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.
curl -O https://raw.githubusercontent.com/m-xlsea/ruoyi-plus-soybean/master/.claude/skills/athena-preferences/SKILL.mdgit clone --depth 1 https://github.com/m-xlsea/ruoyi-plus-soybeanWrote 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.
[](https://agentmods.dev/skills/m-xlsea/ruoyi-plus-soybean/athena-preferences)<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.
<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>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.
| Model | Per session | Once 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 |
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。 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>
同 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
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.
- 11d ago First seen · 139 lines · 37 tokens per session scan B 22408d5a780c
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.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.