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.
npx skills add ouyangevan/codex-short-drama-pipeline-skill --skill short-drama-pipelinegit clone --depth 1 https://github.com/ouyangevan/codex-short-drama-pipeline-skillWrote 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/skills/ouyangevan/codex-short-drama-pipeline-skill/short-drama-pipeline)<a href="https://agentmods.dev/skills/ouyangevan/codex-short-drama-pipeline-skill/short-drama-pipeline"><img src="https://agentmods.dev/badge/skills/ouyangevan/codex-short-drama-pipeline-skill/short-drama-pipeline/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/skills/ouyangevan/codex-short-drama-pipeline-skill/short-drama-pipeline"><img src="https://agentmods.dev/badge/skills/ouyangevan/codex-short-drama-pipeline-skill/short-drama-pipeline.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 | $0.00053 | $0.03879 |
| Opus 5 | $0.00026 | $0.01939 |
| Sonnet 5 | $0.00011 | $0.00776 |
| Haiku 4.5 | $0.00005 | $0.00388 |
Grade A, and why
short-drama-pipeline 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 12d 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 — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Short Drama Pipeline
Purpose And Boundary
Run a repeatable AI short-drama production pipeline with source-backed rules, stable assets, professional direction, and hard delivery gates.
Use this skill only for explicit short-drama production work. For ambiguous requests, one-off prompts outside a short-drama project, high-tech premium videos, or external creative-agent platforms, read the relevant section of references/boundaries.md.
Core Contract
- Identify the current stage and whether the request is a lightweight
prompt_test_mode=trueexperiment or normal production. - Follow the conservative source policy and stage reading route below before substantive work.
- Reuse a valid stage cache and audit when upstream facts and rules have not changed.
- Apply the three delivery gates. Never present failed or unverified output as usable.
- Continue through the requested stage or finished-output workflow; stop only for a real blocker or required approval.
For normal production, read references/operations.md sections Source Discipline, Delivery Gate Contract, and Hard Gates once at project/session startup and reuse them while unchanged.
Conservative Source Policy
The compiled cache is the first stable rule layer, not a quality downgrade.
prompt_test_mode=true: read only the relevantknowledge_compiled/files by default. Read targeted reference sections when the cache is insufficient, the test is complex, a rule conflicts, or the result is being promoted to production.- Normal production: read the relevant compiled files and every stage-specific reference section listed in the routing table. Do not omit a listed section. Read linked or adjacent sections too when the current artifact depends on them.
- Formal generation or delivery: also read the relevant blocker sections from
references/qc-gates.md. - Raw or external teaching-material search is allowed only on cache miss, conflict, new material, user-requested relearning, or missing rule coverage.
What ships with it
30 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 278 B
- core/combat/combat_camera_coverage.md 1.3 KB
- core/combat/combat_grammar.md 2.1 KB
- core/combat/combat_prompt_assembler.md 5.9 KB
- core/combat/combat_qc.md 3.2 KB
- core/combat/fight_director_layer.md 3.9 KB
- core/combat/impact_system.md 1.5 KB
- core/combat/power_escalation_system.md 1.1 KB
- core/combat/style_routes.md 1.5 KB
- core/combat/vfx_power_system.md 1.4 KB
- examples/combat/2d_ink_weapon_clash.json 8.8 KB
- examples/combat/3d_guoman_avatar_suppression.json 11 KB
- examples/combat/fast_route_single_impact.json 6.6 KB
- examples/combat/full_fight_sequence_8_shots.json 79 KB
- examples/combat/live_action_close_quarters_exchange.json 9.1 KB
- knowledge_compiled/anime_fight_rules.md 7.1 KB
- knowledge_compiled/camera_rules.md 1.9 KB
- knowledge_compiled/common_failure_cases.md 5.5 KB
- knowledge_compiled/prompt_rules.md 5.7 KB
- knowledge_compiled/seedance_rules.md 9.5 KB
- product/combat_canvas_integration.md 1.8 KB
- providers/seedance.md 2.4 KB
- references/boundaries.md 4.4 KB
- references/operations.md 28 KB
- references/project-package.md 33 KB
- references/prompt-rules.md 49 KB
- references/qc-gates.md 36 KB
- references/workflow.md 57 KB
- schemas/combat_prompt_compiler_output.schema.json 17 KB
- schemas/combat_prompt_compiler_sequence.schema.json 1.3 KB
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.
- 12d ago First seen · 233 lines · 53 tokens per session scan A 3360d541a25d
short-drama-pipeline is a skill published in the GitHub repository ouyangevan/codex-short-drama-pipeline-skill (4 stars, last pushed 1mo ago), licensed MIT. It adds 53 tokens to every session and 3,879 once invoked, about $0.0003 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 skills, from other repositories
lanshu-create-ai-presenter-video
Turn a topic or finished script plus an authorized adult presenter image into a complete, publish-ready AI presenter video. Use for new presenter videos and for continuing, revising, captioning, lip-sync repairing, or re-exporting an existing presenter-video job. Keep model and provider selection capability-based and…
seedance-2-5-video-director
Design, derive, optimize, diagnose, and rewrite scripts or copy-ready prompts specifically for Dreamina/即梦 Seedance 2.5. Use for new text/image/video/audio-to-video concepts, exact-timeline videos, 30-180-second Long Video, extension, video editing, Clay Renderer, seamless transitions, multi-grid storyboards…
script-to-shootable-storyboard
A guide for turning scripts, story outlines, dialogue, or existing storyboards into detailed shot plans. A storyboard is a sequence of planned camera shots showing what viewers see and hear.
auto-video
Run and validate AutoVideo-Agent Markdown-to-video workflows, including the v0.1-compatible deterministic offline command and v0.2 provider mode with ComfyUI media, Mock or Command TTS, scene-level SRT, normalized timelines, FFmpeg, and deterministic QA. Use for build, plan, provider, or QA requests; MiniMax, hosted…
seedance-2-5-prompt-director
A skill for writing and improving prompts for Seedance 2.5, a video-generation system. It covers text-to-video, image-to-video, editing, video extension, references, camera movement, green-screen work, sound, and lip sync.
ai-short-drama
A structured process for creating short AI dramas, from story and reference images through storyboard frames and finished episodes. It includes guidance for image prompts and common generation failures.