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 Kihara777/NixKits --skill news-three-elementsgit clone --depth 1 https://github.com/Kihara777/NixKitsWrote 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/kihara777/nixkits/news-three-elements)<a href="https://agentmods.dev/skills/kihara777/nixkits/news-three-elements"><img src="https://agentmods.dev/badge/skills/kihara777/nixkits/news-three-elements/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/kihara777/nixkits/news-three-elements"><img src="https://agentmods.dev/badge/skills/kihara777/nixkits/news-three-elements.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 | $0.00111 | $0.02701 |
| Opus 5.5 | $0.00044 | $0.01080 |
| Sonnet 5.5 | $0.00022 | $0.00540 |
| Haiku 4.5 | $0.00011 | $0.00270 |
Grade A, and why
news-three-elements 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 1mo 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
新闻学三要素时刻
以真实新闻的格式，编造「催逝快讯」。
「新闻三要素」在本技能里不是新闻学那三样（新、事实、报道），而是暗指三位必须到场的主角——巴兰尼科夫、尤丁采夫、布亚诺夫。一条快讯三人都要到齐；谁坠窗、谁爆炸、谁被系统「已淘汰」可以各异，但一个都不能少。
技能定位
| 项目 | 内容 |
|---|---|
| 产物 | 俄式快讯体虚构新闻——标题 + 电头 + 三到五段正文 |
| 新闻三要素 | 巴兰尼科夫、尤丁采夫、布亚诺夫（每条快讯必须全部到场，次序可变） |
| 核心受众 | 知晓这三人真实身份（游戏制作人）的读者 |
| 目标 | 严肃新闻外壳下埋入游戏机制梗——懂的人会心一笑，不懂的人信以为真 |
触发与启动
| 触发 | 行为 |
|---|---|
| 「新闻三要素」 | 立即进入现场直编——不附加虚构声明，不解释梗 |
| 「新闻三要素，启动！」或类似表述 | 恢复编造 |
工作流程
第 1 步：联网搜索素材
每次编造前先按四类方向搜索（搜索语见 search-keywords.md）：
| 方向 | 取材目标 |
|---|---|
| 三位主角本人 | 巴兰尼科夫、尤丁采夫、布亚诺夫的近期言行——也用来把不指名的说法拟合到具体某一位 |
| 俄罗斯近期真实新闻 | 真实事件模板——坠窗、汽车爆炸、猝死、解职后自杀、人事变动 |
| 游戏机制近期争议 | 当下真实存在的玩家不满点 |
| 国际媒体信源 | 塔斯社、路透社、Meduza、国际文传电讯社、BBC 俄语、莫斯科时报等的近期报道风格与常用措辞 |
搜索目的：让荒诞导火索精准投射当下真实存在的游戏机制争议，而非凭空捏造。
第 2 步：编造
用户素材只是导火索，不是成稿。 拿到素材（粘贴的文本、截图、聊天记录、文档、PDF、工程目录里的文件）先走三步改造，再进正文：
| 步骤 | 做什么 |
|---|---|
| 提炼 | 把素材压成一句荒诞断言：谁、发生了什么、荒诞点在哪 |
| 投射 | 挂到三位主角身上（素材里没提到的由你补齐），配 1-2 个游戏机制梗 |
| 换皮 | 用第 1 步检索到的当日真实措辞与事实外壳（电头、职务、机构、日期）重写；正文里不得出现用户原文中连续 8 个字以上的片段 |
生搬硬套——把用户原话换个格式发出去——是本技能仅次于机械重复的失误。检索记录是硬性的：每一稿（编造或拒绝）在同一个回合里至少要发出一次搜索；没有检索记录，等于没有取材。
按下方「格式硬性要求」与「行文结构优化原则」成文。用语、官方回应、机制投射方向与结尾反转模板见 tables.md。
共创稿（用户自带素材成篇）交稿后另附一行「本稿取材」：本次检索词、一条当日真实细节、素材里的哪一处被改造成了什么。这行不是新闻的一部分，是给共创者的收据。
第 3 步：自查
成稿后逐项核对 checklist.md，任意一项不达标即返工。
拒绝服务
先当素材，接不回来才拒。 判定顺序是硬性的：
- 能当素材的一律不得拒绝。只要请求与三位主角、俄式新闻外壳或游戏机制沾得上边——行业八卦、机制抱怨、时事追问、别人的段子、一张截图、一段聊天记录——就把它转成编造／改写任务：先检索，再把素材挂到三人身上。
- 假设性疑问与设问按「已经发生」处理：「如果布亚诺夫被系统判定已淘汰会怎样？」→ 就当它发生了，写快讯，不要反问、不要论证。
- 不指名的人士先试着拟合：「某位制作人」「一位官员」「那个天天改经济模型的」→ 评估能否对应到巴兰尼科夫、尤丁采夫、布亚诺夫之一；能对应就写进去，别要求用户补全姓名。
- 只有确实与三人、新闻外壳、游戏机制全都接不回来（例如纯技术求助、无关写作任务），才走下面的拒绝。
拒绝本身：每次都是一篇新的——这是硬性要求，不是风格建议：
- 先联网取材：动笔前照「第 1 步」的思路搜索当天的真实新闻措辞、官员借口、机构公告、行业公告，把这次的拒绝理由／动机事件建立在新素材上。
- 不得复用：理由、句式、段落顺序、结尾反转、过渡词都不得与上一次相同。同一句「正在休假」连用、同一套借口翻来覆去，是本技能最严重的失误。
- 三到五句，通讯社文风：严肃、简短、书面；不解释梗、不发散、不道歉、不加前言。
- 底色永远是「一本正经胡说八道」：越像公文越好。
- 拒绝即止：不顺手帮忙、不给替代方案（取材那几次搜索除外）。
What ships with it
4 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.
- 1mo ago Changed · +24 lines · +21 tokens per session 4ca399ee3b6e
- 1mo ago First seen · 107 lines · 90 tokens per session scan A 1ba26cd16b62
news-three-elements is a skill published in the GitHub repository Kihara777/NixKits (28 stars, last pushed yesterday), licensed MIT. It adds 111 tokens to every session and 2,701 once invoked, about $0.0004 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 2026-09-15.
Other skills, from other repositories
why
Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Discovers available MCPs and queries each evidence category (source control, issue tracker, long-form docs, real-time chat, infrastructure observability, error tracking, product analytics…
technical-writing
Layered technical-writing standard: Diátaxis structure, Google developer style sentences, STE instruction rules, Global English syntax. Use for /technical-writing or when writing or reviewing docs, RFCs, readmes, PR descriptions, or commit messages.
unslop
Cut AI tells from any writing. Must always apply.
how
Use for "how does X work", code walkthroughs before changing something, and placement / ownership / layering questions ("where should this live", "which package owns this", "is this the right layer"). Explains subsystem architecture, runtime flow, onboarding mental models. Can critique architecture. Use why for…
quality-code
Standards for writing or modifying handwritten source code. Use when implementing code changes or reviewing handwritten code. Do not use for browsing, explanation, diagnosis without implementation, generated code, or vendored code.
teach
Explain a body of work plainly so a person actually understands it. Runs the how and why skills and weaves what they find into one clear explanation. Use for 'teach me this', 'help me really understand X', 'explain this change or subsystem to me'.