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-done)<a href="https://agentmods.dev/commands/sean-xhz/ai-learning-platform/learn-done"><img src="https://agentmods.dev/badge/commands/sean-xhz/ai-learning-platform/learn-done.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 | $0.00042 | $0.01114 |
| Opus 5 | $0.00021 | $0.00557 |
| Sonnet 5 | $0.00008 | $0.00223 |
| Haiku 4.5 | $0.00004 | $0.00111 |
Grade A, and why
learn-done 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
/learn-done
今天的学习告一段落,帮我收尾。
$ARGUMENTS
当前进度:grep '当前进度' learning-plan.md 2>/dev/null | head -1
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收尾命令,与 /learn-today(开环)成对。按以下步骤编排,不要跳步:
Step 1:定位今天
- 如果
$ARGUMENTS含天数(如 "Day 3"),用它 - 否则从上方"当前进度"读取
- 读取该日的主题、核心问题、学习模式
- 若今天是缓冲日(Day 标题含
📥 缓冲日(复习日)):复习日的"所学"就是复习本身——跳过 Step 2-4(队列更新已在/learn-today深度复习时完成),直接执行 Step 5 更新状态
Step 2:Post-test(调用 assessment-officer)
- 让测评官出 Post-test(与 Pre-test 等难度、不同题),重点覆盖 Pre-test 标记的盲区
- 计算学习增量,指出具体进步在哪个维度
- 将 Pre/Post 结果写入
sessions/session-log-dayXX.md(不存在则从templates/session-log.md创建) - 写入后 progress-tracker Hook 会自动更新进度面板
Step 3:project-mentor 价值转化(按学习模式)
调用 project-mentor Subagent(显式传入:当天 Day 号、今日 session-log 路径 sessions/session-log-dayXX.md、学习模式),把今日所学转化为价值,输出追加到 session-log 的「项目导师建议」区:
- 🎯 项目驱动 → 改进动作列表(P0-P3 优先级,目标文件/模块)
- 🔭 领域探索 → 领域洞察列表(趋势/机会/风险)
- 💡 纯粹认知 → 知识网络图(新概念 ↔ 旧知识的连接)
遵守 project-mentor 的约束:找不到真实映射就说没有,不编造关联。
Step 4:采集盲区与疑问入复习队列(P1-7)
从今日 session-log 提取,追加到 review-queue.md(不存在则从 templates/review-queue.md 创建):
- 最大盲区(类型=盲区):取 session-log Post-test 表的「最大盲区」行(Post-test 暴露的最薄弱点,不是 Pre 区的「起点盲区」)
- 仍存在的疑问(类型=疑问):session-log「仍存在的疑问」里学习者自己的开放问题
每条新项:来源Day=今天、首次出现=今天、下次复习Day=今天+1、复习次数=0、忘记次数=0、状态=待复习。
去重:若队列已有相同内容的项,不重复添加,仅在该项状态为「已掌握」时重新激活。
Step 5:更新计划状态
- 将该日
- **状态**:行改为✅ 已完成(只保留单一状态值) - 更新「当前进度」为下一天
- 若今天是计划的最后一天(没有下一天可推进):把
review-queue.md中所有状态=待复习/已重置的项改为carryover——计划结束时仍未消解的盲区/疑问,交由方法论收割(methodology-harvest)作为认知陷阱模式的素材处理
Step 6:阶段末/缓冲日提示
- 若今天是一个阶段的最后一天:先把「里程碑检查点」表中该阶段的「实际完成日」填为今天、「状态」改为 ✅,再提示"本阶段完成,要不要运行方法论收割(methodology-harvest)提炼可复用 pattern?"
- 若明天是缓冲日:提示"明天是复习日,
/learn-today会带你做累积复习而非新内容"
约束
- Post-test 和 Pre-test 不得有重复题目
- 复习队列采集必须去重,不得堆量
- 状态字段只保留单一值(⬜/🔄/✅ 三选一),不要把三个选项都留下
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 · 66 lines · 42 tokens per session scan A b042a9cdcf9d
learn-done is a command published in the GitHub repository Sean-xhz/ai-learning-platform (2 stars, last pushed 1mo ago), licensed MIT. It adds 42 tokens to every session and 1,114 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
review
Cold re-quiz on code that already shipped — your own session commits, not the change in front of you.
learn-story-flow
Learn story-flow concepts with interactive guidance for junior developers.
annex-a-deep-dive
Deep dive analysis of ISO 27001 Annex A control domains with implementation guidance.
start-10-1
A guided lesson on setting up clasp, a command-line tool for managing Google Apps Script projects, and connecting it to Google’s Apps Script API.
start-13-4.en
Welcome to Lesson 13-4: Landing Page Implementation!
start-0-8
A Japanese-language command that displays the current project setup progress.