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.
git clone --depth 1 https://github.com/Sean-xhz/ai-learning-platformWrote 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/sean-xhz/ai-learning-platform/learn-today)<a href="https://agentmods.dev/commands/sean-xhz/ai-learning-platform/learn-today"><img src="https://agentmods.dev/badge/commands/sean-xhz/ai-learning-platform/learn-today/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/sean-xhz/ai-learning-platform/learn-today"><img src="https://agentmods.dev/badge/commands/sean-xhz/ai-learning-platform/learn-today.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00035 | $0.00907 |
| Opus 5 | $0.00017 | $0.00453 |
| Sonnet 5 | $0.00007 | $0.00181 |
| Haiku 4.5 | $0.00003 | $0.00091 |
Grade A, and why
learn-today 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 8d 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
/learn-today
今天是学习计划的第几天?让我看看今天的学习任务。
$ARGUMENTS
当前进度:grep '当前进度' learning-plan.md 2>/dev/null | head -1
已完成会话数:find sessions/ -name 'session-log*.md' -type f 2>/dev/null | wc -l | tr -d ' '
学习模式:grep '学习模式' learning-plan.md 2>/dev/null | head -1
这是每日学习闭环的开环命令,与 /learn-done(收尾)成对。按以下步骤编排:
Step 0:唤起复习(P1-7,先还旧账再学新的)
检查 review-queue.md(若存在):
- 若今天是缓冲日(计划中 Day 标题含
📥 缓冲日(复习日))→ 不学新内容(跳过 Step 1):- 队列有项 → 深度复习:调用 assessment-officer 复习模式(缓冲日深度变体),累积重测所有「待复习/已重置」项 + 迄今最弱的维度
- 队列为空或不存在 → 轻量回顾:带学习者翻看迄今 session-log 的核心收获与仍存疑问,不召 material-steward、不做 Pre-test
- 非缓冲日:筛出
下次复习Day ≤ 今天且状态=待复习/已重置的到期项:- 有到期项 → 先调用 assessment-officer 复习模式(日常到期变体)做检索小测(考你而非重讲),判定记得/模糊/忘了,回写队列更新间隔;然后再进入新内容
- 无到期项 → 一句带过"今天没有到期复习项",直接进入新内容
review-queue.md不存在 → 跳过本步(还没有积累盲区)
Step 1:今日主题
先按下方「判断今天学什么」定位今日。若今天是缓冲日,本步整体跳过(复习日不排新内容,由 Step 0 的深度复习/轻量回顾接管)。否则:
- 若该日
- **状态**:行已是✅ 已完成:提示"今天已经完成了,要回顾还是继续下一天?",不执行后续步骤 - 把该日
- **状态**:行更新为🔄 进行中(幂等——重复运行无副作用;/learn-progress的进行中统计以此为真实来源) - 读取该日计划,输出今日主题和核心问题、预期产出(学完后要能做什么)
- 调用 material-steward Subagent 收集今日材料——显式传入上下文:Day N、今日主题、3-5 个核心问题、学习模式、当前水平、每日可用时长(子代理无法自行定位"今天",只说"收集今日材料"会断链)
- 提醒进行 Pre-test(调用 assessment-officer Skill)
- 告知学习者:自学过程中遇到不懂的概念,随时可以用
/explain召唤讲解员
判断今天学什么
- 如果
$ARGUMENTS包含天数(如 "Day 3"),直接定位到对应天 - 否则从上方反引号输出的"当前进度"读取
- 学完一天后,引导用
/learn-done收尾(Post-test + 价值转化 + 盲区入队)
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.
- 8d ago First seen · 45 lines · 35 tokens per session scan A e0a42e5fe5c3
learn-today is a command published in the GitHub repository Sean-xhz/ai-learning-platform (2 stars, last pushed 1mo ago), licensed MIT. It adds 35 tokens to every session and 907 once invoked, about $0.0002 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 commands, from other repositories
teach-me
Interactive voice-narrated tutorial on the current conversation topic (or a named one) — ASCII diagrams, spoken lesson content, one question per beat, quizzes. Routes to the Teach skill's Teach workflow. USE WHEN /teach-me, teach me, tutorial, quiz me, learn mode. NOT FOR plain written explanations with no dialogue…
tm
Interactive voice-narrated tutorial on the current conversation topic (or a named one). Shortcut for the Teach skill's Teach workflow. USE WHEN /tm, teach me, tutorial, quiz me.
gauntlet
Run an ad-hoc gauntlet challenge session (5 questions, random scope).
gauntlet-onboard
Start or resume a guided onboarding path.
commands
Complete reference for all pair programming session commands.
modes
Detailed guide to pair programming modes and their optimal use cases.