensed Apache-2.0. It adds 938 tokens to every session, about $0.0038 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 2026-10-14.

Related

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).

microsoft/vscode · 9,715 tokens

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.

vercel/next.js · 7,461 tokens

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).

microsoft/vscode · 5,262 tokens

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.

langchain-ai/langchain · 4,680 tokens

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).

microsoft/vscode · 2,731 tokens

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.

denoland/deno · 3,077 tokens