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/wsshow/feikong-teams/agents-mdgit clone --depth 1 https://github.com/wsshow/feikong-teamsWrote 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/wsshow/feikong-teams/agents-md)<a href="https://agentmods.dev/instructions/wsshow/feikong-teams/agents-md"><img src="https://agentmods.dev/badge/instructions/wsshow/feikong-teams/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 5.1 | $0.02646 | $0.02646 |
| Opus 5 | $0.01323 | $0.01323 |
| Sonnet 5 | $0.00529 | $0.00529 |
| Haiku 4.5 | $0.00265 | $0.00265 |
Grade A, and why
feikong-teams 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 6d 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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
fkteams 开发指南
项目概览
fkteams 是基于 CloudWeGo Eino ADK 的 Go 多智能体协作系统，提供 CLI/TUI、Web UI、OpenAI 兼容 API，以及 Discord、QQ、微信消息通道。前端位于 web/，构建产物通过 //go:embed 嵌入 Go 二进制。
本文件适用于整个仓库。若子目录以后增加更具体的 AGENTS.md，只写该子树的增量规则；冲突时以更具体的文件和用户当次指令为准。
- Go 模块：
fkteams，版本以go.mod为准。 - 前端：React、TypeScript、Vite、Bun。
- 默认应用目录：
~/.fkteams；可通过FEIKONG_APP_DIR覆盖。 - 完整架构说明见
docs/architecture.md；修改跨层依赖或运行链路前先阅读该文档。
常用命令
# 完整质量检查（格式、前端类型检查与构建、Go vet/test、diff check）
make check
# 开发与定向验证
make web-build
go test ./path/to/package
go test ./path/to/package -run TestName
go build ./...
go vet ./...
# 运行
go run ./cmd/fkteams
go run ./cmd/fkteams web # 默认监听 :23456
go run ./cmd/fkteams serve
# 前端
cd web && bun run dev
cd web && bun test src
# 发布构建
make native
make all
make build t=linux:amd64
make clean
# 生成配置示例
go run ./cmd/fkteams generate config
go build ./...、go test ./... 和 go vet ./... 依赖已生成的 web/dist；直接运行这些命令前先执行 make web-build，或使用已包含该步骤的 Make 目标。web/dist/ 与 release/ 是生成物，不提交。
架构边界
分层与依赖方向
cmd -> bootstrap -> adapters -> app/runtime -> ports -> domain
internal/domain只放领域模型和值对象，不依赖框架、SDK、app、runtime或adapters。internal/ports定义运行时无关契约，不依赖app、runtime或具体 adapter。internal/app实现用例，不导入具体 adapter、Eino 或终端展示库。internal/runtime提供运行时无关内核，不依赖app或具体 adapter。internal/adapters实现外部技术和传输协议；Eino 只能出现在internal/adapters/runtime/eino。internal/bootstrap是组合根，负责创建并连接 runtime、模型、工具、存储和后台服务。cmd/fkteams/main.go保持最小化，只连接组合根和 CLI 命令入口。
入口必须调用 internal/app 用例，不能在 CLI、HTTP 或消息通道中重新实现核心业务流程。注册表和运行态依赖必须由应用实例持有并显式注入；不要引入可变的进程级默认实例、依赖注册副作用的 init() 或空白 import。
不要恢复已经移除的根级 agentcore、events、server、cli、channels 门面。对应实现分别位于 internal/app、internal/runtime/events 和 internal/adapters/transport。
关键目录
cmd/fkteams/：可执行入口。internal/app/：chat、agent、tools、memory、schedule、skill、lifecycle 等用例。internal/domain/：event、history、memory、message、schedule、session 等领域类型。internal/ports/：hooks、memory、runtime、scheduler、storage、tools 契约。internal/runtime/：turn、events、hooks、checkpoint、retry、pathguard 等内核能力。internal/adapters/：模型、runtime、工具、存储、调度器和传输实现。internal/bootstrap/：默认依赖与服务装配。web/：React 前端；web/dist/为生成物。
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.
- 6d ago First seen · 154 lines · 2,646 tokens per session scan A 9d8ce6fc4dcb
feikong-teams AGENTS.md is an instructions file published in the GitHub repository wsshow/feikong-teams (145 stars, last pushed 24d ago), licensed MIT. It adds 2,646 tokens to every session, about $0.0132 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
hivekeep CLAUDE.md
Claude Code instructions for MarlBurroW/hivekeep, covering hivekeep, documentation map, tech stack, key conventions and naming.
Proma AGENTS.md
AGENTS.md instructions for proma-ai/Proma, covering proma 工程约定, 必须遵守, 常用命令, 开发 and 构建 / 类型检查 / 测试.
in-bed-ai CLAUDE.md
Claude Code instructions for geeks-accelerator/in-bed-ai, covering inbed.ai, multi-agent collaboration, tech stack, commands and local testing (required before commit).
agents AGENTS.md
AGENTS.md instructions for pertamaxxx/agents, covering agents.md, project overview, repository structure, nested agents.md files and setup.
CommonGround AGENTS.md
Instructions for Intelligent-Internet/CommonGround, covering repository guidelines, repository role, documentation priority, code structure and common commands.
twiko AGENTS.md
Instructions for ezocomp118-source/twiko, a project described as: Self-hosted AI agents with their own computers — browser, terminal, files, and long-term memory. MCP tools, app integrations, and scheduled routines. Bring your own model. Web, desktop, and mobile. Apache-2.0.