learning

learning is a skill for Claude Code, Codex from xiaobei930/cc-best. It costs 22 tokens per session (2,456 once invoked), scanned A, original, MIT.

A session-learning workflow that extracts reusable debugging techniques, solutions, workarounds, and project knowledge from development conversations.

In plain words
What is it for?
Use it at the end of a session, after solving a difficult error, or when discovering a repeatable solution or project-specific fact.
Why use it?
It helps useful discoveries survive beyond the current session instead of being forgotten after a problem is solved.

Skill for Claude CodeCodex

Part of the cc-best plugin — 19 skills, 44 commands, 8 agents, 20 hooks shipped together

Install

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.

agentmods
npx agentmods add skills/xiaobei930/cc-best/learning
Any agent
npx skills add xiaobei930/cc-best --skill learning
Clone the repo
git clone --depth 1 https://github.com/xiaobei930/cc-best

Made for: Claude Code, Codex.

Or install cc-best, the plugin that ships this one along with the rest of its 19 skills, 44 commands, 8 agents, 20 hooks.

Wrote 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.

agentmods badge for learning

README.md
[![agentmods](https://agentmods.dev/badge/skills/xiaobei930/cc-best/learning.svg)](https://agentmods.dev/skills/xiaobei930/cc-best/learning)
Your own site
<a href="https://agentmods.dev/skills/xiaobei930/cc-best/learning"><img src="https://agentmods.dev/badge/skills/xiaobei930/cc-best/learning.svg" alt="Measured on agentmods" height="20"></a>
Per session 22 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,456 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00022 $0.02456
Opus 5 $0.00011 $0.01228
Sonnet 5 $0.00004 $0.00491
Haiku 4.5 $0.00002 $0.00246

Measured yesterday against content hash ad715adc4444, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

learning scanned grade A with 1 finding 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 yesterday.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

2. 使用 Postman/curl 直接测试
skills/learning/SKILL.md · 360 lines

How it starts

The opening of the file, as written. The whole thing — 360 lines — stays where its author put it; the contents beside it link to each section on GitHub.

持续学习技能

本技能用于从开发会话中提取可复用的模式和知识,实现持续学习和改进。

快速参考

  • 核心职责: 从开发会话中提取可复用模式(错误解决、调试技巧、变通方案、项目知识)
  • 学习模式: 错误解决模式、调试技巧、变通方案、项目特定知识
  • 本能系统: 观察 → 记录 → 本能 → 演化(置信度 0.3~0.9)
  • 自动化: 会话评估 Hook(evaluate-session.js)+ 观察 Hook(observe-patterns.js
  • 子文件引用:

目录

子文件

触发条件

  • 会话结束时评估
  • 发现新的调试技巧
  • 解决了复杂问题
  • 创建了可复用的解决方案
  • 学到了项目特定知识

学习模式类型

1. 错误解决模式

当解决了一个错误,记录:

  • 错误信息
  • 根本原因
  • 解决方案
  • 预防措施
## 错误: Cannot read property 'xxx' of undefined

### 场景

访问嵌套对象属性时

### 根本原因

异步数据未加载完成就访问

### 解决方案

```typescript
// 使用可选链
const value = obj?.nested?.property;

// 或提供默认值
const value = obj?.nested?.property ?? defaultValue;
```

预防

  • 始终使用可选链访问可能为空的属性
  • 在组件中添加加载状态检查

### 2. 调试技巧

```markdown
## 技巧: 调试 Next.js API 路由

### 场景
API 路由返回意外结果

### 技巧
1. 在 route.ts 开头添加日志
```typescript
export async function GET(request: NextRequest) {
  console.log('[API] GET /api/xxx', {
    url: request.url,
    headers: Object.fromEntries(request.headers)
  })
  // ...
}
  1. 使用 Postman/curl 直接测试
  2. 检查中间件是否拦截

### 3. 变通方案

```markdown
## 变通: Prisma 不支持的复杂查询

### 场景
需要执行 Prisma 不原生支持的 SQL

### 变通方案
```typescript
// 使用 $queryRaw 执行原生 SQL
const result = await prisma.$queryRaw`
  SELECT * FROM users
  WHERE LOWER(name) LIKE ${`%${search.toLowerCase()}%`}
`

// 或使用 $executeRaw 执行命令
await prisma.$executeRaw`
  UPDATE users SET updated_at = NOW()
  WHERE id = ${userId}
`

注意

  • 需要手动处理 SQL 注入防护
  • 返回类型需要手动指定

### 4. 项目特定知识

```markdown
## 项目: 用户认证流程

### 流程
1. 用户提交凭证 → POST /api/auth/login
2. 验证凭证 → 检查数据库
3. 生成 JWT → 设置 httpOnly cookie
4. 返回用户信息

### 关键文件
- `src/app/api/auth/login/route.ts` - 登录接口
- `src/lib/auth.ts` - 认证工具函数
- `src/middleware.ts` - 路由保护

Read the full file on GitHub · 360 lines

Files

What ships with it

3 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.

Changes

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.

  1. yesterday First seen · 360 lines · 22 tokens per session scan A ad715adc4444

Subscribe to this mod's changes

learning is a skill published in the GitHub repository xiaobei930/cc-best (50 stars, last pushed 2mo ago), licensed MIT. It adds 22 tokens to every session and 2,456 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories

self-assessment

Interactive skill assessment with personalized learning path generation.

FlorianBruniaux/claude-code-ultimate-guide · 12 tokens

talk-stage5-script

Produces a complete 5-act pitch with speaker notes, a slide-by-slide specification, and a ready-to-paste Kimi prompt for AI slide generation. Requires validated angle and title from Stage 4. Use when you have a confirmed talk angle and need the full script, slide spec, and AI-generated presentation prompt.

FlorianBruniaux/claude-code-ultimate-guide · 69 tokens

talk-stage6-revision

Produces revision sheets with quick navigation by act, a master concept-to-URL table, Q&A cheat-sheet with 6-10 anticipated questions, glossary, and external resources list. Use when preparing for a talk with Q&A, creating shareable reference material for attendees, or building a safety-net glossary for live delivery.

FlorianBruniaux/claude-code-ultimate-guide · 70 tokens

talk-stage1-extract

Extracts and structures source material (articles, transcripts, notes) into a talk summary with narrative arc, themes, metrics, and gaps. Auto-detects REX vs Concept type. Use when starting a new talk from any source material or auditing existing material before committing to a talk.

FlorianBruniaux/claude-code-ultimate-guide · 64 tokens

talk-stage3-concepts

Builds a numbered, categorized concept catalogue from the talk summary and timeline, scoring each concept HIGH / MEDIUM / LOW for talk potential with optional repo enrichment. Use when you need a structured inventory of concepts before choosing a talk angle, or when assessing which ideas have the strongest…

FlorianBruniaux/claude-code-ultimate-guide · 64 tokens

explain

Explain code, concepts, or system behavior with adjustable depth levels.

FlorianBruniaux/claude-code-ultimate-guide · 15 tokens