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/zekainie/universal-examprep-skill/fullnpx skills add ZeKaiNie/universal-examprep-skill --skill fullgit clone --depth 1 https://github.com/ZeKaiNie/universal-examprep-skillWrote 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/zekainie/universal-examprep-skill/full)<a href="https://agentmods.dev/skills/zekainie/universal-examprep-skill/full"><img src="https://agentmods.dev/badge/skills/zekainie/universal-examprep-skill/full.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 5.1 | $0.00140 | $0.02281 |
| Opus 5 | $0.00070 | $0.01141 |
| Sonnet 5 | $0.00028 | $0.00456 |
| Haiku 4.5 | $0.00014 | $0.00228 |
Grade A, and why
universal-exam-cram-coach 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 2d 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.
This is a copy
100% identical to exam-cram-coach — 100 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Universal Exam Cram Coach — Root Router
This language-neutral router dispatches last-minute exam prep to the chapter-wiki, bank-only, persistent control layer and its wording packs; it is not a duplicate manual.
Language dispatch
Read the canonical, language-neutral study_state.json.language code and load the matching compatibility entry plus its per-skill wording pack BEFORE emitting any student-visible output:
zh(display choice中文) →locales/zh/SKILL.mdplus the selected sub-skill's zh wording pack underlocales/zh/skills/en(display choiceEnglish) →locales/en/SKILL.mdplus the selected sub-skill's en wording pack underlocales/en/skills/bilingual(display choice双语) → compose the zh and en wording block by block, with zh first and a> EN:mirror for each block (composition rules indocs/language-policy.md)
中文, English, and 双语 remain accepted user-facing input aliases. On first contact one combined ask sets mode, budget, and language, then show the independent material-processing choice 轻量按需（推荐） / 完整建库; exam_start.py confirm persists them with the exact workspace/materials receipt. Missing, urgent, accepted-default, and legacy processing choices mean lightweight; only explicit full opens complete ingestion. A later reconfirm with no processing flag preserves an existing canonical choice. Later update_progress.py set --language applies next turn. Default English unless the student opened in Chinese; bilingual is explicit-only.
Control layer (behavior)
Behavior lives in skills/exam-cram/SKILL.md and these subskills:
| Sub-skill | Role |
|---|---|
exam-ingest |
Build/validate workspace |
exam-tutor |
Lazy chapter teaching |
exam-study-guide |
Typed guide and visual artifact gate |
exam-quiz |
Bank-only selection/grading |
exam-review |
Replay mistakes/confusions |
exam-cheatsheet |
Final handout |
exam-audit |
Read-only workspace health check |
exam-help |
Quick reference |
confusion-tracker |
Concept-confusion tracking |
What ships with it
60 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.
- .gitattributes 1.5 KB
- .github/workflows/ci.yml 1.9 KB
- .gitignore 659 B
- AGENTS.md 39 KB
- assets/exam-panic.png 934 KB
- benchmark/.gitignore 1.1 KB
- benchmark/aggregate_matrix.py 16 KB runs code
- benchmark/behavior_smoke/fixtures/mini_course_nostate/references/assets/venn_prompt.svg 677 B
- benchmark/behavior_smoke/fixtures/mini_course_nostate/references/quiz_bank.json 3.2 KB
- benchmark/behavior_smoke/fixtures/mini_course_nostate/references/wiki/ch1_stack_queue.md 447 B
- benchmark/behavior_smoke/fixtures/mini_course_nostate/references/wiki/ch2_trees.md 493 B
- benchmark/behavior_smoke/fixtures/mini_course_nostate/study_plan.md 550 B
- benchmark/behavior_smoke/fixtures/mini_course_nostate/study_progress.md 429 B
- benchmark/behavior_smoke/fixtures/mini_course/references/assets/venn_prompt.svg 677 B
- benchmark/behavior_smoke/fixtures/mini_course/references/quiz_bank.json 4.5 KB
- benchmark/behavior_smoke/fixtures/mini_course/references/wiki/ch1_stack_queue.md 447 B
- benchmark/behavior_smoke/fixtures/mini_course/references/wiki/ch2_trees.md 493 B
- benchmark/behavior_smoke/fixtures/mini_course/study_plan.md 550 B
- benchmark/behavior_smoke/fixtures/mini_course/study_progress.md 429 B
- benchmark/behavior_smoke/fixtures/mini_course/study_state.json 390 B
- benchmark/behavior_smoke/mock/sample_outputs/artifact_mode_chat_auto_pdf_bad.txt 433 B
- benchmark/behavior_smoke/mock/sample_outputs/artifact_mode_chat_good.txt 462 B
- benchmark/behavior_smoke/mock/sample_outputs/artifact_mode_chat_not_persisted_bad.txt 186 B
- benchmark/behavior_smoke/mock/sample_outputs/artifact_mode_one_shot_good.txt 490 B
- benchmark/behavior_smoke/mock/sample_outputs/artifact_mode_one_shot_persist_bad.txt 605 B
- benchmark/behavior_smoke/mock/sample_outputs/artifact_mode_one_shot_probe_error_bad.txt 507 B
- benchmark/behavior_smoke/mock/sample_outputs/artifact_mode_visual_native_good.txt 495 B
- benchmark/behavior_smoke/mock/sample_outputs/artifact_mode_visual_preflight_failed_bad.txt 487 B
- benchmark/behavior_smoke/mock/sample_outputs/artifact_mode_visual_subscription_guess_bad.txt 507 B
- benchmark/behavior_smoke/mock/sample_outputs/hint_skip_offer.txt 349 B
- benchmark/behavior_smoke/mock/sample_outputs/language_ask_good.txt 461 B
- benchmark/behavior_smoke/mock/sample_outputs/language_ask_missing_line.txt 270 B
- benchmark/behavior_smoke/mock/sample_outputs/language_ask_unglossed.txt 211 B
- benchmark/behavior_smoke/mock/sample_outputs/language_persist_good.txt 216 B
- benchmark/behavior_smoke/mock/sample_outputs/language_persist_noncanonical.txt 157 B
- benchmark/behavior_smoke/mock/sample_outputs/language_urgent_bilingual_explicit.txt 372 B
- benchmark/behavior_smoke/mock/sample_outputs/language_urgent_bilingual_negated.txt 306 B
- benchmark/behavior_smoke/mock/sample_outputs/language_urgent_bilingual.txt 261 B
- benchmark/behavior_smoke/mock/sample_outputs/language_urgent_question.txt 224 B
- benchmark/behavior_smoke/mock/sample_outputs/language_urgent_silent.txt 364 B
- benchmark/behavior_smoke/mock/sample_outputs/language_urgent_wrong_language.txt 262 B
- benchmark/behavior_smoke/mock/sample_outputs/notebook_persist_chat_only.txt 952 B
- benchmark/behavior_smoke/mock/sample_outputs/notebook_persist_good.txt 744 B
- benchmark/behavior_smoke/mock/sample_outputs/progress_after_confusion.md 395 B
- benchmark/behavior_smoke/mock/sample_outputs/progress_after_mistake.md 403 B
- benchmark/behavior_smoke/mock/sample_outputs/provenance_answer.txt 492 B
- benchmark/behavior_smoke/mock/sample_outputs/quiz_output_good.txt 351 B
- benchmark/behavior_smoke/mock/sample_outputs/quiz_output_invented.txt 317 B
- benchmark/behavior_smoke/mock/sample_outputs/resume_message.txt 224 B
- benchmark/behavior_smoke/mock/sample_outputs/scope_override_good.txt 258 B
- benchmark/behavior_smoke/mock/sample_outputs/scope_override_missing.txt 127 B
- benchmark/behavior_smoke/mock/sample_outputs/teaching_template_ai_answer_good.txt 1.2 KB
- benchmark/behavior_smoke/mock/sample_outputs/teaching_template_formula_first.txt 1.1 KB
- benchmark/behavior_smoke/mock/sample_outputs/teaching_template_good.txt 1.2 KB
- benchmark/behavior_smoke/mock/sample_outputs/teaching_template_liberal_good.txt 1.4 KB
- benchmark/behavior_smoke/mock/sample_outputs/teaching_template_missing_warn.txt 608 B
- benchmark/behavior_smoke/mock/sample_outputs/teaching_template_no_source.txt 1.1 KB
- benchmark/behavior_smoke/mock/sample_outputs/teaching_template_optin_closers.txt 1.5 KB
- benchmark/behavior_smoke/mock/sample_outputs/teaching_template_skip_ask.txt 948 B
- benchmark/behavior_smoke/mock/sample_outputs/teaching_template_unlabeled_source.txt 517 B
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.
- 2d ago First seen · 53 lines · 140 tokens per session scan A 300cf9d8ef15
universal-exam-cram-coach is a skill published in the GitHub repository ZeKaiNie/universal-examprep-skill (280 stars, last pushed 4d ago), licensed MIT. It adds 140 tokens to every session and 2,281 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to exam-cram-coach, differing in 100 lines, and is treated as a copy.
Other skills, from other repositories
deeptutor-cli
Configure, manage, and use DeepTutor through its CLI, including capabilities, knowledge bases, partners, memory, sessions, notebooks, providers, skills, and the server or Web app.
paper-explainer
科研论文解读：解析 arXiv/PDF 的公式与图表，提炼问题、贡献、方法、关键图和结论，再产出 B站/视频号解读视频或知乎/公众号图文。 当用户说“论文解读、讲论文、论文转视频/图文、科研科普、arXiv、学术视频”时使用。 本 SKILL 从论文做内容；video-to-article 从视频做图文，doc-convert 只转换文档格式。.
bq-skill
行为面试 skill。帮求职者挖掘真实经历、用 STAR/CAR 结构化、映射能力标签、构建可复用的中英双语故事库（Story Bank）；并能接入 JD + 简历，针对具体岗位生成 Top 20 BQ 选题 + 基于真实经历的 STAR 准备模板（HTML 报告）。不是背答案，而是建立可复用的职业叙事体系，让任何行为面试题都能自然作答。关键词：behavioral question, BQ, 行为面试, STAR, 故事库, Amazon LP, 职业故事, tell me about a time, 面试准备, JD 面试题预测, top 20 题。.
bloom-tutor
Use when 用户想以一对一苏格拉底导师的方式系统学习一个课题——开一门新课、推进课题的下一篇、提交学习反馈或说「我读完了」、或整理/查看学习日志。基于 Bloom 2 Sigma 的交互式学习系统。触发词：开个文件夹学X、我想学X、帮我学X、继续、下一篇、我读完了、整理学习、查看学习日志、interactive Socratic tutoring、Bloom 2 sigma learning。.
nihaixia
倪海厦（1954-2012）台湾中医师，经方派代表人物，汉唐中医创始人。核心心智模型：六经辨证、阳气论、经典至上、经方为主。决策启发式：先辨六经再选方、阳气不足先扶阳、经典原方最可靠。触发词：倪海厦、海厦视角、中医倪海厦、经方思维、倪海厦会怎么看、倪师。知识库覆盖：伤寒论条文补齐（太阳下篇+阳明篇，modules/13）+伤寒论129条全（modules/01）+金匮23篇+黄帝内经72篇+针灸教程+神农本草经374种+天纪+1257例全量结构化医案+243例分类叙事医案+梁冬对话+口述表达DNA+六经辨证诊断公式（8个公式+快速诊断流程图+脉舌速查+合病并病速查+真寒假热鉴别+七步走思维模式）。基于一手素材：梁冬对话录音稿、人纪班…
thesis-defense-pptx
Create, polish, and quality-check editable undergraduate or graduate thesis defense PowerPoint decks from a local thesis PDF/LaTeX project and an existing PPTX template. Use when the user asks for a formal defense PPT, thesis presentation, academic答辩PPT, template-matched PPTX, or local PowerPoint deck generation with…