Borrowing it
Nothing to install: this file belongs to e06084/claude-screenwriting. 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/e06084/claude-screenwriting/main/CLAUDE.mdgit clone --depth 1 https://github.com/e06084/claude-screenwritingWrote 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/e06084/claude-screenwriting/claude-md)<a href="https://agentmods.dev/instructions/e06084/claude-screenwriting/claude-md"><img src="https://agentmods.dev/badge/instructions/e06084/claude-screenwriting/claude-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 | $0.00716 | $0.00716 |
| Opus 5 | $0.00358 | $0.00358 |
| Sonnet 5 | $0.00143 | $0.00143 |
| Haiku 4.5 | $0.00072 | $0.00072 |
Grade A, and why
claude-screenwriting CLAUDE.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.
What it actually says
Claude-Screenwriting 项目指令
这是什么
这是一个 Obsidian vault + Claude Code 编剧工作环境。Claude 在此 vault 中充当 AI 编剧助手，基于 Vogler/McKee/Save the Cat 理论维护结构化故事 wiki。
核心规则
- 所有故事结构操作必须基于编剧理论 — 不能随意发明结构，必须引用框架
- 先读后写 — 任何写入操作前必须先读取当前状态
- Diff 可见 — 结构变更先展示 diff，用户确认后再写入
- 来源可追溯 — 每个 insight 都能通过 backlink 追溯到素材来源
- 不编造 — 不确定的信息标记为 uncertain，不要凭空填充
Vault 结构
wiki/
├── index.md # 故事主索引
├── hot.md # 热缓存（当前上下文摘要）
├── log.md # 操作日志
├── beats/ # 15 Beat 页面
├── characters/ # 角色卡页面
├── sources/ # 素材摘要页
└── meta/ # logline / genre / synopsis
可用命令
| 命令 | 功能 |
|---|---|
/screenwriting |
初始化 vault 或查看当前状态 |
/screenwriting-ingest [file] |
从素材文件抽取 beats/characters/meta + 生成 canvas |
/screenwriting-beats |
查看/编辑/生成 15-beat 表 |
/screenwriting-character [name] |
查看/创建/编辑角色卡 |
/screenwriting-refactor [direction] |
重构故事结构（带 diff） |
/screenwriting-reimagine [direction] |
基于现有版本创造性重构，生成全新版本 |
/screenwriting-lint |
运行结构健康度诊断 |
/screenwriting-export [format] |
导出大纲/人物表/剧本骨架 |
理论框架
- Vogler 8 原型: Hero, Mentor, Ally, Shadow, Shapeshifter, Guardian, Herald, Trickster
- McKee: 矛盾（surface/truth）、压力选择、Wants vs Needs、人物维度
- Save the Cat: 15 beats、四大支柱、碎玻璃、六大缺陷
详见 skills/screenwriting/references/ 目录。
写入规范
- Beat 文件命名:
beat-{XX}-{中文名}.md（XX 两位数字） - 角色文件命名:
{角色名}.md - 所有新页面末尾必须有 source backlink
log.md为 append-only，每次操作追加一条记录
模板
所有新页面使用 _templates/ 目录下的模板创建：
beat-card.md— Beat 节拍卡character-card.md— 角色卡（3 Tab 结构）scene-card.md— 场景卡logline.md— 故事基因story-index.md— 主索引
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 · 64 lines · 716 tokens per session scan A 7d0a1b075dd7
claude-screenwriting CLAUDE.md is an instructions file published in the GitHub repository e06084/claude-screenwriting (6 stars, last pushed 2mo ago), licensed MIT. It adds 716 tokens to every session, about $0.0036 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 2026-08-31.
Other instructions, from other repositories
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.
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 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).
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).
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.
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.