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 instructions/fredchu/claude-dotfiles/claude-mdgit clone --depth 1 https://github.com/fredchu/claude-dotfilesWrote 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/instructions/fredchu/claude-dotfiles/claude-md)<a href="https://agentmods.dev/instructions/fredchu/claude-dotfiles/claude-md"><img src="https://agentmods.dev/badge/instructions/fredchu/claude-dotfiles/claude-md.svg" alt="Measured on agentmods" 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 | $0.02495 | $0.02495 |
| Opus 5 | $0.01247 | $0.01247 |
| Sonnet 5 | $0.00499 | $0.00499 |
| Haiku 4.5 | $0.00249 | $0.00249 |
Grade A, and why
claude-dotfiles CLAUDE.md 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
用戶級規則（所有專案共用）
本檔是索引：短硬規則直接內嵌，長流程一律指向細節檔。 路由行的意思是「需要做那類事時才去讀該檔」，不是現在就讀。 規則優先序（高→低）：用戶當下指示 > 專案 CLAUDE.md > 本檔 > memory 指針檔 > wiki/lessons。 兩處規則衝突：照高優先序執行，並在回報末尾附一行「規則衝突：檔A vs 檔B，我照檔A」。 路徑約定：任何檔案裡寫的
memory/...指針檔，一律指/Users/fredchu/.agents/memory/...（2026-07-20 Phase 1 起 canonical memory 在此；由 settings.jsonautoMemoryDirectory載入， 舊~/.claude/projects/-Users-fredchu-Documents-For-Claude/memory/僅剩 stub）。 （2026-07-04 重寫為索引式，備份~/.claude/CLAUDE.md.bak-2026-07-04；2026-07-20 併入原 For_Claude 專案級通用段，備份~/.claude/phase1-backup-20260720/）
核心身份
Fred，台灣桃園，自由工作者。深耕 AI 開發與金融交易領域，擅長將數據分析與自動化工具結合。 例行為財經教育內容創作者 Austin 做字幕與美股財報翻譯。育有一名 4 歲幼兒，追求效率工具與 生活品質的平衡。
- 本體畫像模組按需讀（
/Users/fredchu/Documents/For_Claude/本體畫像/）：01-技術專長（AI/軟工/IT 任務）、02-金融交易（財經/選擇權）、03-工作流與工具鏈（工具/環境/字幕）、04-近期專案（任務規劃/進度）、05-偏好與地雷（決策建議/推薦方案）
治理制度（先讀診斷，其餘按需）
位置：
/Users/fredchu/Documents/For_Claude/company/_shared/governance/
- 三大反模式與修法（token 漏／多源失焦／假完成）→
01-diagnosis.md - 派 Claude subagent：模型與 effort 選型、回報合約、升降級、驗證不自驗 →
02-model-dispatch.md - 判斷 rubric：何時升級／何時算完成／何時問用戶／何時換路／品質底線 →
03-judgment-rubrics.md - 交辦 prompt 範本（搜尋／實作／重構／研究／審查）→
04-prompt-templates.md - 維護協議：哪些檔可自改、教訓寫回哪、多長要精簡 →
05-maintenance-protocol.md
Session Handoff（開場收尾，不可跳過）
- Agent ID: Pro CC；Handoff root:
~/Library/Mobile Documents/iCloud~md~obsidian/Documents/Agent 工作區/handoff；Other Agents: Mini CC, Pro Pi, Air CC, Air Pi - Private budget: 1500 chars；Shared budget: 1000 chars
- 開場第一句回覆必附 hook 注入的 handoff 摘要（3-5 bullets）；收尾觸發「收工／bye／結束」→
/session-handoffskill，不可以「還沒做什麼」為由跳過 - 開場/收尾完整規則（含 wiki uncommitted 檢查、實驗清理盤點兩條 hard rule）→
/Users/fredchu/Documents/For_Claude/company/_shared/references/session-rituals.md
特助模式
- 用戶用極短語句下指令（briefing／記一下／提醒我／進度／收工／信箱／行事曆／日規劃／週規劃／今天做什麼／定時任務／加訂閱／播客摘要／深讀…）→ 查對照表直接執行，不要反問：
/Users/fredchu/Documents/For_Claude/company/_shared/references/assistant-shortcuts.md（含 rem/ical/podscribe 工具路徑、stale-scan briefing 整合、Apple Notes 細節） - Apple Notes 基本規則：內容只放「Claude 工作區」、寫入用 HTML 不用 markdown
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.
- 4d ago First seen · 100 lines · 2,495 tokens per session scan A 8226dbb023b6
claude-dotfiles CLAUDE.md is an instructions file published in the GitHub repository fredchu/claude-dotfiles (2 stars, last pushed 21d ago), licensed MIT. It adds 2,495 tokens to every session, about $0.0125 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 instructions, from other repositories
mattpocock-skills-zh CLAUDE.md
Instructions for devcxl/mattpocock-skills-zh, a project described as: Matt Pocock 技能集的中文翻译版 — 地道中文，原汁原味的技术术语。基于 mattpocock/skills 复刻。每日中午12点钟同步.
memex AGENTS.md
AGENTS.md instructions for memex-lab/memex, covering memex — project context for coding agent, build & run, testing requirements, architecture and layers.
memex CLAUDE.md
Claude Code instructions for memex-lab/memex, covering memex — project context for claude code, authoritative agent rules, product, core capabilities and target platforms.
memex copilot-instructions.md
Copilot instructions for memex-lab/memex: AGENTS.md is the canonical instruction file for this repository. Read it before suggesting or editing code.
memex GEMINI.md
Gemini CLI instructions for memex-lab/memex: AGENTS.md is the canonical instruction file for coding agents in this repository. Read it before editing code.
chatspeed AGENTS.md
AGENTS.md instructions for aidyou/chatspeed, covering chatspeed root rules, personal preferences, project shape, general workflow and work start checklist.