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 ZeKaiNie/universal-examprep-skill --skill confusion-trackergit 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/confusion-tracker)<a href="https://agentmods.dev/skills/zekainie/universal-examprep-skill/confusion-tracker"><img src="https://agentmods.dev/badge/skills/zekainie/universal-examprep-skill/confusion-tracker/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/zekainie/universal-examprep-skill/confusion-tracker"><img src="https://agentmods.dev/badge/skills/zekainie/universal-examprep-skill/confusion-tracker.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 | $0.00058 | $0.01561 |
| Opus 5 | $0.00029 | $0.00781 |
| Sonnet 5 | $0.00012 | $0.00312 |
| Haiku 4.5 | $0.00006 | $0.00156 |
Grade A, and why
confusion-tracker 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.
How it starts
The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
confusion-tracker — concept-confusion tracking
Purpose
Capture the learner's concept-level confusions (why / what / how-derived questions — not quiz answers) during tutoring and record them into the 「概念疑难点记录」 section of study_progress.md, building a pre-exam review list. Used by exam-tutor (while teaching) and exam-review (during the final sweep).
Activation
- During tutoring, when the learner asks a concept question matching: 「为什么…？」/「…是什么、什么意思？」/「这个公式怎么推、怎么来的？」/「…的重点是什么？」/「讲一下…」, or any clarification follow-up that is not a quiz answer.
- Skip for: pure quiz answering (right or wrong), and chit-chat that needs no concept explanation.
Inputs
- The progress-file path (e.g.
study_progress.md), read at session start. - The current chapter/phase name being taught.
Workflow
- Detect — decide whether the follow-up is a concept question (not a quiz item or its answer).
- Answer — give a concise, clear explanation grounded in the current wiki chapter. Label the source: 🟢 来自资料 for material-sourced content, 🟡 AI补充，可能与你老师讲的不完全一致 for AI-supplied background. Never present AI-added content as the teacher's.
- Record — persist the confusion:
关联章节/疑难点(one line) /解答要点(≤2 sentences) /状态(default 待回顾). Ifstudy_state.jsonis absent and Python works, first runpython "${CLAUDE_SKILL_DIR}/scripts/update_progress.py" --workspace <ws> init. The normal and ONLY state-backed write path is thenpython "${CLAUDE_SKILL_DIR}/scripts/update_progress.py" --workspace <ws> add-confusion --chapter <ch> --note <疑难点/解答要点>— the md table is a generated view and a hand-appended row is lost on the next render. Only when Python truly cannot run may the no-Python fallback append directly to the 「## 💡 概念疑难点记录」 table instudy_progress.md, auto-incrementing the序号column. A nonzero state command while Python runs is a fail-loud write failure, not permission to hand-edit.- Persist-first (notebook CLI) — the state row stays exactly as above; ADDITIONALLY persist the full explanation itself (step 2's answer, provenance labels included) so it survives outside chat:
echo <explanation body> | python "${CLAUDE_SKILL_DIR}/scripts/notebook.py" --workspace <ws> add-entry --chapter <ch> --type confusion --id <slug> --title <confusion gist>(body via STDIN; same--idreplaces in place;notebook/index.mdrebuilds; the script resolves from the skill package root). The receipt line then carries the pack-provided link line (zh 「完整解答：notebook/chNN.md#<anchor>｜目录：notebook/index.md」, enFull explanation: notebook/chNN.md#<anchor> | Index: notebook/index.md). On a failed notebook write, TELL the student (the chat explanation already delivered stands as the copy); file-less clients keep chat-only output perexam-cram's capability dispatch.
- Persist-first (notebook CLI) — the state row stays exactly as above; ADDITIONALLY persist the full explanation itself (step 2's answer, provenance labels included) so it survives outside chat:
- Confirm — tell the learner it was logged (e.g. 「已记录到疑难点」) in one short line, without breaking the teaching flow.
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 · 45 lines · 58 tokens per session scan A 77bf715b3bdb
confusion-tracker is a skill published in the GitHub repository ZeKaiNie/universal-examprep-skill (281 stars, last pushed 8d ago), licensed MIT. It adds 58 tokens to every session and 1,561 once invoked, about $0.0003 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
bq-skill
A coaching workflow for building a reusable library of truthful stories for behavioral job interviews. It uses structures such as STAR—Situation, Task, Action, Result—and can connect stories to a job description and résumé.
PersonaLingo
A guided tool for creating personalised IELTS speaking practice materials. IELTS is an English exam, and the tool turns a learner’s answers and conversation into a personal profile and a static study website.
learning-mode
Guide active, hands-on learning without completing the chosen learning target for the learner. Use when the user explicitly wants to learn, practice, master, or build something themselves with guidance, especially when a technology or concept is new to them. Diagnose the smallest missing prerequisite, guide prediction…
html-effectiveness-research
A guide for explaining how a feature works in a code repository or how an abstract technical idea works. It can structure the explanation with a summary, expandable steps, code views, questions and answers, or an interactive visual.
teach
Use when the user wants to learn or be taught a topic interactively over multiple turns, with the agent acting as tutor rather than answer-giver. Triggers on phrases like "teach me", "tutor me", "quiz me", "let's learn", "help me understand X by working through it step by step", or any request framed around learning a…
canvas
Fetch Canvas LMS courses and assignments via API token.