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/thu-maic/openmaic/deep-interactivenpx skills add THU-MAIC/OpenMAIC --skill deep-interactivegit clone --depth 1 https://github.com/THU-MAIC/OpenMAICWrote 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/thu-maic/openmaic/deep-interactive)<a href="https://agentmods.dev/skills/thu-maic/openmaic/deep-interactive"><img src="https://agentmods.dev/badge/skills/thu-maic/openmaic/deep-interactive.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 | $0.00074 | $0.00643 |
| Opus 5 | $0.00037 | $0.00321 |
| Sonnet 5 | $0.00015 | $0.00129 |
| Haiku 4.5 | $0.00007 | $0.00064 |
Grade A, and why
deep-interactive 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 4d 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deep Interactive course design
Default to doing, not reading. A page earns the slide type only when the
learner has nothing to manipulate on it.
Structure
- Scene 1 is a
slide: it frames the question the course answers and tells the learner what they are about to play with. One page, no more. - The body is
interactive. Each body scene isolates one mechanism, one variable, one structure — so the learner can change it and watch the result. - The last scene is a
slideor aquizthat consolidates what the manipulation showed. - Consecutive interactive scenes must not use the same
widgetType. Two simulations in a row is a design failure; vary the modality as the concept moves from "watch it" to "trace it" to "predict it".
Choosing a widget type
| widgetType | Use when the learner should… |
|---|---|
simulation |
vary parameters and watch a system respond in real time |
diagram |
explore structure, flow or hierarchy by expanding and following |
code |
read, modify and run a short program that embodies the idea |
game |
make repeated decisions under a rule set and see the score move |
visualization3d |
inspect a spatial object or scene from angles a slide cannot show |
widgetOutline
Every interactive scene must carry a widgetOutline populated for its type —
an interactive scene with an empty widget outline degrades to a generic page and
defeats the whole point.
simulation:concept,keyVariables(the actual sliders/inputs)diagram:diagramType,nodes(withlabel, andparentIdfor hierarchy)code:language,conceptgame:gameType,challenge,playerControlsvisualization3d:visualizationType,objects,interactions
Scene naming
Titles name what the learner does or discovers, not the topic heading.
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.
- 4d ago First seen · 58 lines · 74 tokens per session scan A bb26d6b34f34
deep-interactive is a skill published in the GitHub repository THU-MAIC/OpenMAIC (31,009 stars, last pushed today), licensed MIT. It adds 74 tokens to every session and 643 once invoked, about $0.0004 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
article-writing
Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.
ljg-learn
Deep concept anatomist that deconstructs any concept through 8 exploration dimensions (history, dialectics, phenomenology, linguistics, formalization, existentialism, aesthetics, meta-philosophy) and compresses insights into an epiphany. Use when user asks to explain, dissect, or deeply understand a concept, term, or…
miniapp
Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
code-documenter
Use when adding docstrings, creating API documentation, or building documentation sites. Invoke for OpenAPI/Swagger specs, JSDoc, doc portals, tutorials, user guides.
deck-course-module
暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.