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-maps-and-spatial-plansgit 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-maps-and-spatial-plans)<a href="https://agentmods.dev/skills/evermind-ai/raven/create-maps-and-spatial-plans"><img src="https://agentmods.dev/badge/skills/evermind-ai/raven/create-maps-and-spatial-plans/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-maps-and-spatial-plans"><img src="https://agentmods.dev/badge/skills/evermind-ai/raven/create-maps-and-spatial-plans.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 | $0.00112 | $0.02766 |
| Opus 5 | $0.00056 | $0.01383 |
| Sonnet 5 | $0.00022 | $0.00553 |
| Haiku 4.5 | $0.00011 | $0.00277 |
Grade A, and why
create-maps-and-spatial-plans 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 today.
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 — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
创建地图与空间规划
核心目标
让用户依靠空间关系做出正确判断或行动。空间事实、分析、制图样式和产品界面分别由合适工具承担， 再通过同一数据与视觉语言组合；手绘折线不能替代路网，专业地图也不能嵌进另一套随意 UI。
按以下顺序工作：
空间任务 → 来源与空间模型 → 分析/路网工具 → 制图母版与 Style
→ 产品视觉系统 → 代表地图 → Web/印刷等终态
本 Skill 拥有空间数据、网络、分析、制图和介质派生。最终由浏览器消费时，与
$build-polished-visual-frontends 组合；它负责产品外壳、控件和 Web 工程，本 Skill 继续拥有地图
source、layer、style、路线和空间 claim。通用渲染、review 与交付沿用 $visual-artifact-design。
1. 先确认任务真由空间关系驱动
只选一个主子型，其他子型作为依赖：
| 主子型 | 用户依赖的空间真相 |
|---|---|
| 定位与参考 | 范围、位置、方向、地名层级与参照物 |
| 导航与路线 | 合法起终点、连续有向网络、连接、成本和限制 |
| 专题与分区 | 区域几何、量纲、分类、缺失、时间和来源 |
| 服务区与空间分析 | 网络或空间方法、成本、阈值、阻隔、孔洞和边界 |
| 场地与规划 | 边界、单位、现状/方案、尺寸、流线、限制和版本 |
| 楼层与室内 | 本地坐标、楼层、门/走廊、跨层连接和观察方向 |
去掉真实位置、邻接、方向、范围或可达性后任务仍成立，转技术图；主要比较数值、排名或趋势，转数据 可视化；持续搜索、编辑和调度对象时，产品 Skill 拥有工作流，本 Skill 只拥有空间引擎和地图真相。
先记录：world_state: observed | proposed | simulated、空间模型、范围、单位、消费者、媒介、数据日期、
允许结论和最危险误读。公共导航、无障碍、安全、疏散、施工、产权、测量或合规要求必须明确证据
边界；作者自检不能替代现场或合格专业判断。
2. 分开空间事实、分析、制图与界面
每项职责只有一个主要负责人：
来源与观测 → 空间要素/CRS/单位 → 网络与分析 → 制图 Style
↓
Web、PDF、印刷或标牌布局
坐标、几何、路线、服务区、距离和分类从上游母版单向派生。HTML、SVG、Canvas、截图和手写文案不能 反向创造空间事实；显示层不得移动入口、拉直路线、补画连接或重写距离来获得更漂亮的构图。
来源、许可、CRS、参数、hash、算法验证和工具比较属于内部 evidence。最终地图只显示用户理解和行动 所需的来源日期、方法、单位、限制与未知，并贴近受影响图层、路线或结论；详细审计按需展开，不做成 侧栏卡片墙、巨幅横幅或重复告示。
3. 按职责选择专业工具
先选择空间/分析工具，再选择制图母版和成熟 Style，最后选择产品视觉系统。地图渲染器并不自动 提供好看的地图，组件库也不能决定道路层级、标签、图例和服务区表达。
| 职责与约束 | 优先考察 |
|---|---|
| Web 矢量地图、缩放、图层、相机和要素状态 | MapLibre GL JS |
| 复杂投影、多源 GIS 与编辑 | OpenLayers；简单小型地图才考虑 Leaflet |
| 成熟地图视觉起点 | 经许可的 MapTiler/CARTO/组织 Style；离线时固定并本地化 Style、sprite、glyph 和数据 |
| 大规模点、弧线、热区或 GPU 空间叠加 | deck.gl，只有数据量和图层需求成立时 |
| 离线瓦片分发 | PMTiles 或项目已有受控瓦片方案 |
| CRS、几何处理、空间连接和自动 QA | GDAL、GeoPandas/Shapely 或现有 GIS 管线 |
| 有限冻结路网和可审计路线 | OSMnx/NetworkX 或项目已有图网络；真实使用有向 edge 与 cost |
| 持久空间数据库和路网服务 | PostGIS + pgRouting，或经验证的专用路由引擎 |
| 专业印刷地图、地图册和固定版 | QGIS Print Layout；组织生态要求时使用 ArcGIS Pro |
| 建筑、楼层和场地权威母版 | 现有 BIM/CAD/GIS 工程及相应专业工具 |
Turf 适合经验证的几何变换、buffer、测量和空间谓词，但不能把障碍栅格最短路或直线计算冒充给定 街道网络上的合法路线。路线必须由真实图网络或相应路由引擎计算，并保留 ordered edge、方向、限制、 connector 和 cost。
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.
- today First seen · 165 lines · 112 tokens per session scan A e5fc0df964bb
create-maps-and-spatial-plans is a skill published in the GitHub repository EverMind-AI/Raven (3,825 stars, last pushed today), licensed Apache-2.0. It adds 112 tokens to every session and 2,766 once invoked, about $0.0006 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 2026-09-12.
Other skills, from other repositories
neuroskill-bci
Use live BCI cognitive and mood state from NeuroSkill.
saelens
Train sparse autoencoders to interpret model features.
manim-video
Manim CE animations: 3Blue1Brown math/algo videos.
drug-discovery
Drug discovery: ChEMBL search, drug-likeness, interactions.
jupyter-notebook
Iterative Python via live Jupyter kernel (hamelnb).
bioinformatics
Gateway to 400+ genomics and computational biology skills.