Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add yarikleto/claude-teacher-plugin/plugin install claude-teacherWrote 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/yarikleto/claude-teacher-plugin/reset-edu)<a href="https://agentmods.dev/skills/yarikleto/claude-teacher-plugin/reset-edu"><img src="https://agentmods.dev/badge/skills/yarikleto/claude-teacher-plugin/reset-edu/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/yarikleto/claude-teacher-plugin/reset-edu"><img src="https://agentmods.dev/badge/skills/yarikleto/claude-teacher-plugin/reset-edu.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 | $0.00486 |
| Opus 5 | $0.00013 | $0.00243 |
| Sonnet 5 | $0.00005 | $0.00097 |
| Haiku 4.5 | $0.00003 | $0.00049 |
Grade A, and why
reset-edu 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.
How it starts
The opening of the file, as written. The whole thing — 28 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reset Education Data
Read ${CLAUDE_PLUGIN_ROOT}/references/education-data.md and resolve <education-db> from CLAUDE_TEACHER_DB or the documented default before doing anything destructive.
1. Inspect the deletion target
Resolve the canonical absolute path and inspect its contents. Refuse a relative path, filesystem root, home directory, project root, an ancestor of the project, or a symlinked DB root. Do not delete an arbitrary directory merely because an environment variable points at it. A valid target contains only the expected education entries: student.json, dashboard.json, topics/, quizzes/, sessions/, and docs/. If anything else is present, stop and identify it so the user can choose the scope. Do not follow symlinks inside the DB into other directories.
If the database is already absent, say so and stop.
2. Confirm the concrete scope
Show the resolved path and explain that its student profile, quiz records, topic progress, session logs, and global saved explanations will be permanently removed across all learning projects using this DB. State that project-local docs/, CLAUDE.md, settings, and learning markers remain.
Ask: “Type YES to permanently delete this database.” Wait for a new response; only YES (case-insensitive) confirms. Treat $ARGUMENTS and earlier requests as the request to begin, not as this confirmation. Any other response cancels.
3. Delete and verify
Recheck that the canonical target and contents still match what was shown. Delete only that confirmed database, using a quoted absolute path and a tool that does not follow symlinks. Never interpolate the path into shell source or use broad wildcards. Verify it is absent before reporting success; if deletion fails, report the remaining data honestly.
Tell the student /claude-teacher:init-edu starts fresh. Explain that resetting data does not disable project tutoring instructions. To pause hook reminders, set enabled: false in .claude/claude-teacher.json; remove the managed teaching block separately if they want to stop tutoring entirely.
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 Changed · -15 lines · -3 tokens per session scan C → A 3a68ea30aac0
- 10d ago First seen · 43 lines · 29 tokens per session scan C 771888a2e8a1
reset-edu is a skill published in the GitHub repository yarikleto/claude-teacher-plugin (8 stars, last pushed 4d ago), licensed MIT. It adds 26 tokens to every session and 486 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
learn-anything
A source-grounded adaptive tutor that tracks proof of mastery rather than content completion. Use it to learn a topic systematically, build a course from PDFs, webpages, transcripts or notes, practice retrieval and transfer, resume a long-running course, or verify whether the learner can recall and apply what they…
learn-by-ai
Run long-term, evidence-based adaptive learning and reconnect named study requests to local project records across sessions. Use when a learner says to start, continue, or resume learning a subject; for systematic study plans, source-grounded teaching, layered practice, review, or maintaining a knowledge graph and…
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…
fyuu-tutor
Operate long-running, document-backed tutoring projects that turn trusted materials or goals into adaptive HTML lessons, practice, and evidence-guided next steps. Use when creating, continuing, reviewing, or handing off a private learning project; auditing source materials; planning a curriculum; generating lessons or…
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…
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.