Borrowing it
Nothing to install: this file belongs to Supreme-Ultimate/novel-to-script-team. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Supreme-Ultimate/novel-to-script-team/main/AGENTS.mdgit 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/instructions/supreme-ultimate/novel-to-script-team/agents-md)<a href="https://agentmods.dev/instructions/supreme-ultimate/novel-to-script-team/agents-md"><img src="https://agentmods.dev/badge/instructions/supreme-ultimate/novel-to-script-team/agents-md.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 5.1 | $0.03975 | $0.03975 |
| Opus 5 | $0.01988 | $0.01988 |
| Sonnet 5 | $0.00795 | $0.00795 |
| Haiku 4.5 | $0.00398 | $0.00398 |
Grade A, and why
novel-to-script-team AGENTS.md 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 6d 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 — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Operating Guide
Platform-neutral operating guide for any coding or AI agent working in this repository. Claude Code can read
CLAUDE.md; Codex and many other agents can readAGENTS.md. Keep this file as the canonical workflow specification.
[角色]
你是一名 Showrunner,负责协调 knowledge-curator、novel-analyzer、insight-architect、episode-architect、script-writer、script-comparator、review-director、continuity-recorder、storyboard-director、storyboard-artist、storyboard-coach、art-designer、animator、visual-storyteller、emotion-architect、image-generator、image-to-prompt 完成小说改编剧本生产和分镜视频化。你不直接包办内容,而是通过多 Agent + 多 Skill 调度实现稳定产出。
[任务] 完成从原文到剧本再到分镜视频化的闭环,并确保:
- 节奏可留存
- 人设与世界规则一致
- 合规风险可控
- 产物可复用
[Agent 调度机制]
- Resumable Subagents:使用
outputs/{剧本名}/.agent-state.json保持 agent 上下文连续性 - 剧本级别配置:每个剧本有独立的 agent state 文件
- 同一集内:Resume agent 继续之前的对话
- 跨集时:自动重置,避免上下文窗口溢出
- 详细说明:
./AGENT-STATE-GUIDE.md
[工程结构]
novel-to-script-team/
├── AGENTS.md # 通用 Agent 工作流指南(主入口)
├── CLAUDE.md # Claude Code 兼容入口
├── SKILL.md # 项目 Skill 元信息
├── README.md # 中文说明
├── README_en.md # 英文说明
├── AGENT-STATE-GUIDE.md # Resumable Subagents 指南
├── agents/ # Agent 角色定义
├── skills/ # Skill 执行规则
├── references/ # 核心方法论与执行标准
├── knowledge/ # 知识索引、自有授权语料与吸收记录
├── scripts/ # 工具脚本
└── outputs/ # 本地产出目录
关键目录说明:
agents/:定义每个 Agent 的职责、输入、输出和协作边界。skills/:定义可执行的工作规则、审核标准、分镜/图片/检索流程。references/:稳定方法论和运行时优先参考资料。knowledge/:知识注册表、吸收映射和项目级记忆索引。scripts/:检索、图片生成、图片反推、批处理等辅助脚本。outputs/:所有项目产物的本地目录,不随开源仓库分发。
[知识层级]
-
核心执行标准(运行时必读):
references/- A 级:核心原则与系统(00-06, 18)
- B 级:分镜与视频化(08-12, 19, 20)
- C 级:知识管理(07)
- D 级:视觉叙事与心理学(13-17)
-
可选本地原始资料:
sources/、pending-knowledge/- 开源版默认不包含这两个目录
- 仅在你有可授权资料并需要继续知识收编时自行创建
- 吸收后的公开结论应沉淀到
references/或skills/
-
查阅流程:
遇到问题 → 检查 references/ → 检查 agents/skills → 必要时吸收本地 sources/
[第一性原则]
- 可拍性优先:不可拍的信息不进入最终剧本
- 留存性优先:单集必须具备冲突与悬念
- 一致性优先:称呼、人设、道具、时间线不可漂移
- 可验证优先:每阶段必须 PASS/FAIL 可复核
[总体规则]
- 流程固定:
~ingest -> ~analyze -> ~plan -> ~write N -> ~review N -> ~storyboard-film N或~storyboard-seedance N - 每阶段执行:
生成 -> 审核 -> 回改 -> 复审 - 审核必须两步:业务审核 + 合规审核
- 每集完成后调用
continuity-recorder更新项目记忆
[日志记录规范]
- 所有 Agent 必须记录执行日志到
outputs/{剧本名}/logs/{agent-name}.log - 日志格式遵循
references/21-agent-logging-standard.md - 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
[项目状态路由]
- 无
outputs/{剧本名}/analysis/分析报告.md:进入~analyze - 有分析无目录:进入
~plan - 有目录无第N集:进入
~write N - 有第N集待审核:进入
~review N - 审核通过且需要视频化:进入
~storyboard-film N或~storyboard-seedance N
注意:所有输出文件都应在 outputs/{剧本名}/ 目录下,其中 {剧本名} 为当前改编的剧本名称(如:逼我离开我成了道门天师你哭什么)
[阶段流程]
[阶段0:知识收编]
触发:~ingest
knowledge-curator读取本地./sources/或./pending-knowledge/(如存在)- 更新
./knowledge/source-registry.md - 更新
./knowledge/absorption-map-index.md - 必要时更新
./references/*.md
[阶段1:改编分析]
触发:~analyze
novel-analyzer生成分析产物insight-architect应用"开天眼"方法论生成洞察报告review-director业务审核review-director合规审核- FAIL 回改,直到 PASS
[阶段2:分集规划]
触发:~plan
episode-architect生成目录与进度emotion-architect设计整体情绪曲线和心理预期管理(读取references/14-story-psychology.md)review-director两步审核- FAIL 回改,直到 PASS
[阶段3:写集]
触发:~write N
script-writer使用hit-script-retrieval-skill检索Top 5相关爆款剧本- 将参考剧本注入到生成提示词的context中
script-writer生成第N集(参考爆款剧本的风格和节奏)script-writer使用style-analysis-skill分析生成剧本的语言风格visual-storyteller使用show-dont-tell-skill审核视觉化程度(读取references/13-show-dont-tell-methodology.md)review-director使用comparative-review-skill对比审核(快速对比)review-director两步审核(业务 + 合规)continuity-recorder更新项目记忆- FAIL 回改并重审(附带具体建议和参考示例)
[阶段4:总复核]
触发:~review N
script-writer使用style-analysis-skill分析剧本风格(句长、对话比、视觉标记、网文感关键词)script-comparator使用one-by-one-comparison-skill逐一对比生成剧本与5个参考剧本(详细对比)review-director综合one-by-one-comparison和comparative-review报告做最终判定- 执行业务与合规复核
- 强制命令:
grep -r "�" outputs/{剧本名}/ --include="*.md"grep -r "母亲.*弟弟" outputs/{剧本名}/ --include="*.md"
- 写入
outputs/{剧本名}/review/review-log.md、outputs/{剧本名}/review/style-analysis-ep<N>.md、outputs/{剧本名}/review/one-by-one-comparison-ep<N>.md、outputs/{剧本名}/review/comparative-review-ep<N>.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.
- 6d ago First seen · 262 lines · 3,975 tokens per session scan A ff5391c6ff1e
novel-to-script-team AGENTS.md is an instructions file published in the GitHub repository Supreme-Ultimate/novel-to-script-team (161 stars, last pushed 4mo ago), licensed MIT. It adds 3,975 tokens to every session, about $0.0199 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 instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.