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 agentmods add skills/rianvdm/product-ai-public/interactive-explainernpx skills add rianvdm/product-ai-public --skill interactive-explainergit clone --depth 1 https://github.com/rianvdm/product-ai-publicWrote 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/rianvdm/product-ai-public/interactive-explainer)<a href="https://agentmods.dev/skills/rianvdm/product-ai-public/interactive-explainer"><img src="https://agentmods.dev/badge/skills/rianvdm/product-ai-public/interactive-explainer.svg" alt="Measured on agentmods" 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 | $0.00148 | $0.02738 |
| Opus 5 | $0.00074 | $0.01369 |
| Sonnet 5 | $0.00030 | $0.00548 |
| Haiku 4.5 | $0.00015 | $0.00274 |
Grade A, and why
interactive-explainer 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 5d 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 — 242 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Interactive Explainer
You build interactive HTML visualisations that make abstract processes, algorithms, and decision logic experiential — something the reader can manipulate and explore, not just read. The goal is to eliminate cognitive debt: after using the visualisation, the reader should feel like they understand the logic, not just that they've seen it described.
Source Material
Preferred input is a linear walkthrough (from the linear-walkthrough skill), because walkthroughs are already structured as a logical narrative with clear sections and identified connections. If none exists:
- Work directly from source material (code, document, concept description)
- If the source material is dense, ambiguous, or poorly structured, invoke the
linear-walkthroughskill first to extract a clear narrative, then use that as input. This produces better visualisations than trying to interpret raw complexity directly.
Before You Build
Identify two things:
1. What is the core thing to make understandable?
Read the walkthrough and ask: what is the single most important thing a reader struggles to grasp from reading alone? This is usually one of:
- A decision algorithm — branching logic that leads to different outcomes based on inputs
- A sequential process — stages that execute in order, each transforming something
- A system with interacting parts — components that affect each other
- A concept with a key mechanism — an abstract idea that becomes clear when you can "turn the dial"
The visualisation should be built around that one thing, not an exhaustive diagram of everything.
2. What visualisation type fits?
| Core content | Visualisation type |
|---|---|
| Decision algorithm / flowchart | Interactive decision tree — live inputs that traverse the logic and highlight the resulting path |
| Sequential pipeline / process stages | Animated step-through — stages that activate in sequence with explanations at each step |
| System with interacting components | Clickable component diagram — click to explore each part; relationships animate on hover/click |
| Parameter-driven concept | Live explorer — sliders/inputs that change the output in real time, showing cause and effect |
| Comparative options | Side-by-side toggle — switch between options and see what 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.
- 5d ago First seen · 242 lines · 148 tokens per session scan A 8e33bca01a53
interactive-explainer is a skill published in the GitHub repository rianvdm/product-ai-public (15 stars, last pushed 16d ago), licensed MIT. It adds 148 tokens to every session and 2,738 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…