learn-agent

Name: learn-agent
Author: 7-e1even

by 7-e1even

Verified

学习Agent开发的笔记，尝试让Agent从可用到可靠

273stars

14forks

JavaScript

Added 7/3/2026

Installation

# Add to your Claude Code skills
git clone https://github.com/7-e1even/learn-agent

Getting Started

Guides for using ai agents skills like learn-agent.

Caveman: Cut Claude Token Use by 65%
How agent-side prompt compression works, when to use it, and when not to.
What is an AI Skills Marketplace?
Definitions, how marketplaces work, and how to choose between them in 2026.
Getting Started with AI Skills

Security ReportVerified

Last scanned: 7/4/2026

{
  "issues": [],
  "status": "PASSED",
  "scannedAt": "2026-07-04T06:48:34.848Z",
  "npmAuditRan": true,
  "pipAuditRan": true,
  "promptInjectionRan": true
}

README.md

Frequently Asked Questions

What is learn-agent?

learn-agent is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by 7-e1even. 学习Agent开发的笔记，尝试让Agent从可用到可靠. It has 273 GitHub stars.

Is learn-agent safe to use?

Yes. learn-agent passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.

How do I install learn-agent?

Clone the repository with "git clone https://github.com/7-e1even/learn-agent" and add it to your Claude Code skills directory (see the Installation section above).

What programming language is learn-agent written in?

learn-agent is primarily written in JavaScript. It is open-source under 7-e1even on GitHub, so you can review or fork the full source.

Are there alternatives to learn-agent?

Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh learn-agent against similar tools.

Agentic AI for Beginners

Build your first AI agent from scratch - tool use, ReAct pattern, memory, deployment

41 minBeginner

Comments (0)

to leave a comment.

No comments yet. Be the first to share your thoughts!

Related Skills

ECC

by affaan-m

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

240,529

ai-prd-workflow pctx

learn-agent · AI Agent 开发笔记

简体中文 · English

开发桌面 agent Reina 过程中记下的笔记，讲 coding agent（Claude Code、Codex、opencode 这类工具）的内部实现机制。每篇讲一个机制，把 Reina 里的生产实现简化成零依赖、单文件、可直接运行的 Node 程序——所以这些做法不是照 API 文档推想的，是实际产品里验证过的。

所有机制最终都建立在同一个循环上

仓库分三块：notes/ 是正篇笔记（s01–s23，每篇一个机制，配可运行 demo）；agent_analysis/ 是其他 agent（pi、Kimi CLI）的源码调研档案，笔记从这里取材；interview/ 是从笔记整理的面试题（连载中）。

运行

Node 18+，零依赖：

git clone https://github.com/7-e1even/learn-agent && cd learn-agent
AGENT_API_KEY=sk-xxx node notes/s01_agent_loop/agent.mjs

任何 OpenAI 兼容的 API key（DeepSeek / Kimi / GLM / OpenRouter / 本地 Ollama）都行；没有 key 的话，多数章节的 demo.mjs 和 s12 的自测模式不需要 key。

clone 之后可以一键验证所有免 key 的示例：node selftest.mjs——20 个章末 demo 加 s12 的整合自测，十几秒跑完。

#	主题	要解决的问题
s01	Agent 主循环	最小可用的 agent 长什么样
s02	工具系统	工具越加越多，怎么不用每次都改循环
s03	循环预算与纠偏	模型原地打转、反复报错，怎么发现并拉回来
s04	工具输出预算与溢出	一条 `cat` 的输出就能撑爆上下文，怎么办
s05	流式输出与中断	用户按下 Ctrl+C，断在一半的消息记录怎么修
s06	上下文压缩	上下文满了要压缩，怎么不忘掉最初的任务
s07	Prompt 缓存	同样的对话，为什么有人的账单贵 10 倍
s08	会话持久化与恢复	进程崩了，跑了半小时的会话怎么接着跑
s09	子代理与看门狗	子任务卡死了，怎么发现它并保住已完成的部分
s10	System prompt 组装	system prompt 越写越长，怎么按需拼装
s11	多 agent 协作	几个 agent 同时干活，怎么分工不重复不冲突
s12	完整 agent 整合	前面所有机制装回一个循环里是什么样
s13	权限与审批	模型要执行 `rm -rf`，怎么在动手前拦住
s14	Provider 兼容层	换个模型 tool call 格式全乱，怎么兼容
s15	渐进式工具披露	工具有几十个，怎么不把上下文塞满
s16	MoA 多模型合议	让多个模型一起商量，到底值不值
s17	自进化复盘环	agent 能不能自己复盘对话，把学到的沉淀成记忆和技能
s18	自主任务的完成门	agent 说"做完了"，凭什么信
s19	压缩与缓存的冲突	压缩必然击穿缓存，怎么把损失降到最低
s20	自动长期记忆	跨项目自动沉淀该记住的事，不烧钱也不攒垃圾
s21	横读其他 agent	同一道题，pi 和 Kimi CLI 为什么给出相反的答案
s22	思考档位	思考档位从滑块到 API 请求，中间要过哪几关
s23	图片输入	一张 8MB 截图进上下文，要过哪几层处理