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/cholf5/skynet/agents-mdgit clone --depth 1 https://github.com/cholf5/skynetWhat 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 | $0.02712 | $0.02712 |
| Opus 5 | $0.01356 | $0.01356 |
| Sonnet 5 | $0.00542 | $0.00542 |
| Haiku 4.5 | $0.00271 | $0.00271 |
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 2d 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 — 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.CoreSkynet.ClusterSkynet.NetSkynet.Extras
2. C# 编码规范
- 语言版本:C# 13 (net9.0)
- 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
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.
- 2d ago First seen · 336 lines · 2,712 tokens per session scan A 5b3459d100c7
skynet AGENTS.md is an instructions file published in the GitHub repository cholf5/skynet (21 stars, last pushed 11mo ago), licensed MIT. It adds 2,712 tokens to every session, about $0.0136 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
planning-with-files AGENTS.md
AGENTS.md instructions for OthmanAdi/planning-with-files, covering agents.md — planning-with-files agent reference card, commit rules, release checklist (12 steps), version bump scope and changelog format.
DevoxxGenieIDEAPlugin GEMINI.md
Instructions for devoxx/DevoxxGenieIDEAPlugin, a project described as: DevoxxGenie is an agentic plugin for IntelliJ IDEA that uses local LLM's (Ollama, LMStudio, GPT4All, Jan and Llama.cpp) and Cloud based LLMs to help review, test, explain your project code. Latest version now also supports Spec Driven Development…
squarebox CLAUDE.md
Instructions for SquareWaveSystems/squarebox, covering claude.md, agent skills, issue tracker, triage labels and domain docs.
mcpelevator CLAUDE.md
Instructions for pacnpal/mcpelevator, covering commands, architecture, conventions, agent skills and issue tracker.
clawchat-plugin-connect AGENTS.md
Instructions for XMethues/clawchat-plugin-connect, covering agent skills, issue tracker, triage labels and domain docs.
autonomous-dev CLAUDE.md
Claude Code instructions for akaszubski/autonomous-dev, covering autonomous-dev, critical rules, maintainer escape hatches, architecture and code navigation.