Learn Agent
学习Agent开发的笔记
Supply asset profile
Coding and developer agents
Code review, repo analysis, testing, CI, GitHub, DevOps, and developer workflow skills.
Scenario
Coding agents
I need a coding agent that can understand a repository, edit code, and review pull requests.
Agent fit
Claude Code + OpenAI Agents + CLI
Codex, Claude Code, Cursor, CLI, or custom agents.
Install
Ready
npx skills add 7-e1even/learn-agent
Maintenance
fresh
1d since push
Risk
Needs review
Permission surface may require sandboxing
GitHub quality
84
76/100 quality · 74/100 trust
Coverage tags
Review notes
Permission surface may require sandboxing · Quality score needs review
Agent adoption scorecard
Trust, audit, and install readiness at a glance
These scores combine public repository metadata, OpenAgentSkill review signals, maintenance freshness, and install readiness. They are a shortlist signal, not a replacement for human review.
Quality
StrongSolid option that is likely worth shortlisting for production workflows.
Trust
Sandbox onlyUseful candidate with missing or mixed trust signals. Keep it in an isolated workspace until the outcome loop proves task fit.
Audit
Needs reviewInstall readiness, security metadata, maintenance, and adoption risk.
Trust Score v5
Human review before install
Run only in a sandbox and compare close alternatives before using it for real work.
Stars
84 GitHub stars
Repo activity
84 stars, 7 forks
Maintenance
1d since push
License
MIT
Install
npx skills add 7-e1even/learn-agent
Install safety
standard package or runtime install path
Permission surface
secrets or environment access, network or browser access
Agent outcomes
No agent outcome data yet
Docs
Strong README/SKILL.md context
Risk summary
Review before production
- Quality score needs review
- Permission surface needs review: secrets or environment access, network or browser access
- GitHub adoption: 84 GitHub stars
- Stars/forks activity: 84 stars, 7 forks; issue activity unavailable in current metadata
Install readiness
Install path available
- Install path is available
- Repository evidence is available
- License is declared
- No Agent Proven outcome evidence yet
Agent-readable metadata
Machine-readable decision data for this skill.
Use this block or the embedded JSON to decide whether an agent should install this skill, choose an alternative, or ask for human review first.
Suited tasks
- Coding agents workflows
- Claude Code teams
- builders willing to evaluate younger projects
- Inspect source files
Suited agents
Install decision
- Command
- npx skills add 7-e1even/learn-agent
- Policy
- review
- Human review
- yes
Trust and risk
- Trust
- 66/100
- Audit
- 81/100
- Risk level
- Needs review
Outcome loop
- Endpoint
- /api/agent/outcome
- Event ID
- resolve
- Outcomes
- 5
Do not use when
- teams that need a vendor-supported SLA
- high-compliance environments without internal security review
- No major risk signals from current metadata
- High-risk permission hints: Secrets or environment access
- Permission surface may require sandboxing
Alternative
Graphify
79.1K stars
npx skills add Graphify-Labs/graphify
Alternative
Gemini CLI
105.8K stars
npx skills add google-gemini/gemini-cli
Alternative
System Prompts And Models Of AI Tools
141.2K stars
npx skills add x1xhlol/system-prompts-and-models-of-ai-tools
Alternative
Caveman
86.0K stars
npx skills add JuliusBrussee/caveman
Agent safety v2
53/100 · Avoid automatic install
Sparse or mixed signals. Useful for discovery, but not for autonomous installation.
Test manually in an isolated workspace and compare against safer alternatives.
medium
Network access
Skill likely fetches remote pages, APIs, repositories, or external services.
medium
Filesystem access
Skill may read or write project files, documents, generated artifacts, or local workspace state.
high
Secrets or environment access
Skill metadata references credentials, tokens, environment variables, or secret-bearing workflows.
- High-risk permission hints: Secrets or environment access
- Permission surface may require sandboxing
Install targets
Install this skill in your agent workflow
Copy the registry command or an agent-specific install prompt for Codex, Claude Code, and Cursor.
OpenAgentSkill CLI
Use the registry command when your workflow supports the OpenAgentSkill installer.
$ npx skills add 7-e1even/learn-agentAgent resolve plan
Let an agent verify fit before installing.
The Resolve API returns the selected skill, alternatives, safety policy, audit notes, install target, and copy-paste prompt an agent can follow without scraping this page.
Resolve JSON
/api/agent/resolve?task=Use%20Learn%20Agent%20for%20an%20agent%20workflow&agent=codex&max_risk=medium
Resolve text
/api/agent/resolve?task=Use%20Learn%20Agent%20for%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text
Install handoff
/api/skills/7-e1even-learn-agent/install
Agent should check
- Task fit and alternatives from Resolve API.
- Audit score, trust score, and safety policy warnings.
- Install target compatibility for Codex, Claude Code, Cursor, or CLI.
Copy prompt
Task: Use Learn Agent in this workspace.
Resolve first: https://www.openagentskill.com/api/agent/resolve?task=Use%20Learn%20Agent%20for%20an%20agent%20workflow&agent=codex&max_risk=medium
Review install handoff: https://www.openagentskill.com/api/skills/7-e1even-learn-agent/install
Install command: npx skills add 7-e1even/learn-agent
Before running it, summarize audit warnings, required permissions, and the fallback skill if install is risky.Agent handoff
Give an agent the install path, not another directory page.
Use the public install endpoint to fetch the command, safety checklist, target prompts, and canonical links for this skill.
Install handoff
/api/skills/7-e1even-learn-agent/install
LLM text format
/api/skills/7-e1even-learn-agent/install?format=text
Find alternatives
/api/skills/search?q=Learn%20Agent&limit=3
Agent prompt
Use Learn Agent for this task. Review https://www.openagentskill.com/api/skills/7-e1even-learn-agent/install, then install with: npx skills add 7-e1even/learn-agentRegistry metadata
Agent-readable profile for automatic skill selection.
This page exposes the same decision, trust, audit, use-case, and install signals through the Registry API, so agents can rank this skill without scraping the UI.
Manifest
/api/registry/manifest/7-e1even-learn-agent
LLM text
/api/registry/manifest/7-e1even-learn-agent?format=text
Install alias
/api/registry/install/7-e1even-learn-agent
Recommend
/api/registry/recommend?task=Use%20Learn%20Agent%20in%20an%20agent%20workflow&limit=3
Agent fit
Coding agents
Use-case tags
Platforms
JavaScript, Claude Code, OpenAI Agents
Audit report
Needs review · 81/100
Review install readiness, maintenance, trust, quality, and metadata warnings before adding this skill to an agent workflow.
Agent decision cockpit
Companion skill for Coding agents
Shortlist this skill and compare it with close alternatives before production adoption.
Role in stack
Companion skill
Primary fit
Coding agents
Trust label
Strong shortlist
Install path
Command ready
Use when
- Coding agents workflows
- Claude Code teams
- builders willing to evaluate younger projects
Evidence
- recent repository activity
- install command or GitHub repo available
- 76/100 quality profile
- 1 OpenAgentSkill engagement events
Review first
- No major risk signals from current metadata
Implementation path
- 1Install it in a sandbox agent and run one Coding agents task end to end.
- 2Compare output quality, latency, and failure behavior against at least one alternative.
- 3Promote it into production only after reviewing repository permissions, license, and maintenance signals.
Trust profile
Sandbox only
Useful candidate with missing or mixed trust signals. Keep it in an isolated workspace until the outcome loop proves task fit.
GitHub adoption
CHECK84 GitHub stars
Stars/forks activity
CHECK84 stars, 7 forks; issue activity unavailable in current metadata
Recent maintenance
PASS1d since push
License clarity
PASSMIT
Good signals
- AI review approved
- Install path is available
- Repository evidence is available
- Recently maintained repository
- Install command has no obvious high-risk pattern
- Outcome loop is ready but needs first real agent run
Review before install
- Quality score needs review
- Permission surface needs review: secrets or environment access, network or browser access
- GitHub adoption: 84 GitHub stars
- Stars/forks activity: 84 stars, 7 forks; issue activity unavailable in current metadata
- Permission surface: secrets or environment access, network or browser access
- No real agent outcome reports yet
- Human review required before unattended installation
Recommended action
Run only in a sandbox and compare close alternatives before using it for real work.
Quality profile
Strong candidate for agent workflows
Solid option that is likely worth shortlisting for production workflows.
Workflow fit
Use this skill in these scenarios
Build and ship code
Coding agents
I need a coding agent that can understand a repository, edit code, and review pull requests.
Manage repositories
GitHub automation
I need my agent to triage GitHub issues, review pull requests, and summarize repository changes.
Publish consistently
Content automation
I need my agent to turn research and product updates into useful content drafts.
Stack fit
Add it to a complete workflow
Inspect, patch, and verify code
Coding review agent
A stack for software agents that inspect repositories, review pull requests, generate tests, and turn findings into shippable patches.
Turn skills into distribution
Content growth agent
A stack for turning newly indexed skills into SEO briefs, social drafts, comparison pages, and reusable publishing workflows.
Scrape, clean, and reuse web data
Web data pipeline
A practical stack for agents that crawl public pages, extract clean content, normalize data, and hand it to downstream research or RAG workflows.
Alternative shortlist
Compare before you install
Similar skills in this category, ranked with the same readiness and quality signals.
Graphify
A tool that converts codebases, SQL schemas, and other files into queryable knowledge graphs for AI coding assistants.
Gemini CLI
Bring a coding agent directly into the terminal
System Prompts And Models Of AI Tools
FULL Augment Code, Claude Code, Cluely, CodeBuddy, Comet, Cursor, Devin AI, Junie, Kiro, Leap.new, Lovable, Manus, NotionAI, Orchids.app, Perplexity, Poke, Qoder, Replit, Same.dev, Trae, Traycer AI, VSCode Agent, Warp.dev, Windsurf, Xcode, Z.ai Code, Dia & v0. (And other Open Sourced) System Prompts, Internal Tools & AI Models
Caveman
🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman
Overview
# learn-agent · AI Agent 开发进阶笔记
**简体中文** · [English](./README_EN.md)
这是我开发桌面 agent [Reina](https://github.com/Reina-Agent/Reina) 过程中整理的一系列进阶笔记,讲解 coding agent(Claude Code、Codex、opencode 这类工具)的内部实现机制。每篇笔记讲一个机制,配一份零依赖、单文件、可以直接运行的 Node 程序。
笔记把 Reina 的核心机制抽出来,简化成单文件代码,按由浅入深的顺序整理成文。因此这里的机制不是照 API 文档推想的,而是实际产品中验证过的做法。
Agent 的核心只有一个循环:模型说要用什么工具,代码执行并把结果喂回去,直到模型不再要工具:
```js while (true) { const msg = await chat(messages); // 调一次模型 messages.push(msg); if (!msg.tool_calls?.length) break; // 模型不再要工具,这一轮结束
for (const call of msg.tool_calls) { // 模型要用工具:执行,把结果喂回去 messages.push({ role: "tool", tool_call_id: call.id, content: runTool(call) }); } } ```
这十几行就是 s01 的全部核心(完整可运行版约 120 行)。笔记的其余部分讲的是:这个循环放进真实任务后会出什么问题,以及每个问题怎么解决。

## 适合
- 写过 agent demo,但在真实任务上遇到问题:循环空转、上下文超限、任务跑偏; - 日常使用 Claude Code,想知道压缩、缓存、子代理、权限审批这些机制内部怎么实现; - 需要在工作中落地 agent,想要一份经过实际验证的机制清单。
Agent 的基本循环很简单,但从"能跑"到"能用"之间有一整层工程问题:成本控制、上下文管理、缓存、持久化、并发、权限。这套笔记每篇解决其中一个。
## 运行方式
代码零依赖,Node 18 以上直接运行,支持任何 OpenAI 兼容的 API key(DeepSeek / Kimi / GLM / OpenRouter / 本地 Ollama):
```sh git clone https://github.com/7-e1even/learn-agent && cd learn-agent AGENT_API_KEY=sk-xxx node s01_agent_loop/agent.mjs ```
没有 key 的话,[s12](./s12_full_agent/) 提供不需要 key 的自测模式,可以端到端跑通核心机制。
建议从 s01 开始按顺序阅读,边读 README 边运行对应代码。
## 目录
主循环在第 1 篇写完,之后基本不再改动,所有机制都围绕它扩展。s01–s12 逐步搭出一个完整可用的 agent;s13 之后补充真实 coding agent 需要处理的边界问题:权限、Provider 兼容、工具披露、多模型协作、自我复盘。每篇结构一致:问题 → 解决方案 → 运行 → 实现 → 练习 → 真实产品对照。
| # | 主题 | 要解决的问题 | |---|---|---| | [s01](./s01_agent_loop/) | Agent 主循环 | 最小可用的 agent 长什么样 | | [s02](./s02_tool_system/) | 工具系统 | 工具越加越多,怎么不用每次都改循环 | | [s03](./s03_loop_budget/) | 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](./s04_output_budget/) | 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](./s05_streaming_interrupt/) | 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](./s06_compaction/) | 上下文压缩 | 上下文满了要压缩,怎么不忘掉最初的任务 | | [s07](./s07_prompt_cache/) | Prompt 缓存 | 同样的对话,为什么有人的账单
Platform Compatibility
Technical Details
- Version
- 1.0.0
- License
- MIT
- Last Updated
- 7/7/2026
- Published
- 7/6/2026
Frameworks & Tools
Decision snapshot
Companion skill
recent repository activity
Audit snapshot
Install review
Install and adoption review
- Security
- 81/100
- Maintenance
- 100/100
- Install
- 92/100
Agent-proven evidence
Agent Proven evidence
Outcome reports after resolve, review, install, and one narrow run.
- Success rate
- —
- Recent failure
- —
- Outcomes
- 0
- Output quality
- —
- Failed
- 0
- Not relevant
- 0
- Installs
- 0
- Risk blocked
- 0
- Setup needed
- 0
- Production
- 0
No agent outcome data yet. The first agent run can report success, setup needs, risk blocks, failure, or not-relevant through /api/agent/outcome.
Install
Add to agent workflow
Free and open source. Review the audit before production use.
Growth loop
Share kit
Scenario-led draft for Learn Agent, ready for a manual X post.
Most coding agents don't fail from lack of model power. They fail when repo context disappears. Learn Agent gives coding agents a repeatable way to plan, patch, review, or ship. 84 stars https://www.openagentskill.com/skills/7-e1even-learn-agent?ref=x #AIAgents
Optional reply with install command
Listing + install path for Learn Agent: https://www.openagentskill.com/skills/7-e1even-learn-agent?ref=x Install: npx skills add 7-e1even/learn-agent
Listing source
Community indexed
This listing was indexed from public sources and is not marked official until a maintainer claim is approved.
- Creator
- 7-e1even
- Source
- 7-e1even/learn-agent
- Indexed by
- OpenAgentSkill community index
Attribution links to the public repository or creator profile. Creators can claim the listing to update ownership signals.
Claim this skillOwner claim
Claim this skill listing
This community indexed listing is attributed to 7-e1even but is not marked official yet. Claim it to add a verified owner signal and make future launch, install, and audit updates easier to trust.
README badge
Add this badge to your GitHub README to show the listing, trust score, and install handoff.
[](https://www.openagentskill.com/skills/7-e1even-learn-agent)Author
7-e1even
@7-e1even
Platform Fit
Health Signals
- GitHub stars
- 84
- Quality score
- 47/100
- Last GitHub push
- Jul 6, 2026
- Framework hints
- 1
- OpenAgentSkill views
- 1
- Install copies
- 0
- Outbound clicks
- 0
Community Signal
Share whether this skill looks useful for your agent workflow. Aggregated feedback improves rankings over time.
Trust & Safety
Sandbox only
- GitHub adoption84 GitHub starsCHECK
- Stars/forks activity84 stars, 7 forks; issue activity unavailable in current metadataCHECK
- Recent maintenance1d since pushPASS
- License clarityMITPASS
- README/SKILL.md completenessMetadata includes enough usage and workflow contextPASS
- Dependency/runtime riskcredential or environment access, network or browser surfaceINFO
Related Skills
Graphify
A tool that converts codebases, SQL schemas, and other files into queryable knowledge graphs for AI coding assistants.
79.1K stars · 0 installsGemini CLI
Bring a coding agent directly into the terminal
105.8K stars · 0 installsSystem Prompts And Models Of AI Tools
FULL Augment Code, Claude Code, Cluely, CodeBuddy, Comet, Cursor, Devin AI, Junie, Kiro, Leap.new, Lovable, Manus, NotionAI, Orchids.app, Perplexity, Poke, Qoder, Replit, Same.dev, Trae, Traycer AI, VSCode Agent, Warp.dev, Windsurf, Xcode, Z.ai Code, Dia & v0. (And other Open Sourced) System Prompts, Internal Tools & AI Models
141.2K stars · 0 installsCaveman
🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman
86.0K stars · 0 installs