ruoyi-plus-soybean: Skill for Claude Code

.claude/skills/athena-preferences/SKILL.md

athena-preferences is a skill for Claude Code from m-xlsea/ruoyi-plus-soybean. It costs 37 tokens per session (1,355 once invoked), scanned B, original, MIT.

A preference-management skill for Claude Code that stores allowed or blocked commands in Claude's native settings and stores tool preferences in its global instruction file.

In plain words
What is it for?
Use it to explicitly remember an allowed command pattern, deny a command, or record preferences such as using pnpm or Vitest.
Why use it?
It keeps global permissions and preferences in the locations Claude Code already reads, while avoiding project-specific paths and automatic changes based on command frequency.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: reads .claude/ paths; mentions CLAUDE.md.

This is m-xlsea/ruoyi-plus-soybean's own configuration. It tells Claude Code how to work on ruoyi-plus-soybean 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 ruoyi-plus-soybean configures →

Reuse

Borrowing it

Nothing to install: this file belongs to m-xlsea/ruoyi-plus-soybean. 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/m-xlsea/ruoyi-plus-soybean/master/.claude/skills/athena-preferences/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/m-xlsea/ruoyi-plus-soybean

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 athena-preferences

README.md
[![agentmods](https://agentmods.dev/badge/skills/m-xlsea/ruoyi-plus-soybean/athena-preferences/github.svg)](https://agentmods.dev/skills/m-xlsea/ruoyi-plus-soybean/athena-preferences)
Your own site
<a href="https://agentmods.dev/skills/m-xlsea/ruoyi-plus-soybean/athena-preferences"><img src="https://agentmods.dev/badge/skills/m-xlsea/ruoyi-plus-soybean/athena-preferences/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 athena-preferences

Your own site · 80×15
<a href="https://agentmods.dev/skills/m-xlsea/ruoyi-plus-soybean/athena-preferences"><img src="https://agentmods.dev/badge/skills/m-xlsea/ruoyi-plus-soybean/athena-preferences.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,355 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00037 $0.01355
Opus 5 $0.00018 $0.00678
Sonnet 5 $0.00007 $0.00271
Haiku 4.5 $0.00004 $0.00136

Measured 11d ago against content hash 22408d5a780c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade B, and why

athena-preferences scanned grade B 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 11d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

Athena 全局偏好便利层。直接操作 CC 原生 ~/.claude/settings.json 的 permissions.allow/deny 和全局 CLAUDE.md。
.claude/skills/athena-preferences/SKILL.md · 139 lines

How it starts

The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/athena-preferences (v9.6)

设计原则

Athena 不造私有偏好文件。所有写入都是 CC 原生位置:

偏好类型 落点
全局 allow ~/.claude/settings.json permissions.allow[]
全局 deny ~/.claude/settings.json permissions.deny[]
工具偏好 (pnpm/vitest) ~/.claude/CLAUDE.md "## Tool Preferences" 段

参考: https://code.claude.com/docs/en/settings + https://code.claude.com/docs/en/permissions

永远不写:

  • ~/.claude/memory/athena-*.list 类私有文件
  • ❌ 项目特定的命令到全局 (路径泛化检查)

永远不自动写:

  • ❌ 不监控命令频次自动建议 (隐私决定)
  • ✅ 仅在用户显式调用本 skill 时写

子命令

/athena:remember-allow <pattern>

参数: 标准 CC permission pattern, 如 Bash(pnpm test:*).

const fs = require('fs');
const os = require('os');
const path = require('path');

const settingsPath = path.join(os.homedir(), '.claude/settings.json');
let s = {};
try { s = JSON.parse(fs.readFileSync(settingsPath,'utf8')); } catch(e) {}
s.permissions = s.permissions || {};
s.permissions.allow = s.permissions.allow || [];

const pattern = process.argv[2];

// 路径泛化检查: 拒绝含项目特定路径的 pattern
if (/\/Users\/|\/home\/[^*/]|C:\\Users\\/.test(pattern) || /[\w-]+\.(com|cn|net)\//.test(pattern)) {
  console.error('❌ 拒绝: pattern 含项目/用户特定路径, 不应写入全局');
  console.error('   如果只想本项目用, 写到 .claude/settings.local.json');
  process.exit(1);
}

if (s.permissions.allow.includes(pattern)) {
  console.log('✓ 已存在, 无需添加');
  process.exit(0);
}
s.permissions.allow.push(pattern);
fs.writeFileSync(settingsPath, JSON.stringify(s,null,2));
console.log(`✓ 已加入全局 allow: ${pattern}`);
console.log(`   位置: ${settingsPath}`);

/athena:remember-deny <pattern>

remember-allow, 写入 permissions.deny[]. 但不做路径泛化拒绝——deny 越严格越好。

/athena:remember-tool <key>=<value>

写入 ~/.claude/CLAUDE.md 的 "## Tool Preferences" 段 (无则创建):

## Tool Preferences

- 包管理器: pnpm
- 测试运行器: vitest
- Linter: biome
- 默认提交者: --signoff

/athena:show-preferences

echo "=== Global allow (~/.claude/settings.json) ==="
node -e 'console.log((JSON.parse(require("fs").readFileSync(require("os").homedir()+"/.claude/settings.json")).permissions?.allow || []).join("\n"))'

echo ""
echo "=== Global deny ==="
node -e 'console.log((JSON.parse(require("fs").readFileSync(require("os").homedir()+"/.claude/settings.json")).permissions?.deny || []).join("\n"))'

echo ""
echo "=== Tool preferences (~/.claude/CLAUDE.md) ==="
sed -n '/^## Tool Preferences/,/^## /p' ~/.claude/CLAUDE.md 2>/dev/null | head -20

Read the full file on GitHub · 139 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. 11d ago First seen · 139 lines · 37 tokens per session scan B 22408d5a780c

Subscribe to this mod's changes

athena-preferences is a skill published in the GitHub repository m-xlsea/ruoyi-plus-soybean (325 stars, last pushed 2mo ago), licensed MIT. It adds 37 tokens to every session and 1,355 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-01.

Related

Other skills, from other repositories