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 renky1025/agent-skills --skill edulabgit clone --depth 1 https://github.com/renky1025/agent-skillsWrote 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/renky1025/agent-skills/edulab)<a href="https://agentmods.dev/skills/renky1025/agent-skills/edulab"><img src="https://agentmods.dev/badge/skills/renky1025/agent-skills/edulab/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/renky1025/agent-skills/edulab"><img src="https://agentmods.dev/badge/skills/renky1025/agent-skills/edulab.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00076 | $0.00795 |
| Opus 5 | $0.00038 | $0.00398 |
| Sonnet 5 | $0.00015 | $0.00159 |
| Haiku 4.5 | $0.00008 | $0.00080 |
Grade A, and why
edulab 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 10d 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.
What it actually says
edulab
中高考数学可视化：空间几何 3D 解题演示 + 函数图形参数可控可视化。产物为单文件交互式 HTML。
何时使用
- 用户给出立体几何题（中高考风格），需要 3D 演示解题过程
- 用户想要函数图像且希望调参看变化（滑块联动）
/edulab <题目或函数>
工作流
路径约定：下文
<skill>指本技能安装目录（如~/.claude/skills/edulab）。运行脚本前请先cd到该目录，或将其替换为实际路径。Python 需已安装 sympy（建议：python3 -m venv .venv && .venv/bin/pip install sympy）。
几何模块
- 读题，确定立体类型与参数，写入 spec JSON（契约见 references/schema.md；题型清单见 references/taxonomy.md）。支持 query.type: line_plane_angle / line_line_angle / dihedral_angle / point_plane_distance / volume_tetra / parallel_perp / skew_distance / circumsphere / three_views / surface_shortest_path / insphere；solid: cube/cuboid/tetra/prism3/pyramid4/cylinder/cone/sphere。
- 求解（需用已安装 sympy 的 Python 3）：
solver 内含 sympy 计算，输出精确值 + 数值。检查 steps 与 result 是否与标准答案一致，不一致则修 spec 重跑，不得静默交付错误答案。cd <skill>/scripts/geometry python3 geometry_solver.py <spec.json> <scene.json> - 生成 HTML（加 --offline 内联 Three.js，无网环境可打开）：
python3 build_html.py <scene.json> <out.html> [--offline] - present_files 打开 out.html。
函数模块
- 确定函数族（quadratic/linear/inverse/trig/exp/log/power 或 custom 自由表达式）。custom 时 params 传 {"expr": "sin(x)/x"}，表达式经 safe_expr.py 安全解析（禁 eval），非法输入直接拒绝。
- 生成 scene（参数写 JSON 文件传入）：
cd <skill>/scripts/function python3 function_engine.py quadratic <params.json> <scene.json> python3 build_html.py <scene.json> <out.html>后 present_files。
扩展约定
- 新几何题型：geometry_solver.py 加 query type 分支 + taxonomy.md 更新状态。
- 新函数族：function_families.py 加项 + template_2d.html 的 f()/computeProps() 加分支。
- 新立体：solids.py 加 vertices/edges。
- 文件写入禁 Box Drawing 等 Unicode 装饰字符（防乱码）；中文标签走 DOM/Canvas 文本。
- 自由函数表达式若支持，禁 eval/Function，须安全 AST 解析。
设计文档
完整架构、阶段规划、已验证结论见 references/design.md。
What ships with it
33 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.
- assets/vendor/CSS2DRenderer.js 4.1 KB runs code
- assets/vendor/OrbitControls.js 26 KB runs code
- assets/vendor/three.min.js 589 KB runs code
- examples/func_custom.json 47 B
- examples/func_multi.json 197 B
- examples/func_quadratic.json 67 B
- examples/geom_circumsphere.json 166 B
- examples/geom_dihedral_angle.json 218 B
- examples/geom_insphere.json 131 B
- examples/geom_line_line_angle.json 194 B
- examples/geom_line_plane_angle.json 202 B
- examples/geom_net.json 126 B
- examples/geom_parallel_perp.json 200 B
- examples/geom_point_plane_distance.json 185 B
- examples/geom_pyramid_apex_angle.json 210 B
- examples/geom_skew_distance.json 193 B
- examples/geom_surface_path.json 175 B
- examples/geom_surface_volume.json 325 B
- examples/geom_three_views.json 134 B
- examples/geom_volume_tetra.json 192 B
- README.md 7.4 KB
- references/design.md 4.4 KB
- references/schema.md 1.2 KB
- references/taxonomy.md 2.4 KB
- scripts/function/build_html.py 865 B runs code
- scripts/function/function_engine.py 5.5 KB runs code
- scripts/function/function_families.py 2.0 KB runs code
- scripts/function/safe_expr.py 5.9 KB runs code
- scripts/function/template_2d.html 7.9 KB
- scripts/geometry/build_html.py 1.9 KB runs code
- scripts/geometry/geometry_solver.py 30 KB runs code
- scripts/geometry/solids.py 5.5 KB runs code
- scripts/geometry/template_3d.html 10 KB
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.
- 10d ago First seen · 56 lines · 76 tokens per session scan A cc554aff836c
edulab is a skill published in the GitHub repository renky1025/agent-skills (11 stars, last pushed today), licensed MIT. It adds 76 tokens to every session and 795 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 2026-08-31.
Other skills, from other repositories
design-taste-frontend
Anti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, and ships interfaces that do not look templated. Real design systems when applicable, audit-first on redesigns, strict pre-flight check.
image-to-code
Elite website image-to-code skill for Codex. For visually important web tasks, it must first generate the design image(s) itself, deeply analyze them, then implement the website to match them as closely as possible. In Codex, it must prefer large, readable, section-specific images instead of tiny compressed boards…
design-taste-frontend-v1
The original v1 taste-skill, preserved for projects depending on its exact behavior. The current default is design-taste-frontend (v2 experimental), which is a substantial rewrite. Use this v1 install name only if you need exact backward compatibility.
redesign-existing-projects
Upgrades existing websites and apps to premium quality. Audits current design, identifies generic AI patterns, and applies high-end design standards without breaking functionality. Works with any CSS framework or vanilla CSS.
industrial-brutalist-ui
Raw mechanical interfaces fusing Swiss typographic print with military terminal aesthetics. Rigid grids, extreme type scale contrast, utilitarian color, analog degradation effects. For data-heavy dashboards, portfolios, or editorial sites that need to feel like declassified blueprints.
high-end-visual-design
Teaches the AI to design like a high-end agency. Defines the exact fonts, spacing, shadows, card structures, and animations that make a website feel expensive. Blocks all the common defaults that make AI designs look cheap or generic.