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 cosmicstack-labs/mercury-agent-skills --skill learning-sciencegit clone --depth 1 https://github.com/cosmicstack-labs/mercury-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/cosmicstack-labs/mercury-agent-skills/learning-science)<a href="https://agentmods.dev/skills/cosmicstack-labs/mercury-agent-skills/learning-science"><img src="https://agentmods.dev/badge/skills/cosmicstack-labs/mercury-agent-skills/learning-science.svg" alt="Measured on agentmods" 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 | $0.00025 | $0.00527 |
| Opus 5 | $0.00013 | $0.00264 |
| Sonnet 5 | $0.00005 | $0.00105 |
| Haiku 4.5 | $0.00003 | $0.00053 |
Grade A, and why
learning-science 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 4d 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.
What it actually says
Learning Science
Evidence-based techniques that make learning stick.
Core Techniques
1. Active Recall
What: Test yourself instead of re-reading. Why: Retrieving information strengthens neural pathways.
Instead of re-reading notes → Close the book and summarize from memory.
2. Spaced Repetition
| Review | Timing |
|---|---|
| First | 1 day |
| Second | 3 days |
| Third | 1 week |
| Fourth | 2 weeks |
| Fifth | 1 month |
Tool: Anki or any spaced repetition app.
3. Interleaving
What: Mix different topics in one study session. Why: Forces brain to discriminate between concepts.
Instead of "Chapter 1 problems all day" → Mix Chapter 1, 2, and 3 problems.
4. Dual Coding
What: Combine words and visuals. Why: Two mental representations = stronger memory.
Draw diagrams, mind maps, flowcharts — not just text notes.
5. Elaboration
What: Explain concepts in your own words with examples. Why: Deeper processing creates richer memory traces.
"How would I explain this to a 10-year-old? What's a real-world example?"
Study Session Structure
Pomodoro + Active Recall
25 min focused study (active recall, no passive reading)
5 min break (stand, stretch, hydrate)
25 min active practice (problems, self-test)
5 min break
25 min review/spaced repetition
Metacognition
- Before studying: What do I already know? What's my goal?
- During: Am I understanding this? Should I re-read or practice?
- After: What worked? What was confusing? What should I review tomorrow?
Common Myths
❌ Learning styles (visual/auditory/kinesthetic) are not supported by evidence ❌ Highlighting and re-reading are low-utility techniques ❌ Multitasking impairs learning — single-task ✅ Struggle is part of learning — desirable difficulties
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.
- 4d ago First seen · 73 lines · 25 tokens per session scan A 50d740a7f30f
learning-science is a skill published in the GitHub repository cosmicstack-labs/mercury-agent-skills (471 stars, last pushed 14d ago), licensed MIT. It adds 25 tokens to every session and 527 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 2026-09-03.
Other skills, from other repositories
math-olympiad
Solve competition math problems (IMO, Putnam, USAMO, AIME) with adversarial verification that catches the errors self-verification misses. Activates when asked to 'solve this IMO problem', 'prove this olympiad inequality', 'verify this competition proof', 'find a counterexample', 'is this proof correct', or for any…
google-agents-cli-onboarding
Onboarding entrypoint for agents-cli in Agent Platform. It should be used when the user wants to "create a new agent", "develop an agent", "build an agent using ADK", "run the agent locally", "debug agent code", "test an agent", "evaluate an agent", "deploy an agent", "publish an agent", "monitor an agent", or needs…
edu-math-tutorial
A Chinese-language guide for turning a maths problem into a step-by-step teaching video. It explains how to break down the solution, write narration, format equations, and structure scenes.
practice-cognition
A method for testing ideas in practice, learning from the results, and improving the next attempt through repeated cycles.
81-pipecat
Create your Pipecat skill from official documentation, then learn to improve it throughout the chapter.
35-google-adk-reliable-agents
Create your Google Agent Development Kit skill in one prompt, then learn to improve it throughout the chapter.