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 build-content-websitesgit 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/build-content-websites)<a href="https://agentmods.dev/skills/evermind-ai/raven/build-content-websites"><img src="https://agentmods.dev/badge/skills/evermind-ai/raven/build-content-websites/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/build-content-websites"><img src="https://agentmods.dev/badge/skills/evermind-ai/raven/build-content-websites.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 | $0.00089 | $0.06454 |
| Opus 5.5 | $0.00036 | $0.02582 |
| Sonnet 5.5 | $0.00018 | $0.01291 |
| Haiku 4.5 | $0.00009 | $0.00645 |
Grade A, and why
build-content-websites 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 — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.
构建内容型网站
领域边界
当主要对象是有身份和来源的内容实体,用户价值依赖其被找到、阅读、引用或持续维护时,使用本 Skill。若删除独立内容身份与阅读发现后价值仍不受损,应重新路由;营销图片属于传播图形,组件复用属于设计系统,审批、配置或保存业务对象属于产品界面。
服从 $visual-artifact-design 的共享治理。本 Skill 对内容 authority、发现和出版连续性保持介质中立:先确定最终消费者与目标介质,再选择呈现、构建和验收路径。只有最终消费者是 Web 或合同交付本身是 Web 时才调用 $build-polished-visual-frontends;非网页媒介不能用浏览器证据冒充目标消费者,浏览器预览最多是派生检查。
合同至少包含一个人类阅读或查看的最终消费者。网页、PDF、EPUB、邮件或应用内视图可各自呈现; feed/API 只能附属于同一内容,不能替代人的最终消费。只有机器消费时退出本视觉 Skill。内容事实、 URL、媒体来源和发布历史不因介质改变。先读 领域模式;选工具前读 工具能力档案。
Web 视觉送达前置 gate
最终消费者包含 Web 时,在形成视觉方向或写第一行页面代码之前调用
$build-polished-visual-frontends,并完成以下记录;本域不能以内容 authority、框架选择或构建成功
替代它:
- 锁定
identity_route与layout_route并写入REFERENCE-CONTRACT(定义见$build-polished-visual-frontends); 两条路线各自锁定,一条不能代替另一条。保存实际来源画面和 3–6 条可观察关系, 至少覆盖宏观结构/阅读顺序、层级/密度、主对象/图像角色;模板、标杆或品牌名称不算证据。 - 建立
VISUAL-THESIS与MASTER-VISUAL-CONTRACT。在写页面 DOM、布局 CSS 或改造模板版式前, 先调用image_generate产出并查看项目级主视觉母版;已有合法真实资产只有在完成同一语义工作时 才可替代。每个主要页面族在布局前填写page_family / opening_job / visual_role / asset_lineage / reason / final_evidence,visual_role只用dominant_background / integrated_visual_field / content_first并默认第一种,先按大背景路线完成代表帧。若实际像素显示它妨碍主要阅读或操作任务, 先检查构图、裁切与文字关系;若冲突来自任务本身,可改用integrated_visual_field或content_first。 在当前页面族的reason与final_evidence中记录具体冲突、调整前后像素和主要任务改善的证据, 并更新参考合同与视觉角色声明;单个页面族的例外不得推广到全站。实现便利、生成失败、资产成本、 没有真图、未经像素验证的可读性顾虑或模型偏好不能单独成为改路线的理由。visual_role声明须与渲染返回的opening_visual读数相符。大背景建立页面族开场,不要求每个 后续区块铺图;后续用同源资产、排印、内容结构或交互延续身份,不能退回默认内容块。 - 遇到对比、评测或选型任务,先判断读者意图属于
decision_support / neutral_comparison / benchmark_report / editorial_analysis,关键词本身不决定 页面形态。只有decision_support必须把场景或标准、选项、证据和边界组织成可扫描的决策结构; 推荐必须有条件,不制造无依据的总体冠军。其他子型保留其自然文类,不强加推荐或决策矩阵。 - 先按整页定义图像角色,再按主要区块建立资产路由表:
truth_asset | standard_symbol | generated_visual | exact_graphic。内容页无合适真图时,hero、 场景、插画、纹理、表现型 icon 与 feature pictogram 使用image_generate;系列 变体默认以主视觉或家族母图作为 image edit 输入。每项资产填写semantic_job和它与背景、 排印、内容结构或交互中至少两项的关系。标准功能 icon 来自一个既有系统或成熟家族;数据、文字、坐标和拓扑由 专业库或 renderer 负责。所有生成图在 provenance 记录真实性边界;纯氛围背景只记录 provenance, 不在成品展示制作过程。只有省略说明会造成事实误认时才用内容语境内的短说明消除误认,说明后 仍会误认则不得使用。不存在手绘 SVG、CSS 装饰或最终占位图降级路线。 页头、favicon 与 og 图的标识槽位按$visual-artifact-design的既有身份盘点:主体已有标识必须用它,没有 必须设计出来;简报里"无 logo / 自制标记"之类结论不是证据,自己去出处查看像素。 - 代表画面直接使用已经取得的真实/生成资产,并逐条对照参考合同。
generated_visual只有在 成功调用、查看原图、记录 lineage、进入最终文件且被产品代码引用后才算使用;生成失败是能力 缺口,不授权用 SVG、Canvas 或 CSS 模拟。 - 建立
DETAIL-CONTRACT:SURFACE-MANIFEST覆盖页面族、顶层区块、独特状态和视觉例外;COMPONENT-BEHAVIOR-MAP按独特行为类记录示能、动作、反馈、恢复与自动遍历入口。同组件、同状态 合同和同数据规则的重复实例可共享视觉证据,但所有实际目标仍须由浏览器自动遍历。最后一次可见 修改后逐行结账,再执行替图测试和模板距离测试;整页缩略图、构建成功或少数控件通过不能代替。 来源、权利、方法和真实性边界邻近其约束的内容,不自动做成巨幅或重复横幅。色条、标题旁竖线、 局部边框和图标外框只有在稳定编码导航、状态、分组或身份语法时保留,不能用来制造“权威感”。
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 · 230 lines · 89 tokens per session scan A 6d0a2f260858
build-content-websites is a skill published in the GitHub repository EverMind-AI/Raven (5,463 stars, last pushed today), licensed Apache-2.0. It adds 89 tokens to every session and 6,454 once invoked, about $0.0004 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.