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 commands/cfrs2005/claude-init/learngit clone --depth 1 https://github.com/cfrs2005/claude-initWhat 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 | $0.00000 | $0.00522 |
| Opus 5 | $0.00000 | $0.00261 |
| Sonnet 5 | $0.00000 | $0.00104 |
| Haiku 4.5 | $0.00000 | $0.00052 |
Grade A, and why
learn 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 2d 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.
What it actually says
/learn - 提取可复用模式
分析当前会话并提取任何值得保存为技能的模式。
触发条件
当你在会话中解决了一个非主要问题时，随时运行 /learn。
提取内容
寻找：
-
错误解决模式
- 发生了什么错误？
- 根本原因是什么？
- 怎么修复的？
- 这对类似错误是否可复用？
-
调试技巧
- 那些不明显的调试步骤
- 起作用的工具组合
- 诊断模式
-
变通方案 (Workarounds)
- 库的怪癖
- API 限制
- 特定版本的修复
-
项目特定模式
- 发现的代码库约定
- 做出的架构决策
- 集成模式
输出格式
在 ~/.claude/skills/learned/[pattern-name].md 创建技能文件：
# [Descriptive Pattern Name] ([描述性模式名称])
**Extracted:** [Date] (**提取日期:** [日期])
**Context:** [Brief description of when this applies] (**上下文:** [适用情况简介])
## Problem (问题)
[What problem this solves - be specific] ([这也解决了什么问题 - 具体说明])
## Solution (解决方案)
[The pattern/technique/workaround] ([模式/技巧/变通方案])
## Example (示例)
[Code example if applicable] ([代码示例，如果适用])
## When to Use (何时使用)
[Trigger conditions - what should activate this skill] ([触发条件 - 什么应该激活此技能])
流程
- 审查会话以查找可提取的模式
- 识别最有价值/可复用的见解
- 起草技能文件
- 保存前请用户确认
- 保存到
~/.claude/skills/learned/
注意事项
- 不要提取微不足道的修复（拼写错误、简单的语法错误）
- 不要提取一次性问题（特定 API 中断等）
- 专注于能为未来会话节省时间的模式
- 保持技能专注 - 每个技能一个模式
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.
- 2d ago First seen · 71 lines · 0 tokens per session scan A 9ee0ea626d78
learn is a command published in the GitHub repository cfrs2005/claude-init (1,364 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 522 tokens. 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 commands, from other repositories
add-portal
You are helping the user build a job-portal search skill for a job board in their market. The repo ships worked examples of the pattern (four Danish portals plus the country-agnostic linkedin-search and freehire-search), and the README invites users elsewhere to build equivalents — this command turns that invitation…
send
Send a message to a running agent session. Use this to correct or direct a live agent mid-stream without killing and respawning it.
execute
Delegate execution to GJC (runs /skill:ultragoal to completion with verification).
vibe-agents
Step 4 of the vibe-coding workflow: generate AGENTS.md + tool configs so the AI builder stays on track.
agentlas-cloud
Staff a task only from the signed-in owner's Agent Cloud agents.
advisor
Advisory gate for triage or plan decisions. Spawns a second-opinion agent that challenges assumptions, surfaces risks, and proposes alternatives before the decision commits. Based on Anthropic advisor tool pattern.