short-drama-produce

short-drama-produce is a skill for Codex from zenstory-ai/oh-story-dsh. It costs 145 tokens per session (4,098 once invoked), scanned A, a copy of short-drama-produce, MIT.

A production guide that sends already approved short-drama image, video, voice, or music jobs to the configured generation tools.

In plain words
What is it for?
Use it to prepare, preview, confirm, and run selected media-generation jobs, including jobs that use reference images and outputs stored in the project.
Why use it?
It prevents accidental paid runs by previewing the exact job, requiring explicit confirmation, and tracking its source prompts, references, outputs, and run state.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: $skill-name invocation.

Good fit Use it to prepare, preview, confirm, and run selected media-generation jobs, including jobs that use reference images and outputs stored in the project.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/zenstory-ai/oh-story-dsh/short-drama-produce
Install

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.

Any agent
npx skills add zenstory-ai/oh-story-dsh --skill short-drama-produce
Clone the repo
git clone --depth 1 https://github.com/zenstory-ai/oh-story-dsh

Made for: Codex.

Wrote 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.

agentmods badge for short-drama-produce

README.md
[![agentmods](https://agentmods.dev/badge/skills/zenstory-ai/oh-story-dsh/short-drama-produce/github.svg)](https://agentmods.dev/skills/zenstory-ai/oh-story-dsh/short-drama-produce)
Your own site
<a href="https://agentmods.dev/skills/zenstory-ai/oh-story-dsh/short-drama-produce"><img src="https://agentmods.dev/badge/skills/zenstory-ai/oh-story-dsh/short-drama-produce/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.

agentmods 80×15 button for short-drama-produce

Your own site · 80×15
<a href="https://agentmods.dev/skills/zenstory-ai/oh-story-dsh/short-drama-produce"><img src="https://agentmods.dev/badge/skills/zenstory-ai/oh-story-dsh/short-drama-produce.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 145 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,098 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 100% copy Near-identical to another mod in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00145 $0.04098
Opus 5.5 $0.00058 $0.01639
Sonnet 5.5 $0.00029 $0.00820
Haiku 4.5 $0.00015 $0.00410

Measured today against content hash dfeca69609dc, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

short-drama-produce 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 today.

The scan reads SKILL.md. This mod also ships 4 executable files (scripts/fixture_adapter.py, scripts/production_tool.py, scripts/provider_adapters.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Origin

This is a copy

100% identical to short-drama-produce — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

packages/knowledge/drama/skills/short-drama-produce/SKILL.md · 192 lines

How it starts

The opening of the file, as written. The whole thing — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.

确认后生产

本技能把已经写好的生产规格送到运行环境配置的 adapter。图片提示词归 $short-drama-image-prompts,视频提示词归 $short-drama-video-prompts,台词归 $short-drama-write,声音身份归 $short-drama-assets。

Quick Start

只在用户明确要求实际生成后,从当前 图片提示词.md、分镜.md 或 视频提示词.md 中 取出本次提示词,建立一个有边界的运行 job。creator-first job 的 source 必须指向拥有这条提示词的 当前 Markdown,source_entry 必须点名该文档允许的二级标题:图片提示词.md 用 IMG-*, 视频提示词.md 用 MOTION-*,分镜.md 用 SHOT-*(modality 为 image,正文取该镜的 ### 冻结关键帧提示词)。此选择器只提取首帧;尾帧需先由图片提示词阶段建立独立 IMG-* 状态图条目, 再从 图片提示词.md 准备 image job。创作者也可以提供已有起始帧—— 在自己的工具里出图再放进项目同样成立,图片始终不进项目时走分镜的 PLAN-...; 产出落在 剧集/<EP>/制作成果/images/ 后,分镜 owner 才能把它绑成 用途:起始帧 的 REF-...。存在真实参考图时, 还必须逐张填写 reference_bindings 的槽位、顺序、路径、中文名、用途以及允许/禁止控制范围; 建立 job 时按当前文档的 用途 选择供应商 role,写入 reference_bindings[].role; 内置视频 adapter 读取这个 role,只接受已实现的取值 (MiniMax 为 first_frame/last_frame/reference_image/reference_video/reference_audio, Seedance 也接受这五种 role,具体组合依账号配置的型号而定);带参考图却没有绑定的 job 会直接失败,不猜测 role。 本地图片由内置 adapter 按 base64 data URI 直接送出,不需要自建上传服务。 MOTION-* 的「参考音频」行同样逐条进 reference_bindings,排在图片之后、role 固定为 reference_audio、character 照抄该行的 角色; adapter profile 没有声明接受 reference_audio 时 run 在提交前失败,见 adapter-contract.md。 需要把条目中的 PLAN-... 图片作为生成输入时,prepare 会要求先把真实文件放进项目、改写成 REF-...。直接从 分镜.md 绘制该 SHOT 自身首帧时,选择器可跳过 PLAN 槽位,因为本次生成 使用冻结关键帧正文,不发送创作者在项目外准备的那些图片;已有 REF 绑定仍须逐项一致。 这项豁免要求跳过 PLAN 后剩余 REF 的顺序仍从 1 连续;否则先交分镜 owner 调整源声明顺序, 不能只在 job 中重编号。生产接口还要求参考路径唯一:创作上同一图片可有两个用途槽位,但同路径 双槽目前不能提交。由负责技能与创作者决定修订参考职责或等待接口支持,不在 job 中擅自合并或漏槽。 references 可以省略并由绑定顺序生成,也可以作为相同顺序的显式镜像。输出放在 剧集/<EP>/制作成果/;这个 job 是生产工具的临时输入,不是第六份创作文档:

python3 {技能目录}/scripts/production_tool.py prepare <project> --job <临时-job.json>

先展示 prepare 的完整预览;此时不会调用供应商。

硬闸门

每次生产都必须经过以下四步,顺序不可合并:

  1. 建立一个有边界的 job:一种 modality、明确数量、完整 prompt/spec、参考文件、参数、输出路径和 adapter profile。
  2. 运行 prepare,把返回的完整预览展示给创作者,尤其是数量、prompt、source entry、 reference bindings、references、outputs、overwrite 与 adapter。creator-first job 会在这一步机械核对 所选标题里的可复制提示词,以及参考图槽位、顺序、路径、中文名和控制边界;任一漂移都 fail closed。
  3. 等创作者在看到这份预览之后明确确认。只有明确同意这项当前任务,才运行 confirm; “继续”“都做完”“预算没问题”、上游内容已接受或之前确认过另一版,都不算本次生产确认。
  4. 运行 run。它会在启动 adapter 前消费一次确认;成功或失败后再次执行都必须重新确认, 防止失败重试意外产生第二笔费用。

Read the full file on GitHub · 192 lines

Changes

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.

  1. today Changed · +2 lines dfeca69609dc
  2. 12d ago Changed · +1 lines 5172f57e616e
  3. 24d ago Changed · +5 lines 25ba8c429480
  4. 1mo ago Changed · +4 lines 90716253be3e
  5. 1mo ago Changed · +21 lines 8e664f0a3a59
  6. 1mo ago Changed · +20 lines 9eb35a905f94
  7. 1mo ago First seen · 139 lines · 145 tokens per session scan A e52a4775fe70

Subscribe to this mod's changes

short-drama-produce is a skill published in the GitHub repository zenstory-ai/oh-story-dsh (629 stars, last pushed today), licensed MIT. It adds 145 tokens to every session and 4,098 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to short-drama-produce, differing in 0 lines, and is treated as a copy.