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-product-and-tool-interfacesgit 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-product-and-tool-interfaces)<a href="https://agentmods.dev/skills/evermind-ai/raven/build-product-and-tool-interfaces"><img src="https://agentmods.dev/badge/skills/evermind-ai/raven/build-product-and-tool-interfaces/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-product-and-tool-interfaces"><img src="https://agentmods.dev/badge/skills/evermind-ai/raven/build-product-and-tool-interfaces.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 | $0.00147 | $0.06540 |
| Opus 5 | $0.00073 | $0.03270 |
| Sonnet 5 | $0.00029 | $0.01308 |
| Haiku 4.5 | $0.00015 | $0.00654 |
Grade A, and why
build-product-and-tool-interfaces 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 — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
构建产品与工具界面
成功定义
让目标角色把真实输入或对象推进到可核验结果；需要持久化、权限、批量或协作时，这些能力也必须形成真实闭环。完成态不是“页面已经画完”，而是适用于当前子型的输入、命令、状态变化、反馈、恢复与输出成立；不适用的能力应明确记为 N/A，不能用假数据或假控件补齐产品外观。
本 Skill 拥有产品领域判断，并保留介质中立的真实标杆、视觉理由、素材来源与许可和目标环境验收。
最终消费者或合同交付确为 Web 时，再与 $build-polished-visual-frontends 组合；对象模型、迁移报告或
内部状态检查器本身不触发组合。组件系统风格合同和代表性非空方向帧只适用于含可视界面的
Create/Edit；纯对象建模和 Diagnose 记为 N/A + 原因。Diagnose 可只读检查组件语言与渲染证据，
不得借检查改写视觉方向。详细状态矩阵、批量作用域、恢复策略和环境转换模式见
references/patterns.md。
组合时以对象模型、命令关系、任务密度和状态风险决定视觉优先级，不套用“简单、干净、中性”的 默认皮肤。主题材料与标志性表达不得压过主工作对象，除非用户要求、已接受参考或品牌系统明确授权。
选择主要产品循环
按用户反复完成的工作选择主型，不按“有侧栏”“像后台”或采用的框架分类。混合产品只保留一个主要循环，其他能力围绕它服务。
| 主型 | 核心对象 | 高频循环 | 完成证据 |
|---|---|---|---|
| 运营与审核工作台 | 案例、记录、请求、任务 | 定位、判断、分派、批量处置、追踪 | 状态去向、责任人、审计记录 |
| 创作与编辑工具 | 文档、素材、场景、版本 | 选择、编辑、预览、比较、保存、发布 | 可恢复版本或真实产物 |
| 分析与管理工具 | 数据集、查询、配置、项目、资源 | 查询、比较、解释、配置、处置 | 可追溯决策、配置或报告 |
| 任务流产品 | 申请、订单、工单、审批、作业 | 受理、校验、交接、批准、完成、重开 | 生命周期变化与交接记录 |
页面主要用于发现和阅读内容时，路由到内容网站；交付物主要是跨产品复用的组件、状态与 token 时，路由到 UI 组件与设计系统。单张图的重点是解释数据时属于数据可视化；只有当查询、筛选、告警和处置组成持续工作时，完整界面才属于本领域。操纵变量只为理解规律时属于交互解释器，不要套用业务工作流。
登录、侧栏、搜索、图表或 AI 摘要不自动构成产品工具。混合站点按任务面拆分：发现与阅读仍按内容网站设计；只有反复操作稳定对象、推进持久生命周期或生成可继续使用结果的工作区才应用本 Skill，不把整个站点强行包装成 dashboard。
先定工作模式与适用能力
先根据请求选择工作模式，不能把 Create 的流程机械套到 Edit 或 Diagnose：
| 模式 | 目标 | 硬边界 |
|---|---|---|
| Create | 从需求建立新的对象、命令与工作面 | 只实现有真实输入、状态和结果的承诺；未要求的企业能力不补齐 |
| Edit | 修改现有产品而不破坏既有任务、数据与交互契约 | 先审计不可破坏行为、数据迁移和回归证据，再做最小必要改动 |
| Diagnose | 定位现有界面的行为、状态、性能或可用性问题 | 默认零写入：不改源码、配置、权威数据或产品状态；只做只读复现、追踪和证据归因，修复需用户另行授权 |
再按产品子型建立适用性表，并为每项写 required / optional / N/A + 原因：
| 能力 | 何时需要 | 何时可为 N/A |
|---|---|---|
| 当前对象、选择与批量 | 多对象列表、集合操作、批处理 | 单对象计算器、一次只处理一个文件或文档的工具 |
| 持久化、版本与刷新恢复 | 工作跨会话继续、形成权威记录或可恢复草稿 | 明确的一次性无持久化工具；仍须给真实即时结果或可用输出 |
| 权限与审计 | 多角色、受控动作、合规或高影响变更 | 单用户、本地、无角色差异的工具 |
| 协作与冲突 | 多人同时或异步编辑、交接、评论、审批 | 单人工作流或只读共享 |
| 异步作业与进度 | 导入、计算、上传、发布等确实跨时完成 | 同步且可即时完成的命令 |
| 目标环境任务转换 | brief 明确承诺多个环境完成任务 | 明确限定单一环境的专业重型工作面；仍须在合同视口可用 |
所有子型只共享不变量，不共享固定字段：真实输入进入一个权威任务模型；同一命令的不同入口产生相同效果；可见承诺能追溯到真实状态或输出；失败保留仍可恢复的工作；界面不伪造未实现的后端、权限、协作、版本或持久化。
What ships with it
1 file 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 · 187 lines · 147 tokens per session scan A 955e1d0d83e4
build-product-and-tool-interfaces is a skill published in the GitHub repository EverMind-AI/Raven (3,825 stars, last pushed today), licensed Apache-2.0. It adds 147 tokens to every session and 6,540 once invoked, about $0.0007 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
claude-design
Design one-off HTML artifacts (landing, deck, prototype).
tldraw-offline
Drive and script tldraw offline canvases with an agent.
computer-use
Drive the desktop background-first; escalate on signal.
google-workspace
Gmail, Calendar, Drive, Docs, Sheets via gws CLI or Python.
simplify-code
Parallel 4-agent cleanup of recent code changes.
sketch
Throwaway HTML mockups: 2-3 design variants to compare.