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.
git clone --depth 1 https://github.com/wordflowlab/novel-writerWrote 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/commands/wordflowlab/novel-writer/luyao-dialogue)<a href="https://agentmods.dev/commands/wordflowlab/novel-writer/luyao-dialogue"><img src="https://agentmods.dev/badge/commands/wordflowlab/novel-writer/luyao-dialogue/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/commands/wordflowlab/novel-writer/luyao-dialogue"><img src="https://agentmods.dev/badge/commands/wordflowlab/novel-writer/luyao-dialogue.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 | $0.00000 | $0.02267 |
| Opus 5 | $0.00000 | $0.01133 |
| Sonnet 5 | $0.00000 | $0.00453 |
| Haiku 4.5 | $0.00000 | $0.00227 |
Grade A, and why
luyao-dialogue 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 12d 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 — 265 lines — stays where its author put it; the contents beside it link to each section on GitHub.
创作地道的乡土对话
生成富有陕北地方特色、生活化的人物对话。
使用方法
/luyao-dialogue <场景类型> [情境描述]
场景类型
日常交流
greeting- 见面问候farewell- 告别送别chat- 闲谈拉家常work- 劳动交流meal- 饭桌对话
情感表达
love- 恋爱表白family- 亲情对话conflict- 矛盾冲突comfort- 安慰劝慰encouragement- 鼓励激励
重要场合
decision- 重大决定parting- 离别时刻reunion- 重逢团聚celebration- 喜事庆祝mourning- 丧事悼念
示例输出
劳动中的对话
用户:/luyao-dialogue work 收麦季节的田间对话
AI:
【麦收时节·田间】
场景设置:
1982年夏天,包产到户后的第一个麦收。太阳刚出来,田福堂一家人都在地里割麦子。
人物:
- 田福堂(父亲,50岁)
- 兰花(母亲,45岁)
- 福军(儿子,22岁)
- 小玉(女儿,18岁)
对话内容:
田福堂(直起腰,用袖子抹一把汗):
"福军,你那边割得咱样哩?"
福军(不抬头,继续割):
"还行着哩,快到地头了。"
田福堂:
"今年麦子长得好,一亩地怎么也能打七八百斤。咱家这五亩地,能收四千斤!"
兰花(边割边说):
"你就别数了,还没收到家哩。老话说得好,粮食不到囤里,就不算自己的。"
田福堂(笑):
"哎,你这婆姨,就会泼冷水。今年包产到户,打下的粮食都是咱自己的,高兴还高兴不过来哩!"
小玉(抬头看太阳):
"爹,太阳都老高了,歇一下吧?喝口水再干。"
田福堂:
"不歇!趁着太阳没毒,再割一阵。麦子不等人,晚收一天就多一分风险。"
福军(插话):
"听收音机说,后天可能有雨。咱得抢收哩。"
兰花:
"那就不能歇了。小玉,你把水壶拿过来,让大伙喝口水,喝了继续干。"
小玉(递水壶):
"先给爹喝,爹干得最多。"
田福堂(接过水壶,咕咚喝了几口):
"好!有劲了!福军,你也来喝口。"
福军(走过来,喝水):
"爹,我在想,麦子收了,留够口粮,剩下的卖了,能不能买个手扶拖拉机?"
田福堂(眼睛一亮):
"手扶拖拉机?那可是大件!得两三千块钱哩!"
福军:
"我打听了,县农机站有一台旧的,一千八百块。咱卖了粮,再借点,应该能凑够。"
兰花(担心):
"借钱?那可不是闹着玩的。万一..."
田福堂(打断):
"婆姨,福军说得对!咱现在包产到户了,就得敢想敢干。有了拖拉机,犁地、播种、收割,啥都方便。"
小玉(兴奋):
"真的要买拖拉机?那咱家就是全村第一了!"
兰花(叹气):
"你们父子俩商量好就行。反正我这婆姨说了不算。"
田福堂(坚定):
"就这么定了!麦子一收完,就去县里看拖拉机。咱农民也要机械化!"
[对话继续...]
【语言特点分析】
1. 方言词汇:
- "咱样哩" - 怎么样
- "着哩" - 着呢(表进行态)
- "婆姨" - 妻子
- "泼冷水" - 打击积极性
2. 语气词:
- "哩" - 陕北方言特有语气词
- "咱" - 我们(亲切感)
- "啥" - 什么(口语化)
3. 表达特征:
- 句子简短朴实
- 情感含蓄内敛
- 多用俗语谚语
- 体现劳动人民智慧
离别时刻
用户:/luyao-dialogue parting 儿子第一次出远门打工
AI:
【车站送别】
时间:1985年初春
地点:县城汽车站
人物:
- 孙少平(24岁,准备去煤矿打工)
- 母亲(52岁)
- 妹妹兰香(20岁)
母亲(把一个布包往少平手里塞):
"这里面有十几个馒头,路上饿了吃。还有一块咸菜,别舍不得吃,出门在外,没人照顾你。"
少平(接过包,声音有些哽咽):
"妈,我知道了。你和爹要照顾好自己。"
母亲(眼圈红了,但强忍着没掉泪):
"到了那边,别和人吵架,别惹事。活累点没啥,但要当心,矿里危险。"
兰香(递给少平一个小布袋):
"哥,这是我给你做的鞋垫,两双。矿里潮,多备几双好换。"
少平(摸摸妹妹的头):
"兰香真懂事了。你在家好好学习,别让妈操心。"
母亲:
"一个月写一封信回来,让家里知道你平安。别省邮票钱。"
少平:
"一定写。妈,等我挣了钱,第一个月工资就寄回来。"
母亲(急忙摇手):
"不用!你自己留着。在外面,啥都要花钱。家里还过得去。"
司机(大声喊):
"去铜川的,上车了!马上开车!"
少平(转身要走,又回头):
"妈,你回去吧,别送了。"
母亲(终于忍不住,泪水涌出来):
"我看着你走。路上...路上当心。"
兰香(拉住母亲):
"妈,哥会照顾好自己的。哥,你快上车吧。"
少平(上车前,最后一句):
"妈,我走了!照顾好身体!"
[车开动后的描写...]
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.
- 12d ago First seen · 265 lines · 0 tokens per session scan A e86031611568
luyao-dialogue is a command published in the GitHub repository wordflowlab/novel-writer (944 stars, last pushed 10mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,267 tokens. 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 2026-08-30.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.