build-interactive-explainers

build-interactive-explainers is a skill for Claude Code, Codex from EverMind-AI/Raven. It costs 102 tokens per session (3,087 once invoked), scanned A, original, Apache-2.0.

A guide for building interactive explainers, calculators, and simulations driven by an executable model. Users change inputs, steps, states, or events to understand a rule or see how a process develops over time.

In plain words
What is it for?
Use it to teach a relationship, calculate a result from validated inputs, or simulate rule-based change with repeatable states, independent checks, and clear limits on interpretation.
Why use it?
It keeps the underlying model separate from the display, so animations and interface changes cannot invent results or causal relationships. It also limits claims to what the model actually represents rather than implying a real-world prediction.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: $skill-name invocation.

Good fit Use it to teach a relationship, calculate a result from validated inputs, or simulate rule-based change with repeatable states, independent checks, and clear limits on interpretation.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/evermind-ai/raven/build-interactive-explainers
About the project

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.

EverMind-AI/Raven · 3,825 stars · on GitHub · raven.evermind.ai

Install

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.

Any agent
npx skills add EverMind-AI/Raven --skill build-interactive-explainers
Clone the repo
git clone --depth 1 https://github.com/EverMind-AI/Raven

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for build-interactive-explainers

README.md
[![agentmods](https://agentmods.dev/badge/skills/evermind-ai/raven/build-interactive-explainers/github.svg)](https://agentmods.dev/skills/evermind-ai/raven/build-interactive-explainers)
Your own site
<a href="https://agentmods.dev/skills/evermind-ai/raven/build-interactive-explainers"><img src="https://agentmods.dev/badge/skills/evermind-ai/raven/build-interactive-explainers/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.

agentmods 80×15 button for build-interactive-explainers

Your own site · 80×15
<a href="https://agentmods.dev/skills/evermind-ai/raven/build-interactive-explainers"><img src="https://agentmods.dev/badge/skills/evermind-ai/raven/build-interactive-explainers.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 102 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,087 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00102 $0.03087
Opus 5 $0.00051 $0.01543
Sonnet 5 $0.00020 $0.00617
Haiku 4.5 $0.00010 $0.00309

Measured today against content hash 4304e4c808cb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

build-interactive-explainers 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.

plugins-dist/design-engine/raven_design/skills/build-interactive-explainers/SKILL.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

构建交互解释器与仿真

领域权责

本 Skill 拥有领域路由、模型与学习 claim、八个领域 gate、专业能力需求、claim ceiling 和失败返回; 任务契约、工具事实、authority/promotion、渲染、review 与交付语义沿用共享视觉底座。

本 Skill 保持介质中立。开工前锁定最终消费者、目标媒介或 renderer、输入设备、尺寸/观看条件、必须可达的状态和最终验收;介质由任务和真实消费环境决定,不因实现方便默认 HTML、浏览器外壳或固定画幅。最终像素、声音、触觉、打印、原生场景或可编辑文件只检查当前媒介实际承诺的通道。

只有最终消费者或合同交付明确为 Web 时,才加载 $build-polished-visual-frontends,由它补充 Web 技术栈、组件系统、响应式、DOM/CSS、浏览器交互与像素批评。非网页媒介不能用浏览器截图、Gallery iframe、HTML 查看器或 DOM 测试冒充目标消费者证据;浏览器只作为查看器时,必须回到目标 renderer、实体样张、原生应用、投影/打印环境或声明设备完成最终验收。

模型契约、生产计算、独立 oracle、实验状态、表示映射、学习任务和交付源是不同 concern。Reference model 与 production computation 拥有规则和结果 truth;表现层只消费带版本的权威 result/snapshot,拥有尺度、编码、布局、相机和交互映射,不能反向改写模型或以动画补出不存在的因果。每个 concern 只能有一个 authoritative owner,但不同 concern 可以由不同原生母版拥有;模型或结果 hash 改变时,相关表示与最终消费者证据全部 stale。截图、Viewer、导出和缓存只能是 derived output。

1. 先分路,再允许实现

先写一句:用户改变什么 → 模型执行什么 → 观察什么证据 → 最多能解释什么

主型 成立条件 默认 claim ceiling
explainer 操纵输入或步骤是为了理解、解释或迁移一条规律 当前模型范围内的关系被可操作地揭示;不声称学习效果
calculator 主要价值是从已验证输入得到结果,理解过程并非必要 按声明模型计算结果;不声称时间过程、因果学习或现实预测
simulation 状态依规则、时间、事件、随机或求解器演化,过程本身影响解释 复现声明模型的演化;不等同真实系统或决策工具
game 主要循环是挑战、计分、胜负、解锁或技巧表现 路由到游戏领域;模型说明只能作为次要合同

外部观测数据的比较与发现路由到数据可视化;持续保存、协作和运营处置路由到产品工具;无需干预即可理解的固定关系路由到技术图解。文件是 HTML、SVG、Canvas 或 WebGL 不改变主领域。

2. 专业工具与 authority 接口

任务子型 → 所需能力 → Registry candidate → 选择理由 → 原生模型/语言 → authority concern → 使用证据 → 失败返回 选择工具。具体路由读取专业工具能力档案,领域模式读取模式与检查

  • 先读取共享 Tool Registry;档案中的 candidate id 不是 availability 或 usage 证明。
  • 选定工具后,让其原生方程、构造图、状态模型、数据集、组件、管线或导出成为对应 concern 的作品语言,不只借一个控件后手写其余能力。
  • used 必须有依赖、解析版本、许可、真实调用、可编辑母版、重建/导出及当前 consumer/pixel 证据。
  • GUI、商业或当前不可执行的候选只记录 unavailablehuman_handoff;不得模拟调用。
  • 自研前必须实际运行 capability probe;只有 fail 能证明能力缺口。unavailable 返回其他候选或 handoff。
  • 自定义只拥有已证明缺失的最小边界,并记录数据、交互、表示和导出的一致性证据。
  • 专业工具若必须写入才能形成 capability proof,Create/Edit 只可在用户授权 workspace 内操作隔离的“一次性验证副本”:记录输入 hash、最小真实操作、重开/重算、导出 hash 和目标消费者结果;不得写入 canonical master、替换当前交付或改变 canonical/promotion。Diagnose/Audit 一律零写入,不得为取得 proof 新建验证副本、改配置、重算缓存或制造新帧。Proof 与最终交付分别记录自身 hash;前者只回答被探测能力,不能自动晋升后者。

Read the full file on GitHub · 123 lines

Files

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.

Changes

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.

  1. today First seen · 123 lines · 102 tokens per session scan A 4304e4c808cb

Subscribe to this mod's changes

build-interactive-explainers is a skill published in the GitHub repository EverMind-AI/Raven (3,825 stars, last pushed today), licensed Apache-2.0. It adds 102 tokens to every session and 3,087 once invoked, about $0.0005 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.