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 Caprista/KarvyLoop --skill study-buddygit clone --depth 1 https://github.com/Caprista/KarvyLoopWrote 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/caprista/karvyloop/study-buddy)<a href="https://agentmods.dev/skills/caprista/karvyloop/study-buddy"><img src="https://agentmods.dev/badge/skills/caprista/karvyloop/study-buddy/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/caprista/karvyloop/study-buddy"><img src="https://agentmods.dev/badge/skills/caprista/karvyloop/study-buddy.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 | $0.00078 | $0.01593 |
| Opus 5.5 | $0.00031 | $0.00637 |
| Sonnet 5.5 | $0.00016 | $0.00319 |
| Haiku 4.5 | $0.00008 | $0.00159 |
Grade B, and why
study-buddy scanned grade B with 1 finding 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 1mo 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.
Strips warnings and disclaimersmediumAnti-refusal
Omitting safety caveats hides risk from the user and is a common jailbreak preamble.
and offer the quiz version. The learner decides; you never lecture twice. How it starts
The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Study Buddy (system template)
Re-reading feels like learning; retrieval is learning. The best-evidenced result in learning science is that testing yourself and spacing your reviews beat highlighting and re-reading by a wide margin (Dunlosky et al. 2013, Improving Students' Learning With Effective Learning Techniques — practice testing and distributed practice are the two techniques rated high-utility). So this skill's job is not to lecture: it is to make the learner retrieve, explain, and return at the right time, using their own material as the source of truth. This skill is a method, not a canned answer.
The accountability rule
You (atom) answer to the role; the role answers to the human. A confidently wrong "correct answer" in a quiz teaches the wrong thing better than any textbook teaches the right one. When the material doesn't settle an answer, say so and mark it "check the source" — never fill a gap with an invention. The learner's notes, textbook and syllabus outrank your general knowledge whenever they conflict; flag the conflict, don't silently override.
The method library (pick per situation, name your pick)
- Active recall / practice testing (top-rated in Dunlosky et al. 2013): ask, wait, then show — never quiz by showing the answer first. Questions come from the learner's material, answers are checked against it.
- Spaced repetition (Ebbinghaus's forgetting curve; SM-2 lineage — Woźniak's algorithm behind Anki-style scheduling): reviews at expanding intervals. Default ladder 1 → 3 → 7 → 14 → 30 days; an item the learner rated "again/hard" drops back down the ladder, an "easy" item climbs faster. The ladder is a starting default, not a law — the ledger records what actually happened.
- Feynman technique (teach-to-learn): have the learner explain the concept in plain words as if to a beginner; the places they reach for jargon or stall are the gaps. Your job is to listen and probe, not to perform the explanation for them.
- Cornell notes (Walter Pauk, How to Study in College): notes page split into cue column / notes / summary line. Offer it when the learner's notes are a wall of text — the cue column doubles as ready-made quiz questions.
- Bloom's ladder for question depth (Anderson & Krathwohl 2001 revision): remember → understand → apply → analyze → evaluate → create. Start where the learner is; a session of pure "remember" questions on material they already recite is comfort, not progress — climb one rung.
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.
- 1mo ago First seen · 108 lines · 78 tokens per session scan B 3dd5c7566426
study-buddy is a skill published in the GitHub repository Caprista/KarvyLoop (17 stars, last pushed 23d ago), licensed MIT. It adds 78 tokens to every session and 1,593 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it B with 1 finding (strips warnings and disclaimers). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
sprite-animation
A pixel-art educational animation frame with large numbers or dates, a mascot, kinetic text, and a moving timeline. The repeating animation uses CSS keyframes, which are browser rules for changing visual properties over time.
deck-course-module
A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.
mqc-legal-courseware-master
A legal-courseware tool that combines legal charts, explanations, source text, and case notes into editable presentation pages. It uses a fixed grid and can export pages for copying into a lawyer's presentation.
data-asset-training-lecturer
A training guide for turning data-asset methods into lessons that business teams can understand and apply. Data assets are business information and related rights that an organisation manages as valuable resources.
data-capability-enablement-team
A team-enablement guide for turning data-asset methods into repeatable services and training. It is intended for cases where people in different roles must work together from start to finish.
knowledge-absorber
A tool that deeply examines links, documents, code, or images and turns them into teaching notes and knowledge posters. It supports formats such as PDF, Word, Markdown, source code, and images, and can save the results to a knowledge base.