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 repo-understandgit 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/repo-understand)<a href="https://agentmods.dev/skills/yugash007/edu-agent-skills/repo-understand"><img src="https://agentmods.dev/badge/skills/yugash007/edu-agent-skills/repo-understand/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/repo-understand"><img src="https://agentmods.dev/badge/skills/yugash007/edu-agent-skills/repo-understand.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 | $0.00026 | $0.00614 |
| Opus 5 | $0.00013 | $0.00307 |
| Sonnet 5 | $0.00005 | $0.00123 |
| Haiku 4.5 | $0.00003 | $0.00061 |
Grade A, and why
repo-understand 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 12d 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Create a reliable curriculum map before deep teaching. Prevents shallow file retrieval by forcing the agent to infer learning structure, identify prerequisite dependencies, and recommend coherent starting paths.
Activation
- User asks to learn a repository, course repo, or technical curriculum. User asks "where should I start?" in a multi-module repo. Agent hasn't established module sequence and prerequisites.
- Skip if: user wants a narrow operational task unrelated to learning flow, or repo context is absent and user wants generic theory.
- Routing: run before
teach-concept,socratic-mode,check-understanding, andbuild-with-mefor repo-based learning.
Inputs
- Repository root and visible structure, high-signal docs (README, syllabus, indexes), learner goal and level signals.
Workflow
- Classify — Determine repo type: curriculum-first, project-first, reference-first, or hybrid. Identify learning artifacts (lessons, labs, projects, checkpoints).
- Map Hierarchy — Derive module/phase order from folder structure and docs. Produce a phase map with outcomes per phase.
- Infer Prerequisites — For each phase, list conceptual and tooling prerequisites. Mark dependency edges between phases.
- Estimate Progression — Foundational → applied → advanced. Identify transition points where learners often stall.
- Synthesize Paths — Propose 2–3 path variants based on learner goals and level, with tradeoffs and estimated effort.
- Checkpoint — Ask one decision-forcing question to select a path. Do not start deep instruction before the learner selects or confirms.
Rules
- DO: require a phase map before any deep explanation.
- DO: explain why sequence matters, not just what modules exist.
- DO: provide goal-conditioned paths with tradeoffs — never a single path for all learners.
- DO: surface uncertainty explicitly when repo signals are weak.
- DON'T: quote random files without structural context.
- DON'T: recommend advanced topics before prerequisite chain is visible.
- DON'T: dump long directory trees — cap orientation to phase outcomes and decisions.
- DON'T: invent lessons/modules without evidence — label inferred items as tentative.
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.
- 12d ago First seen · 55 lines · 26 tokens per session scan A 585a93130601
repo-understand is a skill published in the GitHub repository yugash007/edu-agent-skills (7 stars, last pushed 3mo ago), licensed MIT. It adds 26 tokens to every session and 614 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…
scaffold-exercises
Scaffold a graded problem set with sections, problems, worked solutions, and short "why this matters" explainers across analytical, empirical, and coding types. Use when user says "make a problem set on X", "scaffold exercises for this lecture", "create practice problems", "generate homework with a solution key"…