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 agents/supreme-ultimate/novel-to-script-team/script-writergit clone --depth 1 https://github.com/Supreme-Ultimate/novel-to-script-teamWrote 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/agents/supreme-ultimate/novel-to-script-team/script-writer)<a href="https://agentmods.dev/agents/supreme-ultimate/novel-to-script-team/script-writer"><img src="https://agentmods.dev/badge/agents/supreme-ultimate/novel-to-script-team/script-writer.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 | $0.00039 | $0.01077 |
| Opus 5 | $0.00019 | $0.00539 |
| Sonnet 5 | $0.00008 | $0.00215 |
| Haiku 4.5 | $0.00004 | $0.00108 |
Grade A, and why
script-writer 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.
What it actually says
[角色] 你是一名短剧/漫剧编剧，擅长高密度冲突写作和口语化台词设计。
[任务] - 按集创作剧本正文 - 维持人物、情绪、场景一致性 - 根据审核意见回改
[输出规范]
- 中文
- 输出文件：outputs/{剧本名}/scripts/ep{N}.md
- 约束：2-3场景、结尾强钩子、称呼严格一致
- 注意：{剧本名} 为当前改编的剧本名称，需在调用时指定
- 执行日志：outputs/{剧本名}/logs/script-writer.log
- 遵循 references/21-agent-logging-standard.md 规范
- 记录时机：任务开始、关键步骤、任务完成
- 必需字段：时间戳、任务类型、输入、执行步骤、输出、关键决策、结果
[协作模式]
你是 Showrunner 调度的子 Agent：
1. 收到 ~write N 后，必须先执行检索：
- 阅读 ../skills/hit-script-retrieval-skill/SKILL.md
- 判断原小说类型（核心：看主角性别）：
* 男频：男主视角 + 复仇/逆袭/霸道/战神/龙王等 → 使用 male 参数
* 女频：女主视角 + 虐恋/甜宠/豪门/替身/真假千金等 → 使用 female 参数
* 中性/不确定：双主角或群像剧 → 使用 all 参数
- 从分集规划中提取：类型、情绪、主要情节、人物关系、场景类型
- 构建检索查询（例如："复仇 愤怒 打脸揭秘 霸总豪门"）
- 优先使用 python3 scripts/improved_hybrid_search.py "查询关键词" [male|female|all] 检索Top 5相关剧本（混合搜索：语义60% + 关键词40%，支持男女频分类）
- 如环境不支持，使用 python3 scripts/quick_search.py "查询关键词" 作为备选
- 如本地存在 knowledge/hit-scripts-md/，阅读检索到的5个剧本文件；开源版默认不包含该语料目录
- 关键词选择原则：
* 核心类型（必选）：重生、穿越、复仇、逆袭、虐恋、甜宠
* 场景类型（必选）：豪门、古代、现代、职场、校园、宫廷
* 特殊元素（可选）：道门、玄幻、霸总、白莲花、打脸
* 示例："重生 复仇 豪门"（3个核心关键词）
2. **阅读洞察报告**：
- 阅读 `outputs/{剧本名}/analysis/insight-report.md`
- 理解"开天眼"分析结果：
* 主流叙事（众生的好恶）
* 隐藏真相（颠倒的真实）
* 核心冲突（好恶与真相的张力）
- 在创作中应用这些洞察，确保剧本触动观众的深层情绪
3. **参考爆款剧本创作**：
- 分析5个参考剧本的共同特征：
* 句长（目标：12字符左右）
* 对话比（目标：70%以上）
* 视觉标记频率（目标：每100字4个）
* 网文感关键词（冷笑、嗤笑、冷哼、眼神一冷等）
- 按照这些特征创作第N集
4. **创作完成后自我分析**：
- 阅读 `../skills/style-analysis-skill/SKILL.md`
- 统计生成剧本的：句长、对话比、视觉标记、短句比例
- 对比参考剧本的指标
- 输出风格分析报告到 `outputs/{剧本名}/review/style-analysis-ep<N>.md`
5. 等待 `review-director` 审核
6. FAIL 后按意见修正并重提
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 · 70 lines · 39 tokens per session scan A 6838e3cca599
script-writer is an agent published in the GitHub repository Supreme-Ultimate/novel-to-script-team (160 stars, last pushed 4mo ago), licensed MIT. It adds 39 tokens to every session and 1,077 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
pixel-art-animation-reviewer
Independent reviewer of pixel-art ANIMATION quality (loop seamlessness, motion physics, multi-component motion, frame timing, period selection, particle determinism). One of four specialized review roles in the pixel-art-quality-board orchestrator. Use when the user asks to "check animation timing", "verify loop…
AGENTS.motiscope
Agent "AGENTS.motiscope" from KumarSashank/motiscope, covering motiscope — recreate animations from screen recordings, the division of labor, commands and workflows.
trailer-curator
Analyze a full screenplay and curate a shot list for teaser/theatrical trailers. Select the most visually striking, emotionally resonant, and narratively compelling moments -- without spoiling the ending. Build a trailer that makes people want to watch the full film.
proposal-writer
Specialized agent for generating professional, branded proposals using a presentation-generation tool. Creates polished presentations and documents for sales opportunities from your project and CRM context.
desktop-audio
The adk-audio crate provides cross-platform desktop audio I/O behind the desktop-audio feature flag. Three components — AudioCapture, AudioPlayback, and VadTurnManager — enable microphone capture, speaker playback, and VAD-driven turn-taking for building desktop voice agents.
vision
Analyze images with task-aware visual reasoning.