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 skills add a275618631/codex-antigravity-collaboration --skill writing-style-intakegit clone --depth 1 https://github.com/a275618631/codex-antigravity-collaborationWrote 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/a275618631/codex-antigravity-collaboration/writing-style-intake)<a href="https://agentmods.dev/skills/a275618631/codex-antigravity-collaboration/writing-style-intake"><img src="https://agentmods.dev/badge/skills/a275618631/codex-antigravity-collaboration/writing-style-intake/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/skills/a275618631/codex-antigravity-collaboration/writing-style-intake"><img src="https://agentmods.dev/badge/skills/a275618631/codex-antigravity-collaboration/writing-style-intake.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 | $0.00139 | $0.01299 |
| Opus 5 | $0.00069 | $0.00649 |
| Sonnet 5 | $0.00028 | $0.00260 |
| Haiku 4.5 | $0.00014 | $0.00130 |
Grade A, and why
writing-style-intake 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 11d 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.
What it actually says
文字風格確認
先取得足以影響成品的風格資訊，再開始撰寫。不要用一長串問題拖慢任務。
判斷是否需要詢問
- 檢查使用者是否已交代語氣、正式程度、讀者、目的或參考範例。
- 若風格資訊足以執行，簡短重述採用的風格後直接開始。
- 若使用者說「你決定」、「照原文」或要求延續既有風格，直接執行。
- 若只是校正錯字、翻譯短句、修改單一句子或填入固定格式，不要額外詢問。
- 只有在缺少的讀者、目的、格式或語氣會明顯改變成品時，才先詢問一個關鍵問題並提供精簡選項；若可用合理預設完成，直接採用預設並開始。
詢問方式
一次只問一組精簡選項，允許使用者直接回覆代號，也允許自由描述。
使用以下格式：
開始前請選文字風格，可直接回覆代號，例如「B＋正式＋精簡」：
- A. 自然口語：像真人說話，親切、不做作
- B. 專業俐落：重點清楚，句子精簡
- C. 沉穩正式：適合主管、客戶或正式場合
- D. 有說服力：強調價值、證據與行動
- E. 敘事有溫度：有人味、畫面感與情緒層次
- F. 自訂或提供範例：依指定作者、品牌或既有文件調整
另外請補充：讀者是誰、用途是什麼、希望的篇幅。若沒有偏好，可說「你決定」。
只保留與任務有關的選項。例如履歷優先提供「專業俐落／沉穩正式／成果導向」；簡報優先提供「高階摘要／提案說服／教學易懂／故事敘事」。不要把無關選項硬塞給使用者。
若使用者只回答部分資訊，採用該答案並對其餘項目做最保守、合理的預設，不要進行第二輪盤問。只有讀者、目的或格式缺失會造成成品方向明顯不同時，才追問一個關鍵問題。
任務別選項
- 文章：自然口語、知性平實、觀點鮮明、敘事有溫度。
- 履歷與求職文件：專業俐落、成果導向、穩健正式、個人故事。
- 報告與企劃：高階摘要、分析客觀、決策導向、提案說服。
- 簡報與講稿：高階摘要、教學易懂、提案說服、故事敘事。
- 商務訊息與電子郵件：簡潔直接、禮貌專業、溫和協調、明確催辦。
- 行銷與社群：品牌專業、自然親切、活潑有梗、轉換導向。
寫作規則
- 使用台灣繁體中文、台灣常用詞與全形中文標點；專有名詞依慣例保留原文。
- 優先寫清楚的主詞、動詞與具體資訊，刪除不影響意思的開場與收尾。
- 避免空泛拔高、宣傳腔、模糊歸因、過度排比、同義反覆、刻意三段式與「展望未來」式結尾。
- 避免聊天機器人口吻、討好語、過多粗體、裝飾性表情符號及不必要的破折號。
- 不要為了「像真人」故意加入錯字、口頭禪或虛構個人經驗。
- 保留原始事實、數字、專有名詞、引文與使用者立場；不得自行補造資料。
兩輪檢查
完成初稿後，在內部執行兩輪：
- 內容檢查：確認目的、讀者、篇幅、事實與結構符合要求。
- 自然度檢查：朗讀句子節奏，刪除 AI 套語、重複資訊與不自然的書面腔。
只交付修訂後版本；除非使用者要求，不要展示內部檢查過程或自行宣稱「已去除 AI 痕跡」。
與其他技能協作
本 Skill 只負責風格確認與寫作品質。若任務還涉及 DOCX、簡報、PDF 或試算表，先完成風格確認，再依對應的文件技能製作與驗證成品。
What ships with it
1 file 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.
- 11d ago First seen · 69 lines · 139 tokens per session scan A 671f65e2b92d
writing-style-intake is a skill published in the GitHub repository a275618631/codex-antigravity-collaboration (8 stars, last pushed yesterday), licensed MIT. It adds 139 tokens to every session and 1,299 once invoked, about $0.0007 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
agent-harness-fault-injection
Use when an agent workflow needs deterministic recovery evidence for sandbox, MCP/tool, worker, checkpoint, memory, or orchestration failures.
architecture-decision-records
Comprehensive patterns for creating, maintaining, and managing Architecture Decision Records (ADRs) that capture the context and rationale behind significant technical decisions.
aria
Designs the data model, API contracts, and structural foundation of the system.
aws-sst-development
SST v4 (Ion) expert for managing AWS resources as code with the Pulumi-backed framework.
autonomous-agent-patterns
Design patterns for building autonomous coding agents, inspired by Cline and OpenAI Codex.
peon-ping-log
Log exercise reps for the Peon Trainer. Use when user says they did pushups, squats, or wants to log reps. Examples - "/peon-ping-log 25 pushups", "/peon-ping-log 30 squats", "log 50 pushups".