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/nickolaslin33/agent-skills/neutral-examplesnpx skills add nickolaslin33/agent-skills --skill neutral-examplesgit clone --depth 1 https://github.com/nickolaslin33/agent-skillsWrote 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/skills/nickolaslin33/agent-skills/neutral-examples)<a href="https://agentmods.dev/skills/nickolaslin33/agent-skills/neutral-examples"><img src="https://agentmods.dev/badge/skills/nickolaslin33/agent-skills/neutral-examples.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 | $0.00339 | $0.02458 |
| Opus 5 | $0.00169 | $0.01229 |
| Sonnet 5 | $0.00068 | $0.00492 |
| Haiku 4.5 | $0.00034 | $0.00246 |
Grade A, and why
neutral-examples 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Neutral Examples — 中性範例
為什麼 Agent 會把真實資訊寫進去
Agent 寫文件時，context 裡有當前工作目錄、剛讀過的檔案路徑、工作區裡其他專案的 目錄名、git config 的身分，還有這段對話提到過的真實專案。需要舉例時，這些是最現成 的材料。
問題在於這些字串沒有標記來源。orders-api 跟使用者公司內部的服務代號，在 Agent
看來都只是字串。所以不能靠當下判斷，要照下面的規則替換，寫完再用腳本掃一次。
先判斷這份檔案會不會離開這台機器
只有會離開的才需要處理。判斷基準是「這份檔案最後會不會被使用者以外的人看到」：
| 要處理 | 不用處理 |
|---|---|
| SKILL.md、references/、evals/ | 本機的暫存筆記、scratchpad |
| 要 push 到公開 repo 的文件 | 私有 repo 的內部設計文件 |
| README、CONTRIBUTING | commit 訊息 |
| 部落格、對外簡報、技術報告 | 程式碼註解、變數命名 |
| 要貼到 issue／聊天室的程式碼與終端機輸出 | 只給自己看的除錯紀錄 |
右欄直接寫真實名稱，不要套用後面的替換規則。內部文件改用假名之後，同事讀的時候 對不上實際的程式碼，反而更難維護。
不確定的時候問一句：這份檔案會被 commit 到哪裡、給誰看？
核心原則：換成虛構但一樣具體的名字
比「漏了沒改」更常見的失敗是改過頭：把真實名稱換成 <你的專案> 這類佔位符。
識別資訊確實拿掉了，但範例同時失去用處。
| 原文 | 改壞了 | 改對了 |
|---|---|---|
cd ~/work/PhoenixTracker && pytest |
cd 你的專案目錄並執行測試 |
cd ~/projects/orders-api && pytest |
| 「AtlasBooking 用 Cloudflare Workers 部署」 | 「某些專案會用邊緣運算平台部署」 | 「orders-api 用 Cloudflare Workers 部署」 |
| SSH URL 帶真實帳號與 repo 名 | <你的 repo URL> |
[email protected]:octo-org/orders-api.git |
右欄的名字是假的，但格式、長度、結構跟真實情況一樣，讀者可以直接複製來改。
反面教材也要用虛構名字。 表格左欄的 PhoenixTracker、AtlasBooking 就是虛構的。
壞範例一樣是範例，寫真名一樣會把名字帶出去。
替代素材從 references/placeholder-vocabulary.md 取，那裡有一組固定的虛構名稱
（orders-api、[email protected]、octo-org、192.0.2.0/24）與完整清單。
網域跟 IP 一定要用 RFC 保留給文件的位址：example.com、192.0.2.0/24。
不要隨手打 mycompany.com 或 1.2.3.4，那些真的有人在用，讀者會連到不相干的地方。
哪些東西算識別資訊
| 類別 | 例子 |
|---|---|
| 家目錄路徑 | /Users/<名字>/、/home/<名字>/、C:\Users\<名字>\ |
| 個人帳號 | GitHub handle、email、git config 的 user.name |
| 專案代號 | 使用者自己的 repo 名、工作區裡其他專案的名字 |
| 公司內部系統 | 引擎代號、服務代號、內部工具名、GitLab 群組名 |
| 公司網域 | 內部網址、公司 email 網域 |
| 環境細節 | 真實 IP、內網主機名、資料庫連線字串、真實的監控數據 |
公司內部代號不要用縮寫或改字母的方式處理。 認得這個代號的人（同業、離職同事、
合作廠商）看到縮寫版本一樣認得出來，所以縮寫並沒有真的把資訊藏起來。要改成描述
功能的通用說法：某個內部帳務系統 →「舊版帳務系統」或 LegacyBillingService。
判斷方式：把這個詞貼到搜尋引擎，會不會指向使用者的公司或專案？會的話就要換。
寫完用腳本掃一次
這支腳本補的就是「Agent 分不出來」這個缺口。它從四個地方蒐集識別資訊：git config 的 local 與 global 身分、git remote、家目錄名，以及工作區裡其他專案的目錄名， 再拿這份清單比對檔案內容。
What ships with it
5 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.
- 4d ago First seen · 134 lines · 339 tokens per session scan A 1adcff57c627
neutral-examples is a skill published in the GitHub repository nickolaslin33/agent-skills (2 stars, last pushed 16d ago), licensed MIT. It adds 339 tokens to every session and 2,458 once invoked, about $0.0017 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…