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/JS-mark/skillsWrote 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/js-mark/skills/drama)<a href="https://agentmods.dev/commands/js-mark/skills/drama"><img src="https://agentmods.dev/badge/commands/js-mark/skills/drama/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/js-mark/skills/drama"><img src="https://agentmods.dev/badge/commands/js-mark/skills/drama.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 | $0.00012 | $0.00891 |
| Opus 5.5 | $0.00005 | $0.00356 |
| Sonnet 5.5 | $0.00002 | $0.00178 |
| Haiku 4.5 | $0.00001 | $0.00089 |
Grade A, and why
drama 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
执行步骤
步骤一:确定路径 + 加载存档
- 如果用户在
/drama后指定了路径(如/drama ~/my-project),使用该路径作为<DRAMA_ROOT> - 如果之前的对话中已经确定过路径,沿用该路径
- 否则使用默认路径
~/Desktop/drama/
确定路径后:
- 使用 Glob 检查
<DRAMA_ROOT>/project.md是否存在 - 如果存在,依次 Read 以下文件恢复上下文:
<DRAMA_ROOT>/project.md— 项目配置<DRAMA_ROOT>/outline.md— 故事大纲<DRAMA_ROOT>/characters.md— 角色档案<DRAMA_ROOT>/progress.md— 创作进度
- 使用 Glob
<DRAMA_ROOT>/episodes/EP*.md查找已有剧本,Read 最近1-2集恢复剧情上下文
汇报当前状态:
📺 项目:《剧名》
📱 平台:竖屏短剧 / 横屏微短剧
🎭 题材:XX类型
📊 进度:已完成 XX/XX 集
🪝 上集钩子:[上一集结尾悬念]
➡️ 下集预告:[下一集核心冲突]
步骤二:判断当前阶段并执行
根据已有文件判断应进入哪个阶段:
情况 A: 无 project.md → 全新项目
- 进入「阶段一:项目设置」
- 使用 AskUserQuestion 引导用户选择平台类型、题材、集数等
- 完成后自动进入「阶段二:故事大纲」
情况 B: 有 project.md,无 outline.md → 需要写大纲
- 进入「阶段二:故事大纲」
- 参照
references/outline-template.md模板 - 参照
references/genre-templates.md中对应类型的结构
情况 C: 有 outline.md,无 characters.md → 需要设计角色
- 进入「阶段三:角色设计」
- 参照
references/character-template.md模板
情况 D: 有 characters.md,outline.md 中无分集大纲 → 需要写分集大纲
- 进入「阶段四:分集大纲」
- 为每集规划核心冲突和结尾钩子
情况 E: 分集大纲已有,可以写剧本 → 剧本创作
- 进入「阶段五:剧本创作」
- 从 progress.md 确定下一集集号
- 按分集大纲写下一集
步骤三:创作输出
无论处于哪个阶段,完成创作后:
-
保存文件 — 保存到对应路径:
- 大纲 →
<DRAMA_ROOT>/outline.md - 角色 →
<DRAMA_ROOT>/characters.md - 剧本 →
<DRAMA_ROOT>/episodes/EPXXX-标题.md - 分镜 →
<DRAMA_ROOT>/storyboard/EPXXX-分镜.md
- 大纲 →
-
更新进度 — 更新
<DRAMA_ROOT>/progress.md:- 记录完成状态
- 更新伏笔跟踪
- 标注大纲偏离(如有)
- 写下集预告
-
汇报结果 — 附上创作报告:
✅ 已完成:EPXXX《标题》 📊 台词字数:XXXX字 🎬 场景数:X场 🪝 本集钩子:[结尾悬念] ➡️ 下集预告:[下集核心冲突]
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 · 90 lines · 12 tokens per session scan A 0ed41227b275
drama is a command published in the GitHub repository JS-mark/skills (2 stars, last pushed 3mo ago), licensed MIT. It adds 12 tokens to every session and 891 once invoked, about $0.0000 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 2026-08-31.
drama compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| dramaJS-mark/skills | Command | 2 | 3mo ago | MIT | A | 12 | Claude Code |
| checklistgithub/spec-kit | Command | 150k | today | MIT | A | 13 | Claude Code |
| clarifygithub/spec-kit | Command | 150k | today | MIT | A | 27 | Claude Code |
| specifygithub/spec-kit | Command | 150k | today | MIT | A | 13 | Claude Code |
| convergegithub/spec-kit | Command | 150k | today | MIT | A | 35 | Claude Code |
| implementgithub/spec-kit | Command | 150k | today | MIT | A | 14 | Claude Code |
| speckit.bug.fixgithub/spec-kit | Command | 150k | today | MIT | A | 12 | Claude Code |