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 agentmods add skills/sandyup/comfyui-mcp/directornpx skills add sandyup/comfyui-mcp --skill directorgit clone --depth 1 https://github.com/sandyup/comfyui-mcpWrote 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/sandyup/comfyui-mcp/director)<a href="https://agentmods.dev/skills/sandyup/comfyui-mcp/director"><img src="https://agentmods.dev/badge/skills/sandyup/comfyui-mcp/director.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 | $0.00032 | $0.04897 |
| Opus 5 | $0.00016 | $0.02448 |
| Sonnet 5 | $0.00006 | $0.00979 |
| Haiku 4.5 | $0.00003 | $0.00490 |
Grade A, and why
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 4d 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 — 335 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Director — Story-to-Video Production Pipeline
Overview
The Director skill orchestrates a complete short film production from a text story. It breaks the story into scenes, generates start/end frames for each, creates video clips from frame pairs, and concatenates everything into a final video.
Pipeline: Story Planning → Z-Image Hero + Character Refs → Qwen Edit Chain (all frames) → WAN 2.2 FLF Video Clips → ffmpeg Concatenation
Key architectural decisions:
- 1 hero frame + edit chain for character consistency (NEVER independent Z-Image per scene)
- Inter-scene frame continuity: Scene N's end frame IS Scene N+1's start frame (same image file, no edit gap)
- Character reference images fed into Qwen Edit's extra image slots
- State file persists to disk for context compaction survival
- Each scene is independently retryable without affecting others
clear_vrambetween every model family switch
CRITICAL: Inspect modes + verify every output
This pipeline drives the user's live canvas across many stages, so two habits are non-negotiable:
- Inspect node modes before each render. After loading any pack/template/subgraph and before
panel_run, callpanel_get_graphand check each node'smode. Abypassnode is skipped (passes input through); amutenode and everything downstream don't execute. If the path/branch/switch you need is bypassed or muted, enable it withpanel_set_node_mode(set the wanted nodeactive, the unwanted onebypass/mute). Never assume a switch or route is already active. - Verify the output matches before moving on. Every Phase-N render is a gate: actually LOOK at the produced frame/clip (view it) and confirm it matches the intent BEFORE advancing or reporting progress. If it's wrong, diagnose (wrong prompt path? a bypassed/muted builder or switch? wrong widget? wrong ref image?), fix, and rerun. Do NOT declare a phase done or report progress you haven't verified.
- Confirm VIDEO renders via the filesystem, not /history. For a
VHS_VideoCombine/ LTX / WAN clip, do NOT rely onget_history/get_job_statusto confirm it exists — VHS-style video nodes write the .mp4 but frequently do NOT register an output in ComfyUI's/history(prompt shows done, empty outputs, no error). Confirm the file withlist_output_images(now lists videos too, taggedkind: "video") byfilename_prefix+ fresh mtime, then chain it forward withstage_output_as_input. - Bypass completed stages before queuing the next one. If you build the multi-stage pipeline on ONE canvas (e.g. Krea2 → LTX → WAN) rather than running each phase in isolation, once a stage has run and its output is captured/staged,
panel_set_node_mode(mode:"bypass")that stage's nodes BEFORE youpanel_runthe next stage — otherwisepanel_runre-executes the whole graph and you pay for / wait on already-finished work (a real, costly failure mode). Keep only the active stage live; feed the prior output forward withstage_output_as_input(bypass the producer, feed its captured output to the consumer's loader).
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.
- 4d ago First seen · 335 lines · 32 tokens per session scan A ff9f2598c77e
director is a skill published in the GitHub repository sandyup/comfyui-mcp (1 stars, last pushed 1mo ago), licensed MIT. It adds 32 tokens to every session and 4,897 once invoked, about $0.0002 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
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
chengfeng-cut
剪辑中文口播原素材:逐词转录、词典修字出修字表、五轮扫描找口误与重复、汇总表与重复句子表、打开 Studio 让用户复核、复盘沉淀用户偏好与词典。只产出一份已复核的删词账本,不切媒体、不做字幕、不做分镜动画。用户说剪口播、处理口误、生成口播基础素材、继续剪口播,或确认卡回传 action=returncutreview 时使用。不要用于执行物理剪切、导出剪后视频、单独安装、单独打开工作台或口播分镜成片。.
chengfeng-check-updates
剪辑环境的唯一管理者:就绪检查(skills 是否最新 → Runtime 是否配套)、Skills 更新激活、Runtime 安装与体检。用户说检查更新、安装剪辑环境、装播放器、检查剪辑环境、剪辑环境就绪了吗、配置转录凭证时使用;业务 Skill(剪口播/字幕/画面/导出)第 0 步也引用本 Skill 的就绪检查。不用于剪辑、字幕、画面、导出本身或项目数据迁移。.
infographic-template-updater
Update template catalogs and UI prompts after adding new infographic templates (src/templates/.ts), including SKILL.md template list, site gallery template mappings, and the AIPlayground prompt list.
vox-director
Turn ONE topic into a finished Vox-style paper-collage explainer / ad video, end to end on the Atlas Cloud API + local ffmpeg — script, collage keyframes, motion, voice-over, music, captions, all automated. Use this whenever the user wants a "Vox style" video, a paper/torn-paper collage animation, a "motion collage"…