What is dasheng-video-director?

A video-planning tool that turns scripts or rough material into reviewable shot and scene plans. It plans composition, transitions, sound rules, evidence placement, and review steps rather than rendering the finished video.

It helps plan presenter videos, investigative explainers, voice-led educational videos, digital-human videos, advertisements, and planned short dramas.

It makes the intended structure visible before assets are generated or editing begins. This helps teams check claims, continuity, pacing, and the role of each shot early.

dasheng-video-director — Skill for Claude Code and Codex by leecyno1

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo

git clone --depth 1 https://github.com/leecyno1/boutique-skills

agentmods

npx agentmods add skills/leecyno1/boutique-skills/dasheng-video-director

Made for: Claude Code, 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/leecyno1/boutique-skills/dasheng-video-director/github.svg)](https://agentmods.dev/skills/leecyno1/boutique-skills/dasheng-video-director)

Your own site

<a href="https://agentmods.dev/skills/leecyno1/boutique-skills/dasheng-video-director"><img src="https://agentmods.dev/badge/skills/leecyno1/boutique-skills/dasheng-video-director/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/leecyno1/boutique-skills/dasheng-video-director"><img src="https://agentmods.dev/badge/skills/leecyno1/boutique-skills/dasheng-video-director.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 6,331 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 original No closer match found 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.

Model	Per session	Once invoked
Fable 5.1	$0.00053	$0.06331
Opus 5.5	$0.00021	$0.02532
Sonnet 5.5	$0.00011	$0.01266
Haiku 4.5	$0.00005	$0.00633

Measured 5d ago against content hash fc6954a1d509, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

dasheng-video-director 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 5d 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.

skills/default/dasheng-video-director/SKILL.md · 400 lines

How it starts

The opening of the file, as written. The whole thing — 400 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Newma Video Director

Role

You are the director layer. Your job is to turn content into a reviewable video plan, not to render final media.

This skill sits between roughcut/script intake and material generation:

brief/script -> director scene_plan -> claim/evidence ledger -> storyboard review -> asset build/render

Use this skill for six registered lanes. Read configs/video/director_registry.json first and use the matching director profile:

真人出镜口播：speaker is the trust anchor; evidence, PIP, B-roll, charts, documents, and transitions carry pace.
VOX 调查解释：one central question, evidence map, counterargument, qualified conclusion, Shotcraft/Remotion and generated explanatory shots.
无真人 HTML 科普：voiceover is the timeline; animated HTML scenes carry narration, proof, rhythm, and structure.
AI 数字人：single presenter or dual interview; each presenter source is generated independently and composed by active-speaker turns.
电影短剧：planning only by default; produce screenplay, character/continuity bible and storyboard, but do not call paid external video APIs.
广告宣传片：one objective, one CTA, early product reveal, real product/proof assets, brand memory and multi-aspect safe areas.

All six lanes follow:

素材接收 -> 编剧/口播重写 -> 导演分镜 -> 素材生成 -> 剪辑合成 -> 渲染 -> QC/交付

Required Reading

Before producing a director plan, read:

docs/technical/video-pipeline-governance.md
docs/technical/video-editing-driving-mechanism.md
configs/video/video_editing_driver_rules.json
configs/video/director_feedback_memory.json
configs/video/tool_registry.json
configs/video/director_registry.json
configs/external/reserved_projects.json
configs/video/reference_video_dna_registry.json
~/Desktop/自媒体创作/00_范式学习/视频训练/每日博主自学习/knowledge/index.md when the daily self-learning knowledge base exists
The relevant pipeline manifest:
- configs/video/pipelines/talking_head.yaml
- configs/video/pipelines/vox_explainer.yaml
- configs/video/pipelines/explainer_html.yaml
- configs/video/pipelines/digital_human.yaml
- configs/video/pipelines/cinematic_short_drama.yaml
- configs/video/pipelines/commercial_promo.yaml

Read the full file on GitHub · 400 lines

Files

What ships with it

2 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.

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.

5d ago First seen · 400 lines · 53 tokens per session scan A fc6954a1d509

Subscribe to this mod's changes

dasheng-video-director is a skill published in the GitHub repository leecyno1/boutique-skills (6 stars, last pushed yesterday), licensed MIT. It adds 53 tokens to every session and 6,331 once invoked, about $0.0002 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 2026-11-03.

Creative and media

dasheng-video-director next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
dasheng-video-directorleecyno1/boutique-skills	Skill	6	yesterday	MIT	A	53	Claude Code, Codex
imagegenopenai/codex	Skill	134k	today	Apache-2.0	A	113	Codex
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	yesterday	MIT	A	200	Claude Code, Codex
playwright-climicrosoft/playwright	Skill	100k	yesterday	Apache-2.0	A	19	Claude Code
browser-automationopenclaw/openclaw	Skill	394k	today	MIT	A	36	Claude Code
systematic-debuggingobra/superpowers	Skill	314k	4d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code