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/progressgit clone --depth 1 https://github.com/hluaguo/learn-faster-kitWhat 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 | $0.00008 | $0.00585 |
| Opus 5 | $0.00004 | $0.00293 |
| Sonnet 5 | $0.00002 | $0.00117 |
| Haiku 4.5 | $0.00001 | $0.00059 |
Grade A, and why
progress 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context
- Learning directory: !
ls -d .learning 2>/dev/null - Current topic: !
ls .learning/ 2>/dev/null
Note: If .learning/ doesn't exist, inform user to run /learn [topic]. Check topic folders (ignore scripts/).
Note: After getting topic slug, read the necessary files:
.learning/<topic-slug>/metadata.json.learning/<topic-slug>/progress.md(last 30 lines).learning/<topic-slug>/syllabus.md.learning/<topic-slug>/review_schedule.json
Your Task
Generate an encouraging progress report showing learning journey and next steps.
If no .learning/:
- Inform: "No learning in progress yet. Use
/learn [topic]to start!"
Calculate metrics:
- Sessions completed (from metadata)
- Days since start (from created_at)
- Concepts learned (count from progress.md)
- Syllabus progress (checked
[x]vs total[ ]) - Reviews completed (from review_schedule.json)
- Current phase (from syllabus position)
Present report:
📊 Progress Report: [Topic Name]
🎯 Overview
Sessions: [N] | Days: [N] | Phase: [X] - [Name]
Syllabus: [X]% ([M]/[Total] items)
📚 Concepts Learned
✓ [Concept 1]
✓ [Concept 2]
... ([N] total)
🎉 Recent Wins
- [Achievement 1]
- [Achievement 2]
📅 Review Stats
Completed: [N] | Scheduled: [N]
Next review: [date] ([N] concepts)
🎯 Next Focus
1. [Next unchecked item]
2. [Next unchecked item]
💡 Insights
[Personalized based on data]
Celebrate milestones:
- 5 sessions: "🎉 Building momentum!"
- 10 sessions: "🔥 Committed to learning!"
- 25%: "🎯 Quarter way!"
- 50%: "🚀 Halfway there!"
- 75%: "⭐ Almost mastered!"
- 100%: "🏆 Syllabus complete!"
Consistency tracking:
- 3-day streak: "Nice! 3 days in a row!"
- 7-day: "🔥 One week streak!"
- 14-day: "🌟 Two weeks strong!"
- 30-day: "🏅 One month!"
After report:
- Suggest next actions
- Offer options: continue learning, do reviews, or break
- Keep encouraging tone
Key: Progress reports should motivate, not just inform. Celebrate wins, show growth, suggest forward momentum.
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 · 91 lines · 8 tokens per session scan A 91c22f2d6535
progress is a command published in the GitHub repository hluaguo/learn-faster-kit (371 stars, last pushed 29d ago), licensed MIT. It adds 8 tokens to every session and 585 once invoked, about $0.0000 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
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.
develop-explain
Explain how to implement a feature with learning context, covering all approaches and technologies.