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-technical-diagramsgit 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-technical-diagrams)<a href="https://agentmods.dev/skills/evermind-ai/raven/create-technical-diagrams"><img src="https://agentmods.dev/badge/skills/evermind-ai/raven/create-technical-diagrams/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-technical-diagrams"><img src="https://agentmods.dev/badge/skills/evermind-ai/raven/create-technical-diagrams.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 | $0.00127 | $0.03831 |
| Opus 5 | $0.00063 | $0.01916 |
| Sonnet 5 | $0.00025 | $0.00766 |
| Haiku 4.5 | $0.00013 | $0.00383 |
Grade A, and why
create-technical-diagrams 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
创建技术图解与工程文档
领域职责与接口
本 Skill 拥有技术关系、任务子型、用途风险、领域 gate、claim ceiling、失败返回和专业签审门；工作
状态、authority/tool/review/promotion、通用渲染与证据治理沿用 $visual-artifact-design。
先按本文件路由。需要子型模型、专业语法和检查项时读取领域模式与检查；需要选择工具时只读取相关的工具能力档案。工具名称、文件扩展名、成功导出和漂亮 PDF 都不能证明领域正确。
路由子型与用途等级
按读者要完成的判断选择一个主子型；其他视图必须回指同一对象或接口，不把异构语义硬叠在一页。
| 主子型 | 必须保真的关系 | 常见原生能力 |
|---|---|---|
| 说明/培训图 | 对象、主关系、方向、边界、抽象声明 | 结构化 diagram、矢量说明、文档发布 |
| 系统/网络 | 组件、端口、接口、分区、依赖、冗余或信任边界 | graph/diagram 或 MBSE 模型 |
| 流程/SFC/时序 | 步骤或状态、事件、守卫、动作、分支、失败与恢复 | BPMN、SFC/PLC 或文本图模型 |
| 电气/仪控/工艺 | 设备、端子、导体/管线、信号、回路、代号与跨页引用 | ECAD/EDA、P&ID/仪控模型 |
| 机械/系统剖面 | 方位、剖切、装配、接口、尺寸/公差及来源 | 参数化 CAD 与关联工程图 |
| 科学机制 | 实体、过程、条件、因果方向、反馈、证据与不确定性 | 结构化模型加技术矢量图 |
用 claim scope 选择最高用途等级，不用画面外观推断：
| 等级 | 允许的最高领域声明 | 额外前提 |
|---|---|---|
| L0 说明草案 | 内部概念、说明或培训候选；不可操作 | 事实/假设分开，限制可见 |
| L1 复核培训 | 指定受众的培训或技术说明 | 合格领域 reviewer 覆盖相应 claims |
| L2 维护辅助 | 指定配置的维护、调试或故障定位辅助 | as-configured/as-built 来源、原生 ID/端口、现场或维护复核 |
| L3 受控工程 | 工程、施工、安全或合规范围内的受控文件 | 设计依据、适用标准、计算/危害证据、授权校核与发布流程 |
SELF_REVIEW_ONLY 最高停在 L0；它可以支持当前 build 的限定技术/协议 internal-positive，但不能证明视觉独立通过、领域外部正确、现场有效或 L1–L3。externally-validated 只覆盖独立且角色合格的 reviewer 对同一 build_hash 明确通过的 claims。
领域契约
在进入 gate 前记录：
operation_mode: Create | Edit | Diagnose | Audit、主子型、读者任务、最终消费者、目标媒介、目标用途等级和误用后果；positive_for候选、明确非目标、not_evidence_for与excluded_claims；- 必须准确、允许抽象、未知/假设、适用标准族及辖区/组织 profile；
- 需要共享的对象、端口、关系、状态、单位、方向、来源和稳定 ID；
- 授权 workspace 与写入边界，工具、符号库、字体、素材和第三方数据的来源、版本与许可；
- 需要的专业角色，以及哪些 claims 必须由谁独立复核。
缺失资料若会改变连接、顺序、尺寸、保护、因果或发布用途，保持未知并降级、等待或停止；不得用整洁布局补造事实。
操作、媒介与验证合同
本 Skill 始终介质中立：依据最终消费者选择原生母版、派生格式和验证环境，不把 HTML 或浏览器当默认外壳。只有最终消费者或合同交付明确为 Web 时，才加载 $build-polished-visual-frontends；它负责 Web 的 DOM/CSS、响应式、交互和浏览器像素，本 Skill 仍拥有技术语义、专业母版和领域 gate。所有媒介都必须在真实目标消费者中完成最终验收：视觉消费者还要验收与最终交付同一 build_hash 的最终像素；原生或非视觉消费者验收由领域契约定义的等价终态，例如可重开、可编辑以及字段、关系、状态与接口保持一致，不强迫生成像素证据。浏览器、HTML 查看器或 Gallery 只能作辅助预览，不能冒充非 Web 目标消费者证据。
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 · 124 lines · 127 tokens per session scan A 18a51bfc6945
create-technical-diagrams is a skill published in the GitHub repository EverMind-AI/Raven (3,825 stars, last pushed today), licensed Apache-2.0. It adds 127 tokens to every session and 3,831 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
dcf-model
Build discounted cash flow valuation workbooks in Excel.
comps-analysis
Build comparable-company valuation workbooks in Excel.
lbo-model
Build leveraged buyout workbooks with IRR/MOIC in Excel.
neuroskill-bci
Use live BCI cognitive and mood state from NeuroSkill.
saelens
Train sparse autoencoders to interpret model features.
google-workspace
Gmail, Calendar, Drive, Docs, Sheets via gws CLI or Python.