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 HumphreySun98/Smart-Study-Agent --skill smartstudygit clone --depth 1 https://github.com/HumphreySun98/Smart-Study-AgentWrote 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/humphreysun98/smart-study-agent/smartstudy)<a href="https://agentmods.dev/skills/humphreysun98/smart-study-agent/smartstudy"><img src="https://agentmods.dev/badge/skills/humphreysun98/smart-study-agent/smartstudy/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/humphreysun98/smart-study-agent/smartstudy"><img src="https://agentmods.dev/badge/skills/humphreysun98/smart-study-agent/smartstudy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00072 | $0.00610 |
| Opus 5.5 | $0.00029 | $0.00244 |
| Sonnet 5.5 | $0.00014 | $0.00122 |
| Haiku 4.5 | $0.00007 | $0.00061 |
Grade A, and why
smartstudy 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 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.
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.
SmartStudy Coach
You are running inside a repo (or machine) that has the SmartStudy Agent installed. Drive its Python API to run a real adaptive study session — do not simulate the scheduling yourself; the FSRS scheduler and RL policy are the source of truth.
Session flow (OPEAA loop)
- Observe — get the material (user paste, file, or URL the user provides).
from smartstudy_agent import SmartStudyAgent agent = SmartStudyAgent() # auto-picks backend; mock works offline observed = agent.observe(lecture_text) - Plan —
plan = agent.plan(observed), then presentplan.sequencewith its rationale. Respect the concept-graph order. - Act — for the chosen topic,
agent.act(topic, description, n=3). Present ONE question at a time; wait for the user's answer letter. - Evaluate —
agent.evaluate(questions, answers). Report the score and explain misses using each question'sexplanation. - Adapt —
agent.adapt(topic, evaluation). Tell the user the policy's action (advance/reinforce/review) and why.
Persistence (do this every session)
import storage
record = storage.load_student(name) # creates if missing
# ... after adapt():
record["topics_mastered"] = agent.profile.topics_mastered
record["weak_areas"] = agent.profile.weak_areas
record["quiz_history"] = agent.profile.quiz_history
storage.save_student(name, record)
storage.add_questions(name, [vars(q) for q in questions]) # feeds Anki export
What's due today
from spaced_repetition import get_review_queue, get_full_schedule
due = get_review_queue(record["quiz_history"]) # FSRS: weakest memories first
Open every session by checking this queue. If something is due, recommend reviewing it BEFORE new material, and say the recall probability.
Anki hand-off
If the user wants flashcards: from anki_export import export_student_deck; export_student_deck(name) and tell them the .apkg path.
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 · 62 lines · 72 tokens per session scan A 6d7ae03712cb
smartstudy is a skill published in the GitHub repository HumphreySun98/Smart-Study-Agent (57 stars, last pushed 2mo ago), licensed MIT. It adds 72 tokens to every session and 610 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
academic-paper-reviewer
Simulates academic peer review, evaluating papers across Originality, Methodology, Results, and Writing to provide Major/Minor Revision recommendations with actionable feedback. Triggers when a user asks to "review my paper," "simulate peer review," or "give my paper a peer review.
dev-guide-generator
Generates complete technical tutorials from prerequisites and environment setup to core steps, troubleshooting, and a final cheatsheet. Trigger on requests to write a tutorial, create a setup guide, organize steps for beginners, or keywords like step-by-step, quickstart, or how-to guide.
llmtornado-tutorial-generator
Generates comprehensive code tutorials on LlmTornado API formatted for Medium publication with examples, explanations, and best practices.
interview-prep
Job interview prep: prepare, practice, revise; technical, behavioral or placement interview; mock interview questions.
interview-prep
Technical interview preparation expert for algorithms, system design, and behavioral questions.
improve
Critique an outside idea (a pasted tip, post, transcript or video summary) against what this system already has. Use when the founder pastes something and asks whether to adopt it, or says 'improve', 'should we do this', 'compare this to what we have'. Grounded by scripts/improveground.py in the lessons corpora and…