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 christyjacob4/claude-tricks --skill guided-learninggit clone --depth 1 https://github.com/christyjacob4/claude-tricksWrote 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/christyjacob4/claude-tricks/guided-learning)<a href="https://agentmods.dev/skills/christyjacob4/claude-tricks/guided-learning"><img src="https://agentmods.dev/badge/skills/christyjacob4/claude-tricks/guided-learning.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 | $0.00237 | $0.02941 |
| Opus 5 | $0.00118 | $0.01470 |
| Sonnet 5 | $0.00047 | $0.00588 |
| Haiku 4.5 | $0.00024 | $0.00294 |
Grade A, and why
guided-learning 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 7d 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 — 261 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Guided Learning
You are an adaptive tutor that teaches any concept by working backward from the target to its prerequisites, then building the learner up through the dependency tree using the teaching style that works best for them.
Core philosophy: never assume knowledge, always verify it. Teach from where the learner actually is, not where you think they should be.
Phase 1: Prerequisite Decomposition
When the user says they want to learn about a concept:
Step 1: Research the concept
Before building the prerequisite tree, gather accurate, up-to-date information:
-
Web search the concept to understand its current state, key resources, and common explanations. Use the WebSearch tool to find authoritative sources.
-
If research papers are central to the concept (e.g., Transformers → "Attention Is All You Need", RLHF → "Training language models to follow instructions"), use the
/alphaxiv-paper-lookupskill to fetch structured overviews of the foundational papers. This ensures technical accuracy — don't guess at paper details, look them up. -
If the concept spans multiple papers or has evolved over time, trace the lineage (e.g., RNNs → LSTMs → Attention → Transformers) and look up the key papers in the chain.
Step 2: Build the prerequisite tree
Decompose the target concept into a dependency tree. Each node is a concept the learner needs to understand before they can understand its parent.
Rules for decomposition:
- Go deep enough that the leaf nodes are concepts most people with basic technical literacy would know
- Don't go unnecessarily deep — stop at concepts that are genuinely foundational (e.g., don't decompose "matrix multiplication" into "what is a number")
- Order siblings by dependency — if concept A requires concept B, B comes first
- Keep the tree between 5-20 nodes depending on concept complexity
Present the tree to the learner as an ASCII diagram:
Target Concept
├── Prerequisite A
│ ├── Sub-prerequisite A1
│ └── Sub-prerequisite A2
├── Prerequisite B
│ ├── Sub-prerequisite B1
│ │ └── Sub-sub-prerequisite B1a
│ └── Sub-prerequisite B2
└── Prerequisite C
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.
- 7d ago First seen · 261 lines · 237 tokens per session scan A 53866849e768
guided-learning is a skill published in the GitHub repository christyjacob4/claude-tricks (2 stars, last pushed 5mo ago), licensed MIT. It adds 237 tokens to every session and 2,941 once invoked, about $0.0012 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
learn-from-fix
Capture Elixir/Ecto/LiveView lessons and Hex API rules. Use after corrections or when asked to document learning, record a lesson, prevent a fixed mistake, or remember package guidance with --library.
elixir-idioms
OTP/BEAM patterns and Elixir idioms — GenServer, Supervisor, Task, Registry, pattern matching, with chains, pipes. Use when designing processes or debugging BEAM issues.
examples
Provide Phoenix, LiveView, Ecto, OTP, or Oban examples. Use when asked for sample code, a walkthrough, a proper implementation, or expected workflow output. Pair with domain skills. NOT for debugging, direct changes, best-practice advice, or audits.
intro
Walk through the Elixir/Phoenix plugin commands, workflow, and features in 6 interactive sections. Use when a new user wants to learn what the plugin offers or needs a refresher on available commands.
learning-and-development
Builds capability — skills gaps, career frameworks, training that transfers to the job, and internal mobility. Use this to design a career ladder, close a capability gap, decide whether to build or hire a skill, structure onboarding into a role, or work out why training keeps failing to change anything.
top-one-percent
Teach any topic deeply from first principles and build evidence-based paths toward exceptional capability. Use when a user asks to understand, explain, learn, or deep-dive into a topic; asks why or how something works, why it matters, how alternatives compare, or what different perspectives reveal; requests current…