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 skills add fanqingxuan/awesome-skills --skill einogit clone --depth 1 https://github.com/fanqingxuan/awesome-skillsWrote 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/skills/fanqingxuan/awesome-skills/eino)<a href="https://agentmods.dev/skills/fanqingxuan/awesome-skills/eino"><img src="https://agentmods.dev/badge/skills/fanqingxuan/awesome-skills/eino/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/skills/fanqingxuan/awesome-skills/eino"><img src="https://agentmods.dev/badge/skills/fanqingxuan/awesome-skills/eino.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 | $0.00126 | $0.05470 |
| Opus 5 | $0.00063 | $0.02735 |
| Sonnet 5 | $0.00025 | $0.01094 |
| Haiku 4.5 | $0.00013 | $0.00547 |
Grade A, and why
eino 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 12d 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 — 773 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Eino 框架开发指南
Eino 是字节跳动开源的 Golang LLM/AI 应用开发框架,专注于 Agent 开发、工作流编排、工具调用。
环境要求
- Go 版本: 1.18+
- 代码规范: golangci-lint
快速开始
安装
go get github.com/cloudwego/eino
go get github.com/cloudwego/eino-ext
项目初始化
# 创建项目
mkdir my-eino-app && cd my-eino-app
go mod init my-eino-app
# 安装依赖
go get github.com/cloudwego/eino
go get github.com/cloudwego/eino-ext/components/model/openai
核心示例
1. ChatModelAgent(基础 Agent)
最简单的对话 Agent:
package main
import (
"context"
"fmt"
"os"
"github.com/cloudwego/eino-ext/components/model/openai"
"github.com/cloudwego/eino/adk"
)
func main() {
ctx := context.Background()
// 配置 ChatModel
chatModel, err := openai.NewChatModel(ctx, &openai.ChatModelConfig{
Model: "gpt-4o",
APIKey: os.Getenv("OPENAI_API_KEY"),
})
if err != nil {
panic(err)
}
// 创建 Agent
agent, err := adk.NewChatModelAgent(ctx, &adk.ChatModelAgentConfig{
Model: chatModel,
})
if err != nil {
panic(err)
}
// 运行 Agent
runner := adk.NewRunner(ctx, adk.RunnerConfig{Agent: agent})
iter := runner.Query(ctx, "Hello, who are you?")
for {
event, ok := iter.Next()
if !ok {
break
}
fmt.Println(event.Message.Content)
}
}
2. 带工具的 Agent
添加工具调用能力:
package main
import (
"context"
"fmt"
"os"
"github.com/cloudwego/eino-ext/components/model/openai"
"github.com/cloudwego/eino/adk"
"github.com/cloudwego/eino/compose"
"github.com/cloudwego/eino/components/tool"
)
// 定义天气工具
type WeatherTool struct{}
func (w *WeatherTool) Info(ctx context.Context) (*tool.Info, error) {
return &tool.Info{
Name: "get_weather",
Desc: "Get current weather for a location",
ParamsOneOf: tool.NewParamsOneOfByParams(
map[string]*tool.ParameterInfo{
"location": {
Type: "string",
Desc: "City name",
Required: true,
},
},
),
}, nil
}
func (w *WeatherTool) InvokableRun(ctx context.Context, argumentsInJSON string) (string, error) {
// 实际应该调用天气 API
return fmt.Sprintf("Weather in %s: Sunny, 25°C", argumentsInJSON), nil
}
func main() {
ctx := context.Background()
chatModel, _ := openai.NewChatModel(ctx, &openai.ChatModelConfig{
Model: "gpt-4o",
APIKey: os.Getenv("OPENAI_API_KEY"),
})
// 创建工具
weatherTool := &WeatherTool{}
// 创建带工具的 Agent
agent, _ := adk.NewChatModelAgent(ctx, &adk.ChatModelAgentConfig{
Model: chatModel,
ToolsConfig: adk.ToolsConfig{
ToolsNodeConfig: compose.ToolsNodeConfig{
Tools: []tool.BaseTool{weatherTool},
},
},
})
runner := adk.NewRunner(ctx, adk.RunnerConfig{Agent: agent})
iter := runner.Query(ctx, "What's the weather in Beijing?")
for {
event, ok := iter.Next()
if !ok {
break
}
fmt.Println(event.Message.Content)
}
}
What ships with it
60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/docs_examples/_typos.toml 267 B
- references/docs_examples/.golangci.yaml 226 B
- references/docs_examples/.licenserc.yaml 145 B
- references/docs_examples/adk/.example.env 179 B
- references/docs_examples/adk/common/model/chat_model.go 2.8 KB
- references/docs_examples/adk/common/prints/util.go 3.6 KB
- references/docs_examples/adk/common/store/store.go 1.1 KB
- references/docs_examples/adk/common/tool/approval_wrapper.go 2.4 KB
- references/docs_examples/adk/common/tool/follow_up_tool.go 2.5 KB
- references/docs_examples/adk/common/tool/graphtool/examples/1_chain_summarize/main.go 6.2 KB
- references/docs_examples/adk/common/tool/graphtool/examples/1_chain_summarize/README.md 2.6 KB
- references/docs_examples/adk/common/tool/graphtool/examples/2_graph_research/main.go 7.0 KB
- references/docs_examples/adk/common/tool/graphtool/examples/2_graph_research/README.md 4.8 KB
- references/docs_examples/adk/common/tool/graphtool/examples/3_workflow_order/main.go 8.9 KB
- references/docs_examples/adk/common/tool/graphtool/examples/3_workflow_order/README.md 4.2 KB
- references/docs_examples/adk/common/tool/graphtool/examples/4_nested_interrupt/main.go 8.7 KB
- references/docs_examples/adk/common/tool/graphtool/examples/4_nested_interrupt/README.md 6.2 KB
- references/docs_examples/adk/common/tool/graphtool/graph_tool.go 8.7 KB
- references/docs_examples/adk/common/tool/graphtool/README.md 5.6 KB
- references/docs_examples/adk/common/tool/review_edit_wrapper.go 3.3 KB
- references/docs_examples/adk/common/trace/coze_loop.go 2.3 KB
- references/docs_examples/adk/helloworld/helloworld.go 2.0 KB
- references/docs_examples/adk/human-in-the-loop/1_approval/agent.go 2.0 KB
- references/docs_examples/adk/human-in-the-loop/1_approval/main.go 4.2 KB
- references/docs_examples/adk/human-in-the-loop/1_approval/README_ZH.md 3.8 KB
- references/docs_examples/adk/human-in-the-loop/1_approval/README.md 4.1 KB
- references/docs_examples/adk/human-in-the-loop/2_review-and-edit/agent.go 1.6 KB
- references/docs_examples/adk/human-in-the-loop/2_review-and-edit/main.go 2.6 KB
- references/docs_examples/adk/human-in-the-loop/2_review-and-edit/README_ZH.md 5.9 KB
- references/docs_examples/adk/human-in-the-loop/2_review-and-edit/README.md 6.7 KB
- references/docs_examples/adk/human-in-the-loop/2_review-and-edit/tool.go 1.2 KB
- references/docs_examples/adk/human-in-the-loop/3_feedback-loop/main.go 2.2 KB
- references/docs_examples/adk/human-in-the-loop/3_feedback-loop/README_ZH.md 5.9 KB
- references/docs_examples/adk/human-in-the-loop/3_feedback-loop/README.md 6.7 KB
- references/docs_examples/adk/human-in-the-loop/3_feedback-loop/reviewer_agent.go 3.2 KB
- references/docs_examples/adk/human-in-the-loop/3_feedback-loop/writer_agent.go 1.7 KB
- references/docs_examples/adk/human-in-the-loop/4_follow-up/follow_up_agent.go 2.6 KB
- references/docs_examples/adk/human-in-the-loop/4_follow-up/main.go 2.3 KB
- references/docs_examples/adk/human-in-the-loop/4_follow-up/README_ZH.md 8.7 KB
- references/docs_examples/adk/human-in-the-loop/4_follow-up/README.md 9.8 KB
- references/docs_examples/adk/human-in-the-loop/4_follow-up/trip_planner_agent.go 1.6 KB
- references/docs_examples/adk/human-in-the-loop/5_supervisor/agent.go 7.3 KB
- references/docs_examples/adk/human-in-the-loop/5_supervisor/main.go 3.4 KB
- references/docs_examples/adk/human-in-the-loop/5_supervisor/README_ZH.md 4.5 KB
- references/docs_examples/adk/human-in-the-loop/5_supervisor/README.md 4.8 KB
- references/docs_examples/adk/human-in-the-loop/6_plan-execute-replan/agent.go 4.9 KB
- references/docs_examples/adk/human-in-the-loop/6_plan-execute-replan/main.go 3.8 KB
- references/docs_examples/adk/human-in-the-loop/6_plan-execute-replan/README_ZH.md 5.4 KB
- references/docs_examples/adk/human-in-the-loop/6_plan-execute-replan/README.md 5.6 KB
- references/docs_examples/adk/human-in-the-loop/6_plan-execute-replan/tools.go 11 KB
- references/docs_examples/adk/human-in-the-loop/7_deep-agents/agent.go 5.5 KB
- references/docs_examples/adk/human-in-the-loop/7_deep-agents/main.go 3.5 KB
- references/docs_examples/adk/human-in-the-loop/7_deep-agents/README_ZH.md 5.5 KB
- references/docs_examples/adk/human-in-the-loop/7_deep-agents/README.md 6.0 KB
- references/docs_examples/adk/human-in-the-loop/7_deep-agents/tools.go 6.2 KB
- references/docs_examples/adk/human-in-the-loop/8_supervisor-plan-execute/agent.go 7.7 KB
- references/docs_examples/adk/human-in-the-loop/8_supervisor-plan-execute/main.go 3.6 KB
- references/docs_examples/adk/human-in-the-loop/8_supervisor-plan-execute/README_ZH.md 9.2 KB
- references/docs_examples/adk/human-in-the-loop/8_supervisor-plan-execute/README.md 9.6 KB
- references/docs_examples/adk/human-in-the-loop/8_supervisor-plan-execute/tools.go 8.2 KB
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.
- 12d ago First seen · 773 lines · 126 tokens per session scan A ec4e3ef33628
eino is a skill published in the GitHub repository fanqingxuan/awesome-skills (27 stars, last pushed 4mo ago), licensed MIT. It adds 126 tokens to every session and 5,470 once invoked, about $0.0006 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 skills, from other repositories
golang-pro
Implements concurrent Go patterns using goroutines and channels, designs and builds microservices with gRPC or REST, optimizes Go application performance with pprof, and enforces idiomatic Go with generics, interfaces, and robust error handling. Use when building Go applications requiring concurrent programming…
go-concurrency
Use when writing or reviewing Go concurrency — goroutines, channels, errgroup, context cancellation, or goroutine leaks. Not for sequential idioms (go-core-idioms).
go-core-idioms
Use when writing or reviewing idiomatic sequential Go — error handling, slog logging, generics, interfaces, style. Not for concurrency (go-concurrency).
go
Use when writing Go services, CLIs, or libraries. Covers idiomatic error wrapping, goroutine and context discipline, interface design, table-driven tests, and the race detector.
py2go
Migrate Python projects to idiomatic Go end-to-end. Branches into 6 project-type playbooks (CLI, TUI, HTTP backend, data pipeline, async worker, library) with the right stack defaults (Gin, pgx, sqlc, slog, etc.) and pinned library versions. Default strategy: LLM module-by-module rewrite with golden-file parity tests…
test-go
Write, review, and improve Go test code for this project. Use whenever generating, reviewing, or modifying Go tests - including when invoked by the Tester agent, the /test prompt, or any test-related request. Covers table-driven tests, subtests, t.Parallel(), test helpers with t.Helper(), error assertions via…