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/hluaguo/learn-faster-kit/learngit clone --depth 1 https://github.com/hluaguo/learn-faster-kitWrote 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/commands/hluaguo/learn-faster-kit/learn)<a href="https://agentmods.dev/commands/hluaguo/learn-faster-kit/learn"><img src="https://agentmods.dev/badge/commands/hluaguo/learn-faster-kit/learn.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 | $0.00018 | $0.00630 |
| Opus 5 | $0.00009 | $0.00315 |
| Sonnet 5 | $0.00004 | $0.00126 |
| Haiku 4.5 | $0.00002 | $0.00063 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context
- Current topic: !
ls .learning/ 2>/dev/null | grep -v scripts
Note: The .learning/ directory is already initialized. Check the topic folder name (ignore scripts/).
Your Task
Initialize learning for the specified topic using the FASTER framework.
If a topic already exists:
- Inform: "This project is already learning [topic name]"
- Check for due reviews first (conduct before new learning if any)
- Continue with current topic (1 project = 1 learning goal)
If no topic exists yet:
- Gather learning preferences with
AskUserQuestionbase on users selected topic:
[
{
"question": "What level do you want to achieve with [topic]?",
"header": "Level",
"multiSelect": false,
"options": [
{
"label": "Beginner",
"description": "Fundamentals and basic concepts"
},
{
"label": "Intermediate",
"description": "Practical skills and common patterns"
},
{
"label": "Advanced",
"description": "Deep expertise and edge cases"
},
{
"label": "Expert",
"description": "Mastery level, architecture, optimization"
}
]
},
{
"question": "What do you want to focus on?",
"header": "Focus",
"multiSelect": true,
"options": [
{
"label": "Theory",
"description": "Concepts, principles, how things work"
},
{
"label": "Practice",
"description": "Hands-on coding and building projects"
},
{
"label": "Real-world",
"description": "Production patterns and best practices"
},
{
"label": "Interview prep",
"description": "Common questions and problem-solving"
}
]
}
]
- Run:
python3 .learning/scripts/init_learning.py "[topic name]" .learning - Parse JSON output and follow
llm_directive - READ
.learning/<topic-slug>/syllabus.mdto see the template structure - Generate comprehensive syllabus content tailored to user's level and focus areas
- Replace the template placeholders with actual content
- Update metadata:
"syllabus_generated": truein.learning/<topic-slug>/metadata.json
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 · 96 lines · 18 tokens per session scan A 70072e586f21
learn is a command published in the GitHub repository hluaguo/learn-faster-kit (371 stars, last pushed 1mo ago), licensed MIT. It adds 18 tokens to every session and 630 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 2026-08-30.
Other commands, from other repositories
OPSX: Onboard
Guided onboarding - walk through a complete OpenSpec workflow cycle with narration.
dashboard
Launch the learning dashboard web UI to view and edit plans, progress, and spaced repetition data.
learn
Start learning a new topic — asks clarifying questions, researches resources, and creates a structured learning plan.
quiz
Quiz yourself on a topic from your learning plan with adaptive difficulty and mixed question formats.
resources
Find curated learning resources — books, courses, tutorials, and docs for any topic.
review
View your learning progress — quiz scores, weak areas, and what to study next.