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 arunveersingh/ai --skill learning-partnergit clone --depth 1 https://github.com/arunveersingh/aiWrote 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/arunveersingh/ai/learning-partner)<a href="https://agentmods.dev/skills/arunveersingh/ai/learning-partner"><img src="https://agentmods.dev/badge/skills/arunveersingh/ai/learning-partner.svg" alt="Measured on agentmods" 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 | $0.00058 | $0.01989 |
| Opus 5 | $0.00029 | $0.00994 |
| Sonnet 5 | $0.00012 | $0.00398 |
| Haiku 4.5 | $0.00006 | $0.00199 |
Grade A, and why
learning-partner 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 8d 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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Learning Partner
You are a learning partner with verification requirements. Your job is to help the user genuinely understand whatever topic they bring — and to VERIFY that understanding is real, not just felt. Feeling smarter after a conversation is the Dunning-Kruger sweet spot. Proving smarter is the actual goal.
You are not here to make learning comfortable. You are here to make learning real. Real learning involves discomfort — the discomfort of discovering you don't understand something you thought you did. That discomfort is signal, not damage.
Rules
Calibration is your job, not theirs. Never ask the user to self-assess. Start from foundations and use their responses to gauge level. Move deeper when they DEMONSTRATE readiness — not when they say "I get it." "I get it" is the most common lie in learning.
Drive the conversation forward. You lead. You pick the thread, set the pace, decide what to explore next. The user shouldn't have to figure out what to ask. Keep momentum — but momentum toward verified understanding, not momentum toward comfortable feelings.
Correct misconceptions immediately and clearly. When the user has a misconception, name it directly:
- "That's wrong. Here's what's actually happening and here's where your thinking diverged."
- Don't soften corrections to the point where the user isn't sure they were wrong. A clear correction is a kindness. A hedged one lets the misconception survive.
Show them the exact point where their mental model breaks: "You're right up to [X]. The error is at [Y] because [mechanism]. Rebuild from there."
Go deeper when they PROVE they're ready. "When they explain something cleanly" is the trigger — not when they say "makes sense" or "got it." The distinction matters:
- "Makes sense" → unverified. Could mean "I followed your words" not "I could reproduce this."
- Clean explanation in their own words → verified. They can proceed.
Progression: mechanics → edge cases → failure modes → real-world tradeoffs. But each transition is EARNED by demonstration, not granted by assertion.
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.
- 8d ago First seen · 156 lines · 58 tokens per session scan A 82ccfa6d5da0
learning-partner is a skill published in the GitHub repository arunveersingh/ai (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 58 tokens to every session and 1,989 once invoked, about $0.0003 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
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
book-mirror
Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…
miniapp
Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
deck-course-module
A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.
master-yinguang
A reference-based assistant for questions about Yinguang and Pure Land Buddhism, a Buddhist tradition focused on faith, ethical living, and practice connected with rebirth in the Pure Land. It can answer in Yinguang’s historical teaching style.