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 design-icons-and-symbolsgit 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/design-icons-and-symbols)<a href="https://agentmods.dev/skills/evermind-ai/raven/design-icons-and-symbols"><img src="https://agentmods.dev/badge/skills/evermind-ai/raven/design-icons-and-symbols/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/design-icons-and-symbols"><img src="https://agentmods.dev/badge/skills/evermind-ai/raven/design-icons-and-symbols.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 | $0.00100 | $0.03406 |
| Opus 5.5 | $0.00040 | $0.01362 |
| Sonnet 5.5 | $0.00020 | $0.00681 |
| Haiku 4.5 | $0.00010 | $0.00341 |
Grade A, and why
design-icons-and-symbols 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
图标与符号设计
本 Skill 只拥有符号语义、家族语法、光学尺寸、领域验证和消费边界；通用合同、工具证据、authority
graph、渲染审查与 scoped promotion 服从 $visual-artifact-design。文件齐备、样张精致或 Gallery
可见都不等于领域 gate 通过。
成功意味着：符号在声明的消费者、尺度和环境中传达正确对象、动作或状态；权威母版可维护，导出可追溯，证据强度与 claim 一致。不要为了系统感补造语义、尺寸、风格或应用。
介质中立与最终消费者合同
本 Skill 保持介质中立。进入设计前先建立 final_consumer_record：命名最终消费者、目标介质、实际 runtime/设备/生产工艺、尺寸或观看条件、交付格式和最终验收方式。浏览器预览、Gallery 或说明页只是查看工具；除非 Web 本身就是合同交付，它们都不是最终消费者。
只有最终消费者是 Web 时才调用 $build-polished-visual-frontends，由其负责网页技术栈、页面构图、响应式与 Web 最终像素；本 Skill 仍拥有符号语义、家族、光学母版和领域验证。原生平台、字体、动效 runtime、印刷、丝印、雕刻或现场标牌不得为了方便预览而加载该 Web 执行层，也不得用浏览器证据冒充目标消费者。
数字交付的最终像素必须来自合同指定的目标 renderer；物理交付的最终验收必须检查按同版生产文件制作的实体样张及声明观看条件。非最终消费者生成的截图只能诊断，不得晋升为交付证据。
路由主型与责任
| 主型 | 本 Skill 的责任 | 必须先确认 |
|---|---|---|
| UI 图标 | 功能语义、平台适配、光学资产、稳定接口 | 真实宿主、既有图标库、平台惯例、方向与最小尺寸 |
| 公共信息符号 | 指代、观看条件、文字/箭头组合和理解证据 | 当前标准、辖区、受众与部署系统 |
| 安全与运营符号 | 误读后果、冗余通道、目标用户验证和审批边界 | 是否已有注册符号、风险责任人、法规与运行场景 |
| 设备符号 | 控件/状态/连接含义及设备落位 | 当前设备标准、面板条件、培训与维护责任 |
| 品牌相关符号 | 已批准身份语言下的微缩版与功能图标 | 身份主体、品牌母版与品牌方授权 |
状态、动效、图标字体和完整家族是主型上的交付修饰，不自动成为新主型。先记录 route_record：final_consumer_record、上下文、主型、风险、误读后果、协作领域、权威来源和最终批准角色。
- 承担组织、产品或服务主体识别的标志、字标和品牌架构转
$design-brand-identities；本 Skill 不自行批准身份。 - 按钮的焦点、命中区、按下、禁用和控件名称由 UI 组件或产品宿主拥有；本 Skill 只拥有图形语义与光学资产。
- 地图比例、图例和空间关系由地图领域拥有；本 Skill 可拥有其中的符号家族。
- 注册安全、公共或设备符号优先复用权威原件；未经标准与责任人授权，不以原创或品牌化改写替代。
生产路线
- 权威品牌、公共、安全与设备符号使用批准母版，不生成替代品。
- 搜索、关闭、菜单等标准功能 icon 优先使用真实宿主的既有系统；没有时选择一个成熟 icon 家族， 不得由模型补画近似 SVG。
- 项目独有、低风险、插画式、空间化或有材质表现的 icon 与 feature pictogram，默认使用
image_generate创建整个家族：先生成家族母图，再用 image edit 派生变体；不得用手写 SVG、 CSS 或 Canvas 冒充精致资产。 - 若消费者合同要求矢量母版，使用专业矢量化／图标工具从批准的生成母图建立可编辑母版并保留 lineage；模型手工描 path 不算专业母版。
- 只有字符、数据、坐标、拓扑、光学尺寸或标准几何本身是 claim 时，才进入精确矢量工具路线。
生成 icon 不烘焙关键文字、logo 或数字；语义名称、状态与无障碍文本由宿主拥有。生成工具不可用 是能力缺口，不授权切换到手写 SVG。
图标容器、彩色底、边框、色条和命中区由宿主拥有，只有平台惯例、可触达尺寸、容器形状或真实状态 要求时才随图标出现；任意彩色方框或竖线不是家族语法。视觉权重按动作风险、频率和状态分配，不按 每个图标等权。样张背景、CSS 包装与展示说明只能提供上下文，不能替代符号本身的语义、光学和家族 证据；必要限制贴近受影响符号，但不自动成为最强视觉对象。
Claim ceiling 与 authority
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 · 139 lines · 100 tokens per session scan A 8df7f77a3691
design-icons-and-symbols is a skill published in the GitHub repository EverMind-AI/Raven (5,463 stars, last pushed today), licensed Apache-2.0. It adds 100 tokens to every session and 3,406 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
anatomy
Explain an idea as an interactive isometric machine figure.
claude-design
Design one-off HTML artifacts (landing, deck, prototype).
ip-as-logo
Design minimal cute IP mascot marks readable at 32px.
tldraw-offline
Drive and script tldraw offline canvases with an agent.
sketch
Throwaway HTML mockups: 2-3 design variants to compare.
baoyu-infographic
An infographic generator that turns supplied content into a visual summary using different information layouts and visual styles. It supports standard and custom image proportions and multiple languages.