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 deep-divegit 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/deep-dive)<a href="https://agentmods.dev/skills/yugash007/edu-agent-skills/deep-dive"><img src="https://agentmods.dev/badge/skills/yugash007/edu-agent-skills/deep-dive/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/deep-dive"><img src="https://agentmods.dev/badge/skills/yugash007/edu-agent-skills/deep-dive.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 | $0.00029 | $0.00778 |
| Opus 5 | $0.00015 | $0.00389 |
| Sonnet 5 | $0.00006 | $0.00156 |
| Haiku 4.5 | $0.00003 | $0.00078 |
Grade A, and why
deep-dive 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Take a learner from surface understanding to genuine depth on a single concept. Assumes the learner has a working mental model and pushes into mechanism, failure modes, tradeoffs, and production implications. Exit condition: learner can reason about the concept in novel, constrained contexts.
Activation
- Learner asks to go deeper on a known concept.
check-understandingconfirms surface competence but weak mechanism knowledge. Interview prep or architectural decision needs depth. - Skip if: beginner encountering concept for the first time →
teach-concept. Needs immediate practical help →build-with-me/debug-teacher. Has a misconception →misconception-detectorfirst. - Routing: confirm current level with a quick probe before starting. Pair with
challenge-generatorat the end for advanced application.
Inputs
- Target concept, confirmed current understanding level, motivating context (interview/architecture/debugging), known gaps or questions.
Depth Ladder
Five rungs, each confirmed before ascending:
- Surface — Definition and intuition → "State this in one sentence."
- Mechanism — Step-by-step how it works → "Trace a concrete execution."
- Tradeoffs — When it works vs. doesn't → "What would you choose instead, and why?"
- Edge Cases — Boundaries and failures → "What breaks this?"
- Production — Real-world tuning, monitoring, debugging → "How would you debug this at 3am?"
Workflow
- Entry Check — Ask one question to confirm starting rung. Skip confirmed rungs; jump to the frontier.
- Mechanism (Rung 2) — Walk through with a concrete worked trace. Require learner to narrate it back.
- Tradeoffs (Rung 3) — Present a decision context. Elicit learner's reasoning before canonical analysis. Include one case where the naive choice is wrong.
- Edge Cases (Rung 4) — Pose 2–3 edge case questions. Require learner to surface them first, then supplement. For each: symptom + fix.
- Production (Rung 5) — Observability, performance under load, tuning knobs, known failure patterns. Ground in a realistic system. Ask: "If this broke at 3am, what's your investigation sequence?"
- Exit Synthesis — Ask learner to produce a one-paragraph explanation for someone who just learned the basics.
What ships with it
2 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.
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 · 62 lines · 29 tokens per session scan A 3191480d8acf
deep-dive is a skill published in the GitHub repository yugash007/edu-agent-skills (7 stars, last pushed 3mo ago), licensed MIT. It adds 29 tokens to every session and 778 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.
evidence-based-classroom-designer
Design or redesign any course, class, or training session using evidence-based instructional principles. Use this skill when a teacher, instructor, or instructional designer wants to improve student retention and achievement through classroom design, course design, quiz design, or active learning strategies — even if…
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…