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 ayberkcansever/ai-skills --skill learngit clone --depth 1 https://github.com/ayberkcansever/ai-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/ayberkcansever/ai-skills/learn)<a href="https://agentmods.dev/skills/ayberkcansever/ai-skills/learn"><img src="https://agentmods.dev/badge/skills/ayberkcansever/ai-skills/learn/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/ayberkcansever/ai-skills/learn"><img src="https://agentmods.dev/badge/skills/ayberkcansever/ai-skills/learn.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 | $0.00176 | $0.08873 |
| Opus 5 | $0.00088 | $0.04437 |
| Sonnet 5 | $0.00035 | $0.01775 |
| Haiku 4.5 | $0.00018 | $0.00887 |
Grade A, and why
learn 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 9d 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 — 348 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Learn — tech radar brief
Goal: take a tech topic and get the user to a correct 101 level in minimal time — a working mental model, the current state of play, and real hands-on muscle. Not expert depth; expert-shaped fundamentals. Recent material only. Every claim dated and sourced.
Written for a senior engineer who ships production systems: bias toward how-to-think-about-it, maturity, and tradeoffs over feature lists and launch hype. The output must survive two tests: (a) a tech lead could make an adopt/trial/hold/avoid call from it, and (b) after the lab + quiz, the user can explain the topic's core mechanism in their own words without being wrong.
The learning loop
The skill delivers learning in escalating, optional stages — each stage is skippable, but the order is fixed:
1. Brief ~10 min read → mental model + state of play + verdict
2. Learn-it-fast ≤ half day → 3-5 curated resources, time-budgeted, in order
3. Lab ~1-1.5 hours → agent ships working code; user predicts, runs, explains
4. Quiz ~10 min → retrieval practice; wrong answers corrected with sources
Stage 1 always happens. Stages 2-3-4 are offers the user takes or leaves. Muscle comes from 3 and 4; the brief alone is recognition-level knowledge, and the skill should say so when offering the lab.
Topic discovery: when the user doesn't have a topic and asks "what should I learn?", that is the sibling tech-radar skill (~/.cursor/skills/tech-radar/) — it scans the recent landscape, dedupes against this library, and hands ranked topics back to this skill.
Storage
Every brief is saved to disk automatically as a self-contained HTML file, never into the current repo/cwd:
~/Documents/tech-briefs/<Category>/<topic-slug>.html
~/Documents/tech-briefs/index.html # auto-generated landing page
~/Documents/tech-briefs/poc/<topic-slug>/ # guided PoC lab, only when the user says go
poc/<topic-slug>/ is a code workspace, not a document — it holds dependency manifests, virtualenvs, and scratch output. Two consequences: every scaffold ships a .gitignore covering the environment dirs and any local secrets file (.venv/, node_modules/, __pycache__/, .env) so credentials and binaries never land in the briefs tree, and the index builder ignores poc/ — labs are surfaced through their brief's brief-poc chip, never as index entries of their own.
What ships with it
4 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.
- 9d ago First seen · 348 lines · 176 tokens per session scan A 8642e15054c3
learn is a skill published in the GitHub repository ayberkcansever/ai-skills (2 stars, last pushed 5d ago), licensed MIT. It adds 176 tokens to every session and 8,873 once invoked, about $0.0009 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
toolport
Use when the user asks for any external action or data: email, payments, deployments, databases, repos, issues, files, web search, messaging, or any connected service. Toolport is the front door to every MCP server on this machine; search it before concluding a capability is unavailable.
explain
Guided code tour of a file or subsystem this session touched — entry point, the load-bearing pieces, the edges, and what connects to it.
digest
Generate a structured vibe-learn learning digest of the current coding session from .vibe-learn/session-log.jsonl.
quiz
Check your understanding of the vibe-learn session — recall questions grounded in the session log, with results tracked across sessions in the knowledge ledger.
learn
Explain recent vibe-learn session activity or answer a question about what was built, grounded in .vibe-learn/session-log.jsonl.
lookup-topic
Look up a help topic with progressive depth. First call returns concept, repeat calls escalate to task then reference. Triggers on: look up topic, open template, tell me more, go deeper, start over.