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 yugash007/edu-agent-skills --skill check-understandinggit clone --depth 1 https://github.com/yugash007/edu-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/yugash007/edu-agent-skills/check-understanding)<a href="https://agentmods.dev/skills/yugash007/edu-agent-skills/check-understanding"><img src="https://agentmods.dev/badge/skills/yugash007/edu-agent-skills/check-understanding/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/yugash007/edu-agent-skills/check-understanding"><img src="https://agentmods.dev/badge/skills/yugash007/edu-agent-skills/check-understanding.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00023 | $0.00467 |
| Opus 5 | $0.00012 | $0.00234 |
| Sonnet 5 | $0.00005 | $0.00093 |
| Haiku 4.5 | $0.00002 | $0.00047 |
Grade A, and why
check-understanding 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 11d 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
Purpose
Assess conceptual and practical understanding using reasoning-first prompts, then adapt teaching based on detected weak areas.
Activation
- Concept explanation just completed. Learner claims understanding and needs validation. Repeated related mistakes. Readiness check needed before advancing.
- Skip if: no concept context established, or user explicitly declines assessment.
- Routing: pair with
teach-conceptfor explanation→assessment loops. Escalate tosocratic-modewhen misconceptions persist.
Inputs
- Target concept(s), learner level, prior mistakes/confusion signals, repo/project context.
Workflow
- Target — Select 1–2 concepts being validated.
- Question — Generate tiered questions: conceptual reasoning, practical application, debugging/diagnostic.
- Evaluate — Grade reasoning quality, not keyword match.
- Classify — Categorize mistakes: misconception, partial model, or execution gap.
- Correct — Explain root cause and provide corrected model.
- Recheck — One follow-up question to confirm recovery.
Rules
- DO: test reasoning and transfer, not memorization.
- DO: use plausible distractors in MCQ format.
- DO: explain why an answer fails, not just that it's wrong.
- DO: track weak areas across turns when context allows.
- DON'T: use only right/wrong labels — always output mistake type and remediation.
- DON'T: end without a recheck after correction.
- DON'T: ignore repeated weak areas — log and prioritize them.
Output
Responses should contain: concepts under assessment, questions (conceptual + practical + diagnostic), evaluation (strengths, weak areas, mistake types), corrective feedback, and recheck question. Format naturally.
Checklist
- Includes conceptual and practical checks.
- Mistakes categorized, not just scored.
- Corrective feedback explains root cause.
- Follow-up recheck present.
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.
- 11d ago First seen · 54 lines · 23 tokens per session scan A fbcd0be7500d
check-understanding is a skill published in the GitHub repository yugash007/edu-agent-skills (7 stars, last pushed 3mo ago), licensed MIT. It adds 23 tokens to every session and 467 once invoked, about $0.0001 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
learning-coach
A Chinese-language personal coaching guide for learning programming, AI agents, writing, languages, exams, research, or career skills through real projects and tasks. It tracks progress and teaches one useful action at a time.
understand-explain
Use when you need a deep-dive explanation of a specific file, function, or module in the codebase.
baoyu-comic
A tool for creating original educational comics that explain knowledge or ideas through multiple illustrated panels. It supports different art styles and tones and can create several comics in one batch.
ctf-misc
Provides miscellaneous CTF challenge techniques for problems that do not cleanly fit the main categories. Use for encoding puzzles, pyjails, bash jails, RF/SDR, DNS oddities, unicode tricks, esoteric languages, QR or audio puzzles, constraint solving, game theory, unusual sandbox escapes, and hybrid logic puzzles.…
respond-to-eval
Turn student course evaluations (free-text + numeric) into an actionable teaching-improvement plan — the teaching analogue of /respond-to-referees. Clusters comments into themes, separates signal from noise, classifies each theme Keep / Change / Investigate / Out-of-scope, and drafts concrete changes mapped to the…
slide-excellence
Multi-agent comprehensive slide review (visual + pedagogy + proofreading, plus TikZ / parity / substance conditionally). Use when user says "full review", "excellence pass", "comprehensive check", "review everything", "pre-release review", "slide excellence", or before teaching / shipping a deck. Fanout wrapper — for…