skynet: Instructions file for Codex

AGENTS.md

skynet AGENTS.md is an instructions file for Codex, OpenCode from cholf5/skynet. It costs 2,712 tokens per session, scanned A, original, MIT.

Project instructions for a software repository that uses a Kanban board to track work. Kanban is a workflow where tasks move through stages such as backlog, development, review, testing, and completion.

In plain words
What is it for?
Reading the project requirements, creating or updating Markdown task records, following task statuses, evaluating whether test-driven development applies, and recording review or QA results.
Why use it?
It gives the coding agent clear rules for project tracking, code standards, reviews, testing, and acceptance.

Instructions file for CodexOpenCode

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

This is cholf5/skynet's own configuration. It tells Codex and OpenCode how to work on skynet 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 skynet configures →

Reuse

Borrowing it

Nothing to install: this file belongs to cholf5/skynet. 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/cholf5/skynet/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/cholf5/skynet

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 skynet AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/cholf5/skynet/agents-md/github.svg)](https://agentmods.dev/instructions/cholf5/skynet/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/cholf5/skynet/agents-md"><img src="https://agentmods.dev/badge/instructions/cholf5/skynet/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 skynet AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/cholf5/skynet/agents-md"><img src="https://agentmods.dev/badge/instructions/cholf5/skynet/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,712 This file is loaded in full into every session.
When invoked 2,712 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 $0.02712 $0.02712
Opus 5.5 $0.01085 $0.01085
Sonnet 5.5 $0.00542 $0.00542
Haiku 4.5 $0.00271 $0.00271

Measured 1mo ago against content hash 2752af0363c2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

skynet 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 1mo 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 · 336 lines

How it starts

The opening of the file, as written. The whole thing — 336 lines — stays where its author put it; the contents beside it link to each section on GitHub.

阅读 ./docs/PRD.md 了解项目背景和需求。

看板工作流

本项目使用看板工作流进行任务管理,请严格遵守以下规范。

统一 Kanban 看板列(项目级):

  • Backlog(需求池)
  • To Do(Sprint/当前周期待办)
  • In Progress(开发中)
  • In Review(代码审查)
  • Testing / QA(QA 测试中)
  • Blocked(阻塞)
  • Done(验收通过)

每个任务卡必须包含:目标、子任务、开发者、估算复杂度(S/M/L)、验收标准、测试用例、相关文件/设计稿、依赖任务。

任务状态定义(严格)

  • 开发(In Progress):除了完成任务外,还需包含单元测试(若适用)。
  • Code Review(In Review):PR 描述需写清修改点、运行方式、影响面、回归风险;至少 1 名审查者通过(由你切换身份扮演)。
  • QA(Testing):QA 按测试用例执行,记录 BUG,BUG 分级(P0/P1/P2)。所有 P0 必须解决,P1 需评估。QA 完成后 QA 在卡片上写“QA Passed”(由你切换身份扮演)。
  • 验收/Done:产品经理或维护者对接收准则(Acceptance Criteria)进行最终验收,若通过,移动卡片到 Done。(由你切换身份扮演)

Kanban 数据记录在 ./kanban/ 目录(Markdown 格式).

  • ./kanban/board.md 维护看板状态。
  • ./kanban/issues/ 目录存放每个任务的详细描述(Markdown), 每个任务一个文件,文件名为任务 ID,例如 A-1-initialize-repo.md。此文件内不但要记录任务描述,还要记录开发过程中遇到的问题与解决方案、BUG 记录、Review 意见等。

请检查 ./kanban/ 目录:

  • 如果不存在,请根据 PRD 创建初始看板和任务文件。
  • 如果存在,请根据看板上的任务状态,继续推进任务,或遵照用户本次的指示进行工作。

编码规范

👌 明白,这里我帮你整理一份 编码规范与约定,以及 TDD 是否适用的评估。这些内容是专门写给编程 Agent 的(即自动化开发工具 / AI 编码助手),以确保整个项目风格统一、可维护、可扩展。


Skynet 编码规范与约定

1. 项目结构

  • 解决方案结构

    Skynet.sln
    src/
      Skynet.Core/        // 核心运行时 (ActorSystem, ActorRef, send/call)
      Skynet.Cluster/     // 跨节点通信
      Skynet.Net/         // Socket/Http/WebSocket/Gate 模块
      Skynet.Extras/      // Multicast, DataCenter, DebugConsole 等
      Skynet.Examples/    // 示例项目 (EchoServer, ChatRoom, ClusterDemo)
    tests/
      Skynet.Core.Tests/
      Skynet.Cluster.Tests/
      ...
    
  • 命名空间

    • Skynet.Core
    • Skynet.Cluster
    • Skynet.Net
    • Skynet.Extras

2. C# 编码规范

  • 语言版本:C# 14 (net10.0)
  • 缩进:Tab(宽度 4)
  • 文件编码:UTF-8 (no BOM)
  • 大括号:Allman 风格({ 独占一行)
  • 类命名:PascalCase(ActorSystem, ActorRef)
  • 方法命名:PascalCase(Send, CallAsync)
  • 变量命名:camelCase(actorRef, channel)
  • 字段命名:前缀 _(_mailbox, _logger)
  • 常量:大写 + 下划线(MAX_QUEUE_LENGTH)
  • 接口:以 I 开头(IActor, ILoginService)
  • 泛型参数:以 T 开头(TMessage, TResponse)
  • 禁止 var 滥用,只有在类型显而易见时才允许 var
  • 使用表达式主体 (=>) 时必须保持简洁,不要写复杂逻辑

Read the full file on GitHub · 336 lines

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. 1mo ago Changed 2752af0363c2
  2. 2mo ago First seen · 336 lines · 2,712 tokens per session scan A 5b3459d100c7

Subscribe to this mod's changes

skynet AGENTS.md is an instructions file published in the GitHub repository cholf5/skynet (23 stars, last pushed 1mo ago), licensed MIT. It adds 2,712 tokens to every session, about $0.0108 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.

Related

skynet AGENTS.md compared with instructions from other repositories

skynet AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
skynet AGENTS.mdcholf5/skynetInstructions file231mo agoMITA2,712Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode