Raven is an open-source agent harness for running long-term AI work with terminal execution, tracing, memory, skills, evaluation, and reusable workflows. People use the current release to operate and improve persistent AI workflows, while its described future direction is a multi-agent system that combines specialized harnesses.
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 EverMind-AI/Raven --skill create-illustrations-and-scenesgit clone --depth 1 https://github.com/EverMind-AI/RavenWrote 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/evermind-ai/raven/create-illustrations-and-scenes)<a href="https://agentmods.dev/skills/evermind-ai/raven/create-illustrations-and-scenes"><img src="https://agentmods.dev/badge/skills/evermind-ai/raven/create-illustrations-and-scenes/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/evermind-ai/raven/create-illustrations-and-scenes"><img src="https://agentmods.dev/badge/skills/evermind-ai/raven/create-illustrations-and-scenes.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 | $0.00113 | $0.03979 |
| Opus 5.5 | $0.00045 | $0.01592 |
| Sonnet 5.5 | $0.00023 | $0.00796 |
| Haiku 4.5 | $0.00011 | $0.00398 |
Grade A, and why
create-illustrations-and-scenes 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 1mo 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 — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
创作插画与视觉场景
本 Skill 是 visual-artifact-design 的插画领域层,拥有路由、专业 gate、能力需求、claim ceiling 和
失败返回;通用合同、工具事实、authority graph、渲染、review、promotion 与交付沿用共享底座。
需要选择构图、媒介模式或诊断画面时读取 patterns.md;需要比较专业工具能力时读取 tool-profiles.md。候选名称不证明工具可用或已使用。
本 Skill 保持介质中立:先锁定最终消费者、自然媒介、真实观看/播放环境和最终验收,再决定
画布、母版、导出与证据。只有最终消费者是 Web 或合同明确要求用户侧网页交付时,才加载
$build-polished-visual-frontends;网页若只是查看器、内部预览或证据索引,不构成加载理由。
非网页媒介不能用浏览器截图、DOM 或网页渲染冒充目标消费者证据,必须在实际印刷、原生应用、
播放器、展陈、设备或约定 renderer 中检查最终像素、时间表现和使用条件。
1. 领域路由
当去掉标题、标签和控件后,画面中的主体、动作、空间、氛围或隐喻仍承担主要价值时, 以本领域为主。先选一个主子型:
- 编辑/概念插画:用具体画面回应议题或表达抽象关系;
- 叙事场景:让事件、因果、阻力、结果和环境反应可见;
- 角色、群像与生物:用身体、剪影、表演和关系建立身份;
- 环境与世界观:用地点、尺度、气候和生活痕迹建立场所;
- 物件与自然主体:以轮廓、连接、材质和观察角度说明对象;
- 动画场景:时间变化、表演或镜头运动本身承担叙事;
- 抽象/程序化:用可解释的形状关系、规则或参数表达非具象命题。
若长期识别、独立符号、传播转化、版面阅读、精确数值/结构/位置、可操作工作流、 交互解释或游戏规则才是主要价值,路由到相应领域;插画仅作为其资产时,本 Skill 只拥有该资产的画面 claims,不拥有外层系统。SVG、HTML、3D 或动画格式不决定领域。
2. 领域接口
Scope 与 claims
在共享合同中增加:任务模式、视觉命题、主子型、最终消费者、自然媒介、观看距离、 版位/镜头、必须读出的对象与关系、允许省略项、事实/表现边界、真正需要的消费者变体, 以及每个消费者的最终验收方法。对象数量、草图数量、读者人数和比例数量不得作为通用 质量阈值;按 claim、风险与消费环境生成验证计划。
把 claims 分开记录:首读叙事、构图层级、动作/接触/受力、空间连续、光色一致、
媒介真实性、跨载体重构、母版可编辑性、来源/许可和动画连续性。未测试的 claim
必须进入 not_evidence_for 或 excluded_claims,不能由邻近 claim 外推。
先声明 Create / Edit / Diagnose / Audit。Audit 复用 Diagnose 的只读语义,只扩大核对范围,
不获得写入、制作或补证权限。Create/Edit 的正式制作只写用户授权范围;若为证明专业工具的
可编辑性、重开或导出能力而需要额外写入,只能在授权 workspace 从输入建立一个一次性验证
副本,操作前记录输入 hash,操作后记录副本与输出 hash,并保持原输入不变。
Diagnose/Audit 一律零写入:不创建验证副本,不保存、导出、重建、改元数据或更新缓存;
只核对既有母版、交付、记录和 hash,无法只读证明的能力如实标为未验证,不为补证计算或登记
新的 proof/build/output hash。proof 与最终交付的母版、派生输出 hash 分别记录;proof 不得
改变 canonical、release 或 promotion。
Authority
为构图与场景几何、角色/物件设计、光色、外部资产、时间/镜头和消费者变体分别指定 唯一 authoritative owner。选定工具的原生项目或不可拆分的版本化 bundle 是对应 concern 的 master-of-record;扁平图、视频、网页查看器、截图和 Gallery 缓存都是 derived。 混合制作可以有多个母版,但同一 concern 不得双主;修改 derived 时返回其 owner。
Tool selection
Create/Edit 先完成构图、动作、空间和叙事的低成本证明,再锁生产工具与母版;Diagnose/Audit
只核对已有证明,缺失时标为未验证,不制作证明。按
任务子型 → 所需能力 → Registry 候选 → 选择理由 → 原生模型 → 权威母版 → 导出
选择;工具一旦选定,其图层、节点、相机、时间线、资产链接或参数系统必须成为制作语言。
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.
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.
- 1mo ago First seen · 199 lines · 113 tokens per session scan A f0666dc3a290
create-illustrations-and-scenes is a skill published in the GitHub repository EverMind-AI/Raven (5,463 stars, last pushed today), licensed Apache-2.0. It adds 113 tokens to every session and 3,979 once invoked, about $0.0005 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 2026-09-12.
Other skills, from other repositories
dcf-model
Build discounted cash flow valuation workbooks in Excel.
comps-analysis
Build comparable-company valuation workbooks in Excel.
anatomy
Explain an idea as an interactive isometric machine figure.
mcp-oauth-remote-gateway
Manual OAuth for remote MCP servers on headless gateways.
p5js
Use when users request: p5.js sketches, creative coding, generative art, interactive visualizations, canvas animations, browser-based visual art, data viz, shader effects, or any p5.js project.
honcho
Configure and troubleshoot Honcho memory for Hermes.