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 agentmods add commands/sergei-aronsen/claude-code-toolkit/learngit clone --depth 1 https://github.com/sergei-aronsen/claude-code-toolkitWhat 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 | $0.00000 | $0.01294 |
| Opus 5 | $0.00000 | $0.00647 |
| Sonnet 5 | $0.00000 | $0.00259 |
| Haiku 4.5 | $0.00000 | $0.00129 |
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 2d 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 — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/learn — Extract Reusable Patterns
Purpose
Extract problem solutions and save them as scoped rule files that auto-load only for relevant files.
Usage
/learn [description]
Examples:
/learn— Analyze session and find patterns/learn prisma connection pooling fix— Save a specific solution/learn always use UUID for public IDs— Save an explicit instruction
When to Use
Run /learn when:
- Solved a non-trivial problem
- Found a workaround for a library/framework
- Discovered non-obvious behavior
- User corrected your mistake (remember it!)
- Debugging took a long time
- 3+ attempts to fix one problem
DO NOT use for:
- Simple typos
- One-time issues (API was unavailable)
- Obvious solutions
Process
Step 1 — Analyze
Identify what was learned. Look at:
- Recent fixes and their root causes
- User corrections during the session
- Non-obvious behaviors discovered
- Patterns that took multiple attempts
Step 2 — Scope the Rule
Determine which files this rule applies to. Pick the narrowest matching scope:
| Scope | globs example | Rule file name |
|---|---|---|
| Language-specific | ["**/*.ts", "**/*.tsx"] |
rules/typescript.md |
| Framework-specific | ["app/**", "routes/**"] |
rules/laravel.md or rules/nextjs.md |
| Database/ORM | ["models/**", "prisma/**", "migrations/**"] |
rules/database.md |
| UI/Components | ["components/**", "pages/**"] |
rules/ui-components.md |
| API/Backend | ["api/**", "controllers/**", "routes/**"] |
rules/api.md |
| Testing | ["tests/**", "**/*.test.*", "**/*.spec.*"] |
rules/testing.md |
| Infrastructure | ["docker*", "*.yml", "Makefile"] |
rules/infrastructure.md |
| Global (last resort) | ["**/*"] |
rules/project-lessons.md |
Use Global only if the rule genuinely applies everywhere. Most rules have a narrower scope.
Step 3 — Write the Rule
Each rule is compact — 3-4 lines max:
### [Short Title] — [Date]
**Problem:** one-line description
**Solution:** one-line solution
**Apply when:** trigger condition
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.
- 2d ago First seen · 200 lines · 0 tokens per session scan A 52aa0e80c886
learn is a command published in the GitHub repository sergei-aronsen/claude-code-toolkit (5 stars, last pushed 16d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,294 tokens. 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 commands, from other repositories
learn
Force claude-smart to extract learnings from this session now.
component
Scaffold a new React component grounded in the paper-mono primitives. Requires explicit kind or a nearest-existing-component match. No empty divs, no speculative scaffolding.
memory-store
Store an insight, decision, or pattern to memory.
review
Cold re-quiz on code that already shipped — your own session commits, not the change in front of you.
no-vibe
Enter no-vibe mode in OpenCode (tutor mode, no direct project file writes).
teach-me-testing
Teach testing progressively through structured sessions. Use when user says ""lets learn testing"" or ""I want to study test practices"".