Borrowing it
Nothing to install: this file belongs to yuz9610/POE2Overlay. 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/yuz9610/POE2Overlay/main/CLAUDE.mdgit clone --depth 1 https://github.com/yuz9610/POE2OverlayWrote 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/yuz9610/poe2overlay/claude-md)<a href="https://agentmods.dev/instructions/yuz9610/poe2overlay/claude-md"><img src="https://agentmods.dev/badge/instructions/yuz9610/poe2overlay/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/yuz9610/poe2overlay/claude-md"><img src="https://agentmods.dev/badge/instructions/yuz9610/poe2overlay/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 | $0.01002 | $0.01002 |
| Opus 5.5 | $0.00401 | $0.00401 |
| Sonnet 5.5 | $0.00200 | $0.00200 |
| Haiku 4.5 | $0.00100 | $0.00100 |
Grade A, and why
POE2Overlay 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 2mo 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Agent 指南（Claude / Claude Code）
人類開發者請改讀 docs/README.md → docs/ARCHITECTURE.md。本頁供 Claude / Claude Code 自動載入。
Workflow 人類速查（短命令、跳過確認、恢復 session）：docs/AI_AGENT_SETUP.md。
Codex / Cursor 入口：根目錄 AGENTS.md（Codex）、.cursor/rules/（Cursor）。
必讀（改碼前）
- docs/ARCHITECTURE.md — 技術棧、目錄、資料流、IPC 表、常見修改入口
- docs/ENCODING.md — UTF-8 無 BOM、LF、pwsh 7+
- docs/PROJECT_WORKFLOW.md — workflow 單一真相（gate、狀態轉移、commit、diagnostic log）
- docs/AI_AGENT_PROMPTS.md — 六步 prompt 模板與短命令
Workflow 五條硬規則（摘要）
規則全文與狀態轉移：docs/PROJECT_WORKFLOW.md § Agent 強制規則。修改規則先改該文件，再同步本檔與其他入口。
- 先 proposal，後寫回 — 第一次回覆不得改 repo、不得 commit（可讀檔探索）。
- 跳過確認 — 僅限同一則訊息明確說
跳過確認/skip confirmation/直接执行/直接修改等；快点做、In progress不算。 執行 task= 兩階段 — 第一次只出 execution plan；確認後才實作；Step 4 不 commit。驗收 task= 先 review — 第一次只給 Accept / Needs changes / Blocked；自行讀logs/*.log對照 task doc；人類確認 Accept 後才標 Done、downgrade log、commit。- 改 workflow 規則 — 先改
PROJECT_WORKFLOW.md，再同步AI_AGENT_PROMPTS.md、AI_AGENT_SETUP.md、本檔（CLAUDE.md）、AGENTS.md、.cursor/rules/workflow.mdc、.kiro/steering/workflow.md。
| 短命令 | 第一次回覆 |
|---|---|
brainstorm / review / sprint planning |
proposal |
執行 task Ixxx-yy |
階段 A plan |
驗收 task Ixxx-yy |
acceptance review |
Sprint X summary |
summary proposal |
Step 5 commit：第一行 Ixxx Item Name Ixxx-yy Accept task；body 含驗收摘要；最後一行 Co-authored-by: ClaudeAgent；Windows 用 git commit -F（UTF-8 無 BOM）。詳見 PROJECT_WORKFLOW § Commit Message。
關鍵路徑
完整架構見 docs/ARCHITECTURE.md。常用入口：
| 用途 | 路徑 |
|---|---|
| IPC 前端入口 | src/api/tauri.ts |
| 應用狀態 | src/app/useOverlayData.ts |
| Tauri 命令 | src-tauri/src/lib.rs |
| 日誌監聽 | src-tauri/src/watcher.rs、log_parser.rs |
| Sprint / task | docs/SPRINTS.md、docs/sprints/ |
| 型別 | src/types.ts |
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.
- 2mo ago First seen · 56 lines · 1,002 tokens per session scan A 1590f57f64d3
POE2Overlay CLAUDE.md is an instructions file published in the GitHub repository yuz9610/POE2Overlay (9 stars, last pushed 5mo ago), licensed MIT. It adds 1,002 tokens to every session, about $0.0040 per session on Opus 5.5. 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.
POE2Overlay CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| POE2Overlay CLAUDE.mdyuz9610/POE2Overlay | Instructions file | 9 | 5mo ago | MIT | A | 1,002 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| vscode ai-customization.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 1,907 | GitHub Copilot |