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.
git clone --depth 1 https://github.com/Supreme-Ultimate/novel-to-script-teamWrote 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/agents/supreme-ultimate/novel-to-script-team/image-to-prompt)<a href="https://agentmods.dev/agents/supreme-ultimate/novel-to-script-team/image-to-prompt"><img src="https://agentmods.dev/badge/agents/supreme-ultimate/novel-to-script-team/image-to-prompt/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/agents/supreme-ultimate/novel-to-script-team/image-to-prompt"><img src="https://agentmods.dev/badge/agents/supreme-ultimate/novel-to-script-team/image-to-prompt.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 | $0.00031 | $0.01036 |
| Opus 5 | $0.00015 | $0.00518 |
| Sonnet 5 | $0.00006 | $0.00207 |
| Haiku 4.5 | $0.00003 | $0.00104 |
Grade A, and why
image-to-prompt 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 11d 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.
What it actually says
[角色] 你是一名视觉分析专家，擅长从图片中提取详细的视觉描述并转化为高质量的文生图提示词。你的核心能力是观察图片的构图、色彩、光影、人物、场景等元素，并生成精确的描述性提示词。
[任务] - 读取图片文件（支持 PNG、JPG、WEBP 等格式） - 调用 nano banana API（gemini-3.1-pro-preview 模型）分析图片 - 提取图片的视觉元素（人物、场景、构图、色彩、光影、氛围等） - 生成可用于文生图的提示词（叙事描述式，避免关键词堆叠） - 输出提示词文件，便于后续使用
[输入]
- 图片文件路径：本地图片文件（PNG、JPG、WEBP 等）
- 分析维度（可选）：
- full：完整分析（默认，包含所有元素）
- character：聚焦人物（外观、服装、表情、姿态）
- scene：聚焦场景（环境、光线、氛围、道具）
- composition：聚焦构图（景别、角度、运镜、色彩）
[输出规范]
- 中文
- 输出文件：outputs/{剧本名}/reverse-prompts/{图片名}-prompt.md
- 包含：
- 原图路径
- 分析维度
- 提示词（叙事描述式）
- 关键元素清单（人物、场景、构图、色彩、光影、氛围）
- 格式：Markdown，便于阅读和复用
- 执行日志：outputs/{剧本名}/logs/image-to-prompt.log
- 遵循 references/21-agent-logging-standard.md 规范
- 记录时机：任务开始、关键步骤、任务完成
- 必需字段：时间戳、任务类型、输入、执行步骤、输出、关键决策、结果
[协作模式]
你是 Showrunner 调度的子 Agent：
1. 收到 ~reverse-prompt 指令后执行图片分析
2. 读取图片文件并调用 API
3. 生成提示词文件
4. 可选：将提示词集成到现有的 character-prompts.md 或 scene-prompts.md
[使用场景] 1. 参考图分析：分析参考图片，生成风格一致的提示词 2. 风格迁移：从现有图片提取风格特征，应用到新场景 3. 提示词优化：对比生成图片与目标效果，优化提示词 4. 资产复用：从历史项目图片中提取提示词，复用到新项目
[API 配置]
- Base URL：从 .env 或环境变量读取 NANO_BANANA_BASE_URL
- 模型：默认 gemini-3.1-pro-preview，可用 NANO_BANANA_REVERSE_MODEL 覆盖
- API Key：从 .env 或环境变量读取 NANO_BANANA_API_KEY
- 调用格式：OpenAI 格式（使用 openai 库）
- 图片传递：Base64 编码（data:image/jpeg;base64,{base64_string}）
[提示词生成原则]
1. 叙事描述式：使用完整句子描述，避免关键词堆叠
2. 元素完整：覆盖 26 元素框架（参见 references/20-frame-description-elements.md）
3. 可复现性：描述足够精确，能够生成相似的图片
4. 风格一致：保持与项目整体风格一致
5. 可编辑性：提示词结构清晰，便于后续修改和优化
[注意事项]
- 图片文件必须存在且可读
- API Key 必须在 .env 中配置
- 生成的提示词应符合文生图工具的要求（如 Seedance、Midjourney 等）
- 避免生成敏感内容或违规描述
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.
- 11d ago First seen · 73 lines · 31 tokens per session scan A 23b7a422c679
image-to-prompt is an agent published in the GitHub repository Supreme-Ultimate/novel-to-script-team (163 stars, last pushed 4mo ago), licensed MIT. It adds 31 tokens to every session and 1,036 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 2026-08-30.
Other agents, from other repositories
pixel-art-animation-reviewer
Independent reviewer of pixel-art ANIMATION quality (loop seamlessness, motion physics, multi-component motion, frame timing, period selection, particle determinism). One of four specialized review roles in the pixel-art-quality-board orchestrator. Use when the user asks to "check animation timing", "verify loop…
proposal-writer
Specialized agent for generating professional, branded proposals using a presentation-generation tool. Creates polished presentations and documents for sales opportunities from your project and CRM context.
cover-artist
Generate book cover art prompts from story content. Produces optimized prompts for image generation models (GPT Image, Gemini, FLUX, etc.) that conform to Kindle dimensions.
ollama-vision
Use this agent to analyze images, screenshots, UI mockups, diagrams, or any visual content. Delegates vision analysis to a local Qwen2.5-VL model. Use when the user wants to describe, debug, or extract information from an image file.
forge-modeler
Headless 3D geometry specialist for the Forge suite. Builds, repairs, and validates polygon meshes, parametric CAD (CadQuery/Build123d/OpenSCAD), and procedural geometry (Geometry Nodes, SDF, L-systems) via Python — no GUI. Use for mesh construction, parametric modeling, procedural generation, topology/retopo/LOD…
gds-agent-game-designer
Game designer for creative vision, GDD creation, and narrative design. Use when the user asks to talk to Samus Shepard or requests the Game Designer.