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 62656456/ai-film-skills --skill director-agentgit clone --depth 1 https://github.com/62656456/ai-film-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/skills/62656456/ai-film-skills/director-agent)<a href="https://agentmods.dev/skills/62656456/ai-film-skills/director-agent"><img src="https://agentmods.dev/badge/skills/62656456/ai-film-skills/director-agent/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/62656456/ai-film-skills/director-agent"><img src="https://agentmods.dev/badge/skills/62656456/ai-film-skills/director-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00188 | $0.05825 |
| Opus 5 | $0.00094 | $0.02913 |
| Sonnet 5 | $0.00038 | $0.01165 |
| Haiku 4.5 | $0.00019 | $0.00583 |
Grade A, and why
director-agent 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 — 411 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Director Agent
This skill is the screenplay-and-director decision brain, not the final shot-list engine. In script mode its first duty is to tell a complete, understandable story through believable character actions and purposeful dialogue. State, causality, and cold-read tools verify that story after the writing logic is clear; they do not replace storytelling. In director mode it decides how an already coherent story should be interpreted, visualized, performed, sounded, paced, and prepared for a storyboard.
For serious director analysis or pre-storyboard planning, read references/verified-director-logic.md. Use it as a decision scaffold; do not invent film history, director methods, textbook claims, or named examples.
For script creation, script revision, script diagnosis, scene repair, or dialogue work, read references/screenplay-writing-core.md first. Every writing rule needed by that workflow is bundled locally. For substantial or explicitly high-quality screenplay work, also read references/screenplay-exemplar-benchmarks.md. Draft from the plain-language story, character behavior, and dialogue-purpose logic; then use references/screenplay-state-engine.md as the verification layer. Do not let a ledger or checklist generate the story.
When the user explicitly needs an AI-video/AI-comic executable screenplay, prompt-ready action text, or repair of model-confusing action, read references/screenplay-ai-execution-compiler.md only after the readable story has passed the writing and state checks. Preserve the human-readable screenplay as the semantic master; compile a separate execution layer instead of forcing subject repetition, dense movement instructions, or model-facing syntax into every screenplay.
For an independent screenplay audit, use a fresh reader or isolated context only when that capability is explicitly available and allowed. Give it only references/screenplay-cold-read-protocol.md, the raw script, the user's locked constraints, and necessary format information. Otherwise run the same protocol in the current context, label the result SELF-AUDIT ONLY, and never present it as independent evidence.
When the user explicitly wants a full AG-CLIP storyboard, shot list, or generation-ready分镜 and the director layer is unresolved, this Skill first creates a complete DIRECTOR_PLAN, then uses references/production-storyboard-compiler.md to deliver the full production storyboard and prompt package in the same run. If the task is only shot expansion from an already approved plan, this Skill is not the matching entrypoint.
What ships with it
14 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 268 B
- references/anti-laziness-contract.md 5.6 KB
- references/director-thinking-spine.md 2.7 KB
- references/director-workbench-protocol.md 10 KB
- references/github-project-watchlist.md 5.6 KB
- references/local-knowledge-map.md 3.2 KB
- references/production-storyboard-compiler.md 4.4 KB
- references/research-update-protocol.md 4.6 KB
- references/screenplay-ai-execution-compiler.md 8.9 KB
- references/screenplay-cold-read-protocol.md 14 KB
- references/screenplay-exemplar-benchmarks.md 7.3 KB
- references/screenplay-state-engine.md 14 KB
- references/screenplay-writing-core.md 11 KB
- references/verified-director-logic.md 10 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.
- 4d ago Changed · +12 tokens per session 6c0341cdbd6b
- 7d ago Changed · +12 lines · -18 tokens per session 9bc6bc147270
- 12d ago First seen · 399 lines · 194 tokens per session scan A 3d8017c68555
director-agent is a skill published in the GitHub repository 62656456/ai-film-skills (17 stars, last pushed yesterday), licensed Apache-2.0. It adds 188 tokens to every session and 5,825 once invoked, about $0.0009 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
seedance-20
This skill should be used when creating, improving, or troubleshooting Seedance 2.0 video on any surface — Dreamina, Jimeng, CapCut, Doubao, Volcengine/Ark, BytePlus, Runway's Seedance route, fal, or third-party provider/router surfaces such as EvoLink, OpenRouter, Kie.ai, PiAPI, LaoZhang, Runware, ModelsLab, AI/ML…
seedance-prompt
This skill should be used when the user asks to write, improve, translate, compress, or debug a Seedance 2.0 video prompt; mentions T2V, I2V, V2V, R2V, camera direction, prompt quality, or provides reference assets for a production-ready prompt.
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.
travel-skill
A production guide for realistic travel-promotion videos that combine authorised real footage with AI-generated shots.
minimax-h3
Write, debug and structure prompts for MiniMax H3 video generation (T2VA, I2VA, FL2VA, L2VA, Ref2VA) and configure its ComfyUI workflow. Use when the user mentions MiniMax H3, minimaxh3, fl2va, ref2va, MiniMaxH3ReferenceToVideo, reference-to-video, asks to animate a photo, write a video prompt, pick a model quant, or…
minimax-h3-prompting
Guide an idea into a generation-ready MiniMax H3 / Hailuo H3 prompt or diagnose an inspected H3 output. Use for T2VA, I2VA, FL2VA, L2VA, or Ref2VA; text-only PV and kinetic type, Motion Design/MG, packaging and transitions, product/UI/game/MV/title work, localized reality-to-hand-drawn edits, audio/timbre reference…