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/with-geun/alive-analysis/analysis-learn-hintgit clone --depth 1 https://github.com/with-geun/alive-analysisWrote 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/with-geun/alive-analysis/analysis-learn-hint)<a href="https://agentmods.dev/commands/with-geun/alive-analysis/analysis-learn-hint"><img src="https://agentmods.dev/badge/commands/with-geun/alive-analysis/analysis-learn-hint.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 | $0.00000 | $0.00466 |
| Opus 5 | $0.00000 | $0.00233 |
| Sonnet 5 | $0.00000 | $0.00093 |
| Haiku 4.5 | $0.00000 | $0.00047 |
Grade A, and why
analysis-learn-hint 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 6d 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.
What it actually says
/analysis-learn-hint
Request a progressive hint for the current learning stage.
Instructions
Step 1: Identify current session and stage
Read .analysis/education/progress.md to find the active learning session.
- If no active session → "No active learning session. Run
/analysis-learnto start one."
Determine the current ALIVE stage (same logic as /analysis-learn-next Step 2).
Step 2: Track hint usage
Read the current hint level for this stage from the session's hint tracking.
The hint system works in 3 progressive levels per stage:
- Level 1: Direction hint — points toward the right area to explore
- Level 2: Specific hint — narrows down to the specific factor or method
- Level 3: Near-answer — provides most of the answer for learners who are stuck
Each /analysis-learn-hint call advances one level for the current stage.
Step 3: Deliver the hint
Read the hint file: core/education/scenarios/{scenario-id}/hints/{stage}.md
{stage}is one of:ask,look,investigate,voice,evolve
Present the appropriate level's hint based on how many times the user has asked for this stage:
- First call → Level 1
- Second call → Level 2
- Third call → Level 3
- Fourth+ call → "You've used all 3 hint levels for this stage. Review the hints above and try your best — you can always run
/analysis-learn-nextto see the feedback and move on."
Presentation format:
💡 Hint (Level {N}/3) for {STAGE}:
{hint content}
For Beginner scenarios, add encouragement: "Take a moment to think about how this applies to your analysis. You're doing great!" For Intermediate scenarios, keep it concise — just the hint.
Step 4: Record hint usage
Update .analysis/education/progress.md:
- Increment the hint count for the current session
Track internally which stages have had hints used and at what level, so /analysis-learn-review can report total hints used.
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.
- 6d ago First seen · 52 lines · 0 tokens per session scan A 97019a23c8eb
analysis-learn-hint is a command published in the GitHub repository with-geun/alive-analysis (41 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 466 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 2026-08-30.
Other commands, from other repositories
mentor
Educational mode that explains concepts, teaches patterns, and guides learning. Ideal when learning a new codebase, technology, or programming concept.
learn
Learn about Task Master capabilities through interactive exploration.
project_init
이 프로젝트를 ocul-pm 추적 대상으로 초기화 (.oculpm/ + 기록 규칙 생성) — 사용자가 직접 실행하는 명시적 시작.
start-12-6
Command "start-12-6" from minicoohei/ai-agent-camp, covering 🎓 lesson 12-6: 要約の作成とコメントの返信, 📍 このセッションでやること, 🎯 準備チェック, 🚀 step 1: ページ/db内容の取得 and 🚀 step 2: aiによる構造化要約の生成.
start-13-5.en
Command "start-13-5.en" from minicoohei/ai-agent-camp, covering 🎓 lesson 13-5: vercel deploy, 📍 what you'll do, 🎯 readiness check, 🔍 step 0: check project existence and check if output/lp-project directory exists.
start-13-5.es
Bienvenido a Lección 13-5: Despliegue en Vercel.