claude-config-studio: Skill for Claude Code

.claude/skills/luoshu.config/SKILL.md

luoshu.config is a skill for Claude Code from znlnzi/claude-config-studio. It costs 27 tokens per session (1,181 once invoked), scanned A, original, MIT.

A configuration command for luoshu's AI-powered memory system, including its language-model service, API key, and search models.

In plain words
What is it for?
Viewing and validating configuration, changing models or keys, testing the connection, adjusting memory rules, checking system status, and rebuilding the search index.
Why use it?
It shows whether the memory service is connected and guides setup or changes when it is missing or misconfigured.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is znlnzi/claude-config-studio's own configuration. It tells Claude Code how to work on claude-config-studio itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude-config-studio configures →

Reuse

Borrowing it

Nothing to install: this file belongs to znlnzi/claude-config-studio. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/znlnzi/claude-config-studio/main/.claude/skills/luoshu.config/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/znlnzi/claude-config-studio

Made for: Claude Code.

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 luoshu.config

README.md
[![agentmods](https://agentmods.dev/badge/skills/znlnzi/claude-config-studio/luoshu.config/github.svg)](https://agentmods.dev/skills/znlnzi/claude-config-studio/luoshu.config)
Your own site
<a href="https://agentmods.dev/skills/znlnzi/claude-config-studio/luoshu.config"><img src="https://agentmods.dev/badge/skills/znlnzi/claude-config-studio/luoshu.config/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.

agentmods 80×15 button for luoshu.config

Your own site · 80×15
<a href="https://agentmods.dev/skills/znlnzi/claude-config-studio/luoshu.config"><img src="https://agentmods.dev/badge/skills/znlnzi/claude-config-studio/luoshu.config.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,181 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00027 $0.01181
Opus 5 $0.00014 $0.00590
Sonnet 5 $0.00005 $0.00236
Haiku 4.5 $0.00003 $0.00118

Measured 10d ago against content hash 86940a8fee6c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

luoshu.config 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 10d 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.

.claude/skills/luoshu.config/SKILL.md · 146 lines

How it starts

The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/luoshu.config -- 配置管理

展示当前 luoshu 配置状态,引导用户配置或修改 LLM 服务。


流程

1. 获取当前配置

调用 luoshu_config_get 获取完整配置(API Key 已自动脱敏)。

2. 验证连接状态

如果 LLM 已配置(api_key 非空),调用 luoshu_config_validate 检查连接。

3. 按状态展示

根据配置和连接状态,展示对应界面。


展示格式

未配置时

当前 luoshu 配置:

  服务商:  未配置
  API Key: 未配置
  状态:    未连接

以下功能因未配置而不可用:
  - 跨会话智能记忆
  - 语义搜索
  - 自动提取会话要点

配置 LLM 服务?

  [1] 配置火山引擎(推荐,国内用户延迟低)
  [2] 稍后再说

选择 [1] 后,进入配置流程:

  1. 提问"你有火山引擎的 API Key 吗?"
  2. 有 Key → 调用 luoshu_config_set(key=llm.api_key, value=用户输入) → luoshu_config_validate 验证
  3. 没有 Key → 分步引导注册火山引擎 + 获取 Key(同 /luoshu.setup Step 4.4)
  4. 跳过 → 结束

已配置且连接正常时

当前 luoshu 配置:

  服务商:  火山引擎
  API Key: sk-****xxxx
  Endpoint: ark.cn-beijing.volces.com
  LLM Model: doubao-1.5-pro-256k
  Embedding Model: doubao-embedding-large
  状态:    已连接

  记忆策略:
  - 自动提取: 已启用
  - 保留天数: 90 天

输入编号修改:
  [1] 更新 API Key
  [2] 修改 LLM Model
  [3] 修改 Embedding Model
  [4] 修改记忆策略
  [5] 测试连接
  [6] 查看系统状态
  [7] 重建向量索引

各选项操作:

  • [1] 更新 API Key → 要求输入新 Key → luoshu_config_set(key=llm.api_key) → luoshu_config_validate
  • [2] 修改 LLM Model → 展示可选模型 → luoshu_config_set(key=llm.model)
  • [3] 修改 Embedding Model → 展示可选模型 → luoshu_config_set(key=embedding.model)
  • [4] 修改记忆策略 → 展示当前值 → luoshu_config_set(key=memory.auto_extractmemory.retention_days)
  • [5] 测试连接luoshu_config_validate
  • [6] 查看系统状态luoshu_status(展示记忆条目数、向量索引数、缓存大小)
  • [7] 重建向量索引luoshu_reindex

已配置但连接失败时

当前 luoshu 配置:

  服务商:  火山引擎
  API Key: sk-****xxxx
  状态:    连接失败(认证被拒绝)

API Key 可能已过期或被撤销。

  [1] 更新 API Key
  [2] 帮我获取新的 Key
  [3] 测试连接(重试)

Key 验证失败的诊断

当用户输入的 Key 验证失败时,根据 luoshu_config_set 返回的预检结果展示诊断:

预检结果 展示信息
OpenAI Key (sk-proj-) "这看起来是 OpenAI 的 Key,请确认使用火山引擎的 Key"
Anthropic Key (sk-ant-) "这看起来是 Anthropic 的 Key"
AWS Key (AKIA) "这看起来是 AWS 的 Key"
GitHub Token (ghp_) "这看起来是 GitHub Token"
Key 过短 (<20字符) "Key 只有 N 个字符,可能复制不完整"

Read the full file on GitHub · 146 lines

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. 10d ago First seen · 146 lines · 27 tokens per session scan A 86940a8fee6c

Subscribe to this mod's changes

luoshu.config is a skill published in the GitHub repository znlnzi/claude-config-studio (0 stars, last pushed 6mo ago), licensed MIT. It adds 27 tokens to every session and 1,181 once invoked, about $0.0001 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 2026-08-31.