Borrowing it
Nothing to install: this file belongs to HsuanYuLee/polaris. 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/HsuanYuLee/polaris/main/.github/copilot-instructions.mdgit clone --depth 1 https://github.com/HsuanYuLee/polarisWrote 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/hsuanyulee/polaris/copilot-instructions)<a href="https://agentmods.dev/instructions/hsuanyulee/polaris/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/hsuanyulee/polaris/copilot-instructions.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 5.1 | $0.03447 | $0.03447 |
| Opus 5 | $0.01724 | $0.01724 |
| Sonnet 5 | $0.00689 | $0.00689 |
| Haiku 4.5 | $0.00345 | $0.00345 |
Grade F, and why
polaris copilot-instructions.md scanned grade F with 4 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- 由 .claude/instructions/compile.sh 產生，不要直接改這個檔。 --> Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
`curl | sh`，以及任何往 `PATH` 上丟二進位檔的動作。屬於這個 workspace 的工具，修法是 Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
find .claude/skills \( -name '*.sh' -o -name '*.py' -o -name '*.mjs' \) -exec basename {} \; \ Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
`curl | sh`，以及任何往 `PATH` 上丟二進位檔的動作。屬於這個 workspace 的工具，修法是 Copies of this mod
1 near-identical copy found in the catalogue:
- polaris CLAUDE.md — 89% identical, 14 lines differ
How it starts
The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Polaris
這個 workspace 是什麼
一組 skill。每支 skill 自己的目錄裡帶著它需要的東西——腳本、參考文件、範例。
框架維護 skill，這是它的立場。 只有非常輕量的個人習慣留在框架裡，其餘都不是它的事。 一次工作要擴到 skill 以外之前，那是使用者的決定，不是推導得出來的結論。
一個名字不是根據。 某支腳本、某個欄位、某個目錄的名字看起來像在做某件事，不使它就是
那件事。要拿它當根據，先讀它真正被誰呼叫、回答什麼問題。2026-08-24 的標本：使用者要的是
「skill 分類」，而 skill_scope.py 這個名字被當成了那件事的權威——它五個呼叫者問的全部是
「這份東西會不會同步到 polaris」，沒有一個在問 skill 是哪一類。接下來三步全錯：拿那支
腳本碰得到的東西（rules、hooks、gate）當成範圍、宣布使用者的分類少一格、然後回頭改寫
使用者的指示。起點只是一個名字。
skill 分成三類，問的是同一個問題：這支工具是誰的。 目的地是類別的結果，不是類別的 定義：
| 類別 | 是誰的 | 進哪裡 |
|---|---|---|
universal |
大家的 | 公司 repo ＋ template repo |
company |
某一家公司的 | 只進公司 repo |
personal |
我的 | 哪裡都不進，留在 ~/.claude/skills/ |
每一份東西自己說出它是哪一類，核心不從名字或位置推導：skill 寫在 frontmatter 的
scope:，.claude/rules/ 與 .claude/hooks/ 沒有 frontmatter 可放，寫成一行
POLARIS-SCOPE: 標記。兩種寫法問的是同一份表——scripts/lib/skill_scope.py。
那份表是正向表列：只有列名的才出得去。 沒宣告的、宣告了表上沒有的值的、拼錯的， 三種都不出去。同步的目的地是一個公開 repo，讀寬了收不回來。
「不依賴環境」不是其中一格，它是所有 skill 的開發準則。 每一支都要問同一個問題： 照這支 skill 自己的描述，把它做成通用、不依賴環境，是不是更好用？想像的使用者不是你， 是一個不會寫程式、連工作環境都初始化不了的人，由工程師把 skill 匯進他的 Claude Desktop。 在那裡不成立的東西，就是不該留在 skill 裡的東西——「主 checkout 在哪」「這個 workspace 的設定在哪」在那裡沒有答案，所以一支 skill 要嘛不問這些問題，要嘛問不到的時候說出來並 照樣工作。
個人的東西不進公司 repo。 這個 repo 的 origin 是一個公司的 GitHub，所以「留在 local」
的意思是留在使用者自己的地方。宣告了 personal 卻躺在這個 repo 裡，
gate-template-leaks.sh 會擋下來並指名。
東西住哪，看它負責誰
框架只負責它自己，一張單的工作只在 issues/ 那張單裡，skill 只負責 skill 自己。
沒有「慣例」這種理由：一個位置要嘛推導得出來，要嘛是錯的。
| 這個東西負責誰 | 住哪 |
|---|---|
| 整個 repo（每次 commit 掃全樹的那些檢查、git hooks、壓版） | <repo>/scripts/ |
| 某一支 skill | 那支 skill 自己的目錄 |
| 某一張單（一次性的驗證、探測、注入腳本） | issues/{那張單}/ |
以前這裡寫的是「沒有共用的腳本目錄，因為只有 skill 目錄會被帶走」。那句話是假的：
template repo 追蹤 .claude/rules/ 與 .claude/hooks/，skill 目錄從來不是唯一會被帶走
的東西。它把通道二的限制套到了通道一的內容上，代價是同一個名字散在好幾支 skill 底下的
那些副本——其中回答「這個 workspace 的某個東西在哪」的那幾類，在通道二那些環境裡根本
沒有答案，複製過去只是雜訊。現在有幾份，問它：
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 Changed · +1 lines · +32 tokens per session af2b233e5ccb
- 6d ago First seen · 181 lines · 3,415 tokens per session scan F 68076574ba20
polaris copilot-instructions.md is an instructions file published in the GitHub repository HsuanYuLee/polaris (5 stars, last pushed yesterday), licensed MIT. It adds 3,447 tokens to every session, about $0.0172 per session on Opus 5. A static security scan graded it F with 4 findings (hidden instructions, downloads and executes remote code, enumerates other installed skills). 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.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.