Borrowing it
Nothing to install: this file belongs to MusesCraft/awesome-claude-designCN. 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/MusesCraft/awesome-claude-designCN/main/CLAUDE.mdgit clone --depth 1 https://github.com/MusesCraft/awesome-claude-designCNWrote 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/musescraft/awesome-claude-designcn/claude-md)<a href="https://agentmods.dev/instructions/musescraft/awesome-claude-designcn/claude-md"><img src="https://agentmods.dev/badge/instructions/musescraft/awesome-claude-designcn/claude-md/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/instructions/musescraft/awesome-claude-designcn/claude-md"><img src="https://agentmods.dev/badge/instructions/musescraft/awesome-claude-designcn/claude-md.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 | $0.03979 | $0.03979 |
| Opus 5 | $0.01989 | $0.01989 |
| Sonnet 5 | $0.00796 | $0.00796 |
| Haiku 4.5 | $0.00398 | $0.00398 |
Grade A, and why
awesome-claude-designCN CLAUDE.md scanned grade A 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 9d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- 手動:curl 端點 11 次,看到 rate limit 錯誤 How it starts
The opening of the file, as written. The whole thing — 399 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — 受 Karpathy 啟發的 Claude Code 指南
整合自 multica-ai/andrej-karpathy-skills 源自 Andrej Karpathy 對 LLM 編碼陷阱的觀察
行為準則,用以減少 LLM 編碼中的常見錯誤。可與專案特定指令合併使用。
權衡說明: 這些準則傾向於謹慎而非速度。對於瑣碎任務(簡單拼寫修正、顯而易見的一行修改),請自行判斷 —— 並非每個改動都需要完整的嚴謹流程。
問題背景
來自 Andrej Karpathy 的觀察:
"模型會代你做錯誤假設,然後不假思索地執行。它們不管理自身的困惑,不尋求澄清,不呈現矛盾,不展示權衡,在應該提出異議時也不反駁。"
"它們真的很喜歡把代碼和 API 搞複雜,堆砌抽象概念,不清理死代碼……明明 100 行能搞定的事情,非要實現成 1000 行的臃腫架構。"
"它們有時仍會改動或刪除自己理解不足的代碼和註釋,即使這些內容與任務本身無關。"
四大原則總覽
| 原則 | 解決什麼問題 |
|---|---|
| 1. 編碼前思考 | 錯誤假設、隱藏困惑、缺少權衡 |
| 2. 簡潔優先 | 過度複雜、臃腫抽象 |
| 3. 精準修改 | 無關編輯、觸碰不應碰的代碼 |
| 4. 目標驅動執行 | 通過測試優先、可驗證的成功標準 |
1. 編碼前思考
不要假設。不要隱藏困惑。呈現權衡。
LLM 經常默默選擇一種解釋然後執行。此原則強制明確推理:
- 明確說明假設 — 如果不確定,詢問而不是猜測
- 呈現多種解釋 — 當存在歧義時,不要默默選擇
- 適時提出異議 — 如果存在更簡單的方法,說出來
- 困惑時停下來 — 指出不清楚的地方並要求澄清
範例:隱藏假設
用戶請求: "添加導出用戶數據的功能"
❌ 錯誤做法(默默做出多重假設)
def export_users(format='json'):
users = User.query.all() # 假設要導出所有用戶
if format == 'json':
with open('users.json', 'w') as f: # 假設檔案位置
json.dump([u.to_dict() for u in users], f)
# ... 假設字段、假設格式
✅ 正確做法(呈現假設)
在實作之前,我需要釐清幾點:
1. **範圍**:導出所有用戶還是篩選後的子集?(隱私考量)
2. **格式**:你說的"導出"是指:
- 瀏覽器下載檔案?
- 背景任務搭配郵件通知?
- 回傳數據的 API 端點?
3. **字段**:包含哪些用戶字段?(部分可能敏感)
4. **量級**:通常有多少用戶?(影響實作方式)
最簡方案:新增回傳分頁 JSON 的 API 端點。
如需檔案導出則需更多資訊。
你偏好哪種?
範例:多重解釋
用戶請求: "讓搜尋更快"
✅ 正確做法
"讓搜尋更快"可能指:
1. **回應時間更快**(< 100ms 而非 500ms)
- 加資料庫索引、快取常見查詢
- 預估工時:2 小時
2. **承載更多並發搜尋**(吞吐量)
- 加 async/await、連線池
- 預估工時:4 小時
3. **體感更快**(UX)
- 即時顯示部分結果、漸進式載入
- 預估工時:3 小時
目前搜尋耗時約 500ms。哪個面向對你最重要?
2. 簡潔優先
用最少的代碼解決問題。不要過度推測。
對抗過度工程的傾向:
- 不要添加要求之外的功能
- 不要為一次性代碼創建抽象
- 不要添加未要求的"靈活性"或"可配置性"
- 不要為不可能發生的場景做錯誤處理
- 如果 200 行代碼可以寫成 50 行,重寫它
檢驗標準: 資深工程師會覺得這過於複雜嗎?如果是,簡化。
範例:過度抽象
用戶請求: "加一個計算折扣的函數"
❌ 錯誤做法(過度工程)
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.
- 9d ago First seen · 399 lines · 3,979 tokens per session scan A b3c7ab2a8eb4
awesome-claude-designCN CLAUDE.md is an instructions file published in the GitHub repository MusesCraft/awesome-claude-designCN (1 stars, last pushed 3mo ago), licensed MIT. It adds 3,979 tokens to every session, about $0.0199 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.