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 noir-designgit 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/noir-design)<a href="https://agentmods.dev/skills/62656456/ai-film-skills/noir-design"><img src="https://agentmods.dev/badge/skills/62656456/ai-film-skills/noir-design/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/noir-design"><img src="https://agentmods.dev/badge/skills/62656456/ai-film-skills/noir-design.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 | $0.00070 | $0.03016 |
| Opus 5 | $0.00035 | $0.01508 |
| Sonnet 5 | $0.00014 | $0.00603 |
| Haiku 4.5 | $0.00007 | $0.00302 |
Grade A, and why
noir-design 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
黑色类型视觉设计预设
独立执行细则：
references/COMMON-12-SECTION-PROTOCOL.md；色值来源：references/SOURCE-LEDGER.md。
0. 加载规则与映射表
确认当前任务需要此类型视觉参数 → 先执行本包画面关系判断 → 读第2–4节最小参数包 → 分镜/视频任务按需读第1、5–7、11节 → 挂接资产合同 → 按媒介使用10段式对应字段 → 第8节质检与第9节按成像方式选择负向 → 输出。映射：1→①④，2→⑤，3→②，4→⑦，5→③，6→⑥，7→①–⑩，8–9→质检/⑩，10→平台接口，11→⑧⑨。
设计、改写或诊断画面/提示词时，先读本包 电影画面关系判断，锁定画面命题、注意力和成像方式，再选预设；编号、来源或字段查询不必加载。色表、焦段、光比、饱和度和时间线均为可选起点，不覆盖用户锁定，也不代表原图实测参数。
1. 镜头语言预设 → ①④
| 任务 | 景别/焦段 | 构图 | 运动 |
|---|---|---|---|
| 关系/对话 | 可从MCU/CU、50–85mm起步，按关系与空间调整 | 平视、过肩或其他有目的的视点；轴线可追溯 | 按注意力和关系变化选择固定、单项或复合运镜 |
| 空间建立 | 可从EWS/WS、24–35mm起步，按空间信息调整 | 有用的尺度参照、纵深与遮挡 | 按揭示顺序选择固定、单项或复合运镜 |
| 信息变化 | 可从CU、65–100mm起步，按信息载体调整 | 主次注意力明确、遮挡可控 | 按信息出现时机选择运动与切点，不预定速度或方向 |
IF 对话 THEN 按人物关系、注意力和空间变化决定固定或运动；推、拉、绕行、变焦及复合运动须有明确目的与可执行路径；IF 建立 办公室、雨巷、审讯室、酒吧、住宅、码头 THEN 先给尺度和人物占比；IF 动作升级 THEN 比较连续调度与切镜能否清楚表达因果，再决定节拍；复杂运动写清起止、路径、速度、触发与衔接，不预设必须内切。禁止无依据的轴线漂移、无动机机位和错误高度关系。
2. 色彩八要素预设 → ⑤
预设依据与证据边界见本包 references/SOURCE-LEDGER.md；下表是悬疑与犯罪色彩关系的可选设计起点，并非经过逐项实测的类型定律。
| 主/辅/强调色 | 饱和度 | 光源 | 光比 | 区域分配 |
|---|---|---|---|---|
| 深蓝 #00008B；冷灰黑；暗金 #B8860B | 20–35%，暗部可读而非死黑 | 台灯、百叶窗、钠灯等实用光；高反差 | 按场景显式标 3:1/6:1/10:1 等 | 前景材质、中景主体、背景纵深分别指定 |
已有色值可从本包来源账本选择；用户锁定或新方案需要其他颜色时可另行设计，并标明属于设计选择。强调色按当前注意力与情绪关系分配；光色须有可解释的光源位置、遮挡和反射路径，光源可以在画外。
3. 场景色彩速查 + 空间结构模板 → ②
场景范围：办公室、雨巷、审讯室、酒吧、住宅、码头。
左侧：[固定建筑/遮挡/主光来源]；中部：[人物关系/可通行区域]；右侧：[出口、纵深或危险信息]。
前景：[遮挡/材质]；中景：[Cxx、Sxx、Pxx]；背景：[尺度锚点、雾或实用灯]。
人物锁定左右位置、身高、朝向和距离；Pxx 记录持有人、可见面、朝向与最终状态。
3.1 场景参数表
| 场景 | 主色 | 辅色 | 强调色 | 光源 | 色温 | 饱和 | 光比 | 情绪 |
|---|---|---|---|---|---|---|---|---|
| 办公室 | 冷灰黑 | 深棕 | 暗金 #B8860B | 台灯/百叶窗 | 3200K | 25% | 10:1 | 腐败 |
| 雨巷 | 深蓝 #00008B | 湿灰 | 钠灯暖黄 | 路灯/雨反射 | 3600K | 25% | 10:1 | 危险 |
| 审讯室 | 冷灰黑 | 暗青 | 顶灯白 | 顶灯 | 4500K | 15% | 12:1 | 压迫 |
| 酒吧 | 暗金 #B8860B | 深褐 | 暗红 | 吧台灯 | 2800K | 30% | 8:1 | 暧昧 |
| 住宅 | 暖灰 | 深蓝 #00008B | 台灯黄 | 窗光/台灯 | 3200K | 25% | 6:1 | 疑虑 |
| 码头 | 冷蓝 | 黑 | 钠灯黄 | 路灯/船灯 | 4000K | 20% | 10:1 | 孤立 |
空间模板仍遵循：左/中/右固定锚点 + 前/中/后景深 + 人物站位与高度关系 + Pxx 面向/状态。
What ships with it
5 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.
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 · +2 lines 19b8d4e3d2e7
- 7d ago Changed 16e8a886ba99
- 12d ago First seen · 140 lines · 70 tokens per session scan A 026e36ef83a3
noir-design is a skill published in the GitHub repository 62656456/ai-film-skills (17 stars, last pushed yesterday), licensed Apache-2.0. It adds 70 tokens to every session and 3,016 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
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…