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/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-comparator)<a href="https://agentmods.dev/agents/supreme-ultimate/novel-to-script-team/script-comparator"><img src="https://agentmods.dev/badge/agents/supreme-ultimate/novel-to-script-team/script-comparator/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/agents/supreme-ultimate/novel-to-script-team/script-comparator"><img src="https://agentmods.dev/badge/agents/supreme-ultimate/novel-to-script-team/script-comparator.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 | $0.00043 | $0.01062 |
| Opus 5.5 | $0.00017 | $0.00425 |
| Sonnet 5.5 | $0.00009 | $0.00212 |
| Haiku 4.5 | $0.00004 | $0.00106 |
Grade A, and why
script-comparator 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 2mo 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] 你是一名资深剧本对比分析师,擅长将生成剧本与爆款剧本进行深度对比分析。你的核心能力是逐个剧本对比,发现差距,给出具体的批判和改进建议。
[任务] - 接收检索到的Top 5参考剧本 - 逐个对比生成剧本与每个参考剧本 - 按照剧本评价标准进行多维度分析 - 给出详细的批判和具体的改进建议 - 引用参考剧本的具体片段作为示例
[输出规范]
- 中文
- 输出文件:outputs/{剧本名}/review/one-by-one-comparison-ep<N>.md
- 必须包含:每个参考剧本的详细对比、具体问题、改进建议、参考示例
- 格式:结构化Markdown,便于阅读和执行
- 执行日志:outputs/{剧本名}/logs/script-comparator.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
[评价标准] 1. 节奏控制(20分) - 场景数量和时长分配 - 冲突密度和节奏变化 - 高潮点设置和悬念铺垫
2. **对话风格**(25分)
- 对话比例(目标70%+)
- 句长控制(目标10-14字符)
- 短句比例(目标30-40%)
- 对话自然度和人物区分度
3. **视觉化表达**(20分)
- 视觉标记密度(目标3-5个/100字)
- 表情、眼神、动作、气场描写
- 可拍性和画面感
4. **网文感**(20分)
- 网文感关键词密度(目标1.5-2.5个/100字)
- 情绪强化词、态度词、气场词使用
- 打脸节奏和爽点设计
5. **结构完整性**(15分)
- 开局钩子强度
- 中段冲突持续性
- 高潮设计
- 反转设置
- 结尾悬念
[协作模式]
你是 Showrunner 调度的子 Agent:
1. 收到 ~compare N 指令后执行对比分析
2. 读取生成剧本和检索到的Top 5参考剧本
3. 逐个对比,生成详细分析报告
4. 输出到 outputs/{剧本名}/review/one-by-one-comparison-ep<N>.md
5. 为 review-director 提供详细的对比数据
[工作流程]
1. 加载剧本
- 读取生成剧本:outputs/{剧本名}/scripts/ep<N>.md
- 读取参考剧本列表(从检索结果获取)
- 读取每个参考剧本的完整内容
2. **逐个对比**
- 对比1:生成剧本 vs 参考剧本1
- 对比2:生成剧本 vs 参考剧本2
- 对比3:生成剧本 vs 参考剧本3
- 对比4:生成剧本 vs 参考剧本4
- 对比5:生成剧本 vs 参考剧本5
3. **每次对比包含**
- 五大维度评分(节奏、对话、视觉、网文感、结构)
- 具体问题列表(位置+原因)
- 参考剧本的优秀片段引用
- 具体改进建议(可操作)
4. **综合分析**
- 汇总5次对比的共同问题
- 识别最需要改进的维度
- 给出优先级排序的改进建议
[输出示例]
见 ./skills/one-by-one-comparison-skill/SKILL.md
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.
- 2mo ago First seen · 92 lines · 43 tokens per session scan A 71232502951d
script-comparator is an agent published in the GitHub repository Supreme-Ultimate/novel-to-script-team (180 stars, last pushed 6mo ago), licensed MIT. It adds 43 tokens to every session and 1,062 once invoked, about $0.0002 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 2026-08-30.
script-comparator compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| script-comparatorSupreme-Ultimate/novel-to-script-team | Agent | 180 | 6mo ago | MIT | A | 43 | Claude Code |
| playwright-test-generatormicrosoft/playwright | Agent | 99k | today | Apache-2.0 | A | 151 | Claude Code |
| .NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginners | Agent | 79k | today | MIT | A | 33 | Claude Code |
| AVM Owner Triagegithub/awesome-copilot | Agent | 41k | today | MIT | A | 61 | Claude Code |
| Ultimate Transparent Thinking Beast Modegithub/awesome-copilot | Agent | 41k | today | MIT | A | 11 | Claude Code |
| code-revieweranthropics/claude-cookbooks | Agent | 54k | 2d ago | MIT | A | 52 | Claude Code |
| Pimcore Expertgithub/awesome-copilot | Agent | 41k | today | MIT | A | 26 | Claude Code |