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 skills/fredchu/claude-dotfiles/rem-clinpx skills add fredchu/claude-dotfiles --skill rem-cligit clone --depth 1 https://github.com/fredchu/claude-dotfilesWhat 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 | $0.00066 | $0.02050 |
| Opus 5 | $0.00033 | $0.01025 |
| Sonnet 5 | $0.00013 | $0.00410 |
| Haiku 4.5 | $0.00007 | $0.00205 |
Grade A, and why
rem 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 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.
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.
How it starts
The opening of the file, as written. The whole thing — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
rem — macOS Reminders CLI
環境
- 路徑：
/Users/fredchu/bin/rem（不在 PATH，所有指令必須用完整路徑） - 解析輸出時用
-o json，顯示給用戶時用預設 table - 環境變數：
NO_COLOR=1（避免 ANSI 碼干擾 JSON 解析）
非互動規則
| 情境 | 規則 |
|---|---|
| delete | 必須加 --force（非互動環境無法確認） |
| list-mgmt delete | 必須加 --force |
| add / update | 禁用 -i（interactive mode） |
| 搬移 list | update 不支援改 list → 必須 delete --force + add 重建 |
| 確認動作 | 刪除前先 show 該項目，告知用戶內容，再執行 |
List 智能路由
用戶沒指定 list 時，根據內容關鍵詞自動判斷目標 list：
| 關鍵詞特徵 | 目標 List |
|---|---|
| 投資/股票/選擇權/ETF/財報/持倉/殖利率/配息 | Investing |
| 程式/code/bug/deploy/PR/skill/app/API | dev |
| 煮/食譜/買菜/超市/料理 | Cooking |
| 掃地/洗衣/倒垃圾/拖地/吸塵/換床單 | 例行家事 |
| 拍照/底片/暗房/沖片/相機 | 攝影暗房 |
| 遊戲/PS5/Switch/Steam/Xbox | Video Games |
| 家人名字/家庭事務/爸媽/小孩 | Family |
| 書/讀/閱讀 | 書 |
| 以上都不符合 | 雜 |
現有 lists（供比對）：Family, Investing, 雜, 例行家事, dev, 攝影暗房, Work, 書, Gadgets, Cooking, Video Games
dev List 前綴 Convention
dev list 使用前綴分組，模擬 Reminders app 的段落結構（EventKit API 不支援 sections/subtasks）。
新增 dev items 時必須加前綴：
| 前綴 | 代表 | 範例 |
|---|---|---|
| MK | MumbleKey 功能 | MK 術語自動學習 |
| MKA | MumbleKey Agent | MKA Release manager |
| MKP | MumbleKey 平台 | MKP Android client |
| VF | VerbatimFlow | VF 實測 2B-6bit |
| CC | Claude Code 工具 | CC loop 實驗 |
| DC | Discord Bot | DC 修長訊息分段發送 |
| EA | Earnings Autopilot | EA 移植逐字稿流程 |
格式：{前綴} {項目名稱}（前綴和名稱之間用空格分隔）
搜尋特定群組：rem search "MK " --list "dev" --incomplete
分組顯示：讀取 dev list 後，用前綴分組呈現給用戶，而不是扁平列表。
排序 dev list：用戶說「排序」「整理 dev list」「排一下」時，用 JXA 腳本按前綴分組排序。
排序方法（JXA move({to: list}) 會移到 list 末尾）：
rem list --list "dev" --incomplete -o json取得所有項目- 按前綴排序：MK → MKA → MKP → VF → EA → CC → DC → 無前綴（同前綴內按名稱字母序）
- 按排好的順序依次
move({to: devList})→ 先 move 的排前面
// /tmp/sort_dev.js — 排序 dev list 的 JXA 腳本模板
const app = Application("Reminders");
const devList = app.lists.whose({name: "dev"})[0];
const sortedNames = ["MK item1", "MK item2", "MKA item1", ...]; // Python 產生
for (let i = 0; i < sortedNames.length; i++) {
try {
const rems = devList.reminders.whose({name: sortedNames[i], completed: false});
if (rems.length > 0) rems[0].move({to: devList});
} catch(e) {}
}
What ships with it
2 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.
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.
- yesterday First seen · 178 lines · 66 tokens per session scan A 7b483abd73d8
rem is a skill published in the GitHub repository fredchu/claude-dotfiles (2 stars, last pushed 19d ago), licensed MIT. It adds 66 tokens to every session and 2,050 once invoked, about $0.0003 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.
Other skills, from other repositories
wayfinder
规划一大块工作——超过一次 agent 会话能容纳的体量——在你的 Issue 跟踪器上以共享的决策 ticket 地图形式呈现，逐个解决，直到通往目的地的道路变得清晰。.
setup-ts-deep-modules
将 dependency-cruiser 接入 TypeScript 仓库，使每个 package 都是一个深度模块：实现隐藏在子文件夹中，只能通过入口点文件访问。由用户调用。.
codebase-design
设计深度模块的共享词汇。当用户想要设计或改进模块的接口、寻找深化机会、决定 seam 的位置、让代码更可测试或更易被 AI 导航，或者其他 skill 需要深度模块词汇时使用。.
setup-matt-pocock-skills
为本仓库配置工程技能——设置其 issue tracker、分诊标签词汇表和领域文档布局。首次使用其他工程技能前运行一次。.
triage
将 issue 和外部 PR 推过一组分诊角色的状态机——分类、验证、必要时盘问，并写出 agent 就绪的任务简报。.
writing-fragments
Writing, explore ： 挖掘原始碎片，不施加结构。.