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 skills add yyz666ai/Learning-Agent --skill learner-onboardinggit clone --depth 1 https://github.com/yyz666ai/Learning-AgentWrote 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/skills/yyz666ai/learning-agent/learner-onboarding)<a href="https://agentmods.dev/skills/yyz666ai/learning-agent/learner-onboarding"><img src="https://agentmods.dev/badge/skills/yyz666ai/learning-agent/learner-onboarding/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/skills/yyz666ai/learning-agent/learner-onboarding"><img src="https://agentmods.dev/badge/skills/yyz666ai/learning-agent/learner-onboarding.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 | $0.00036 | $0.00899 |
| Opus 5.5 | $0.00014 | $0.00360 |
| Sonnet 5.5 | $0.00007 | $0.00180 |
| Haiku 4.5 | $0.00004 | $0.00090 |
Grade A, and why
learner-onboarding 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 1mo 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
学习者建档（先摸情况，再开讲）
只补齐真正缺失的建档信息。若界面已经确认画像，立刻退出本 Skill，不能再用聊天重复摸底。
界面确认快速通道
当请求含 forbid_more_onboarding=true，或画像标记为界面已确认并且 active_plan 可读取时：
- 不再询问、复述或要求用户确认基础、主题、时间与偏好；
- 不重新写画像，不把界面选择降级成
unknown； - 直接交给教学 Skill，从活动计划的当前任务开始第一小步。
执行流程
- 只读
$USER_DIR/learning-state.json和$USER_DIR/profile.md；用户给了项目路径再读项目链接，别扫历史。 - 输入框就是新主题入口。用户直接打字或语音说新内容，先使用
learning-intent-router获得经多轮 slot filling 确认的意图槽位；不先要求他点“学新知识”。 - 已填的主题、目标、结果、基础证据、期限和范围直接复用，不重复询问；只有缺少会改变路线的信息才问。
- 用户的主题可以是语言、库、API、工程、项目、面试方向或单一概念；保留他真正说的主题，不套成默认 Go/Python。
- 用户自己说的是
self_reported，小诊断的结果是diagnostic_evidence，别混成「已掌握」。 - 情况问够了，用一两句话复述你听到的，对方点头才算确认。没确认不写状态。
- 确认后，按
assets/profile-template.md更新画像，按references/state-contract.md写状态。 - 最后只标记「该定学习计划了」，交给
learning-plan，别自己开始上课。
Plan 确认交互
- Plan 准备好后作为对话中的普通 Agent 消息展示，不打开另一个文档框或学习页。
- 审阅 Plan 时收起之前的选择题，只保留一个紧凑的确认按钮。
- 不提供“前面快一点”“多做项目”“我想调整”等预设选项。用户要改时直接在输入框说，立即路由
plan-revision。
概念速学分支
当用户输入“RAG 是什么”“幂等是什么”这类显式概念问句，直接改走 concept_clarity，不再追问学习路线：
- 只问一个会改变教法的点击题：“你只想理解概念，还要看代码实现？”
- 选“只理解概念”记为
meaning_only；不问基础，不问每日时长，不做诊断，直接交给短 Plan。 - 选“还要看代码实现”记为
code_walkthrough；只再问一次代码阅读熟悉度，然后立即开始。仍然不问每日时长，不加 3–4 道起点诊断。 - 不要因为界面有“时长”字段就反向追问。运行时默认值只用于超时与页数上限，不属于用户课表。
- “这个是什么”“这一页怎么理解”类指代问句是当前课程答疑，留在对话中，不新建学习项目。
边界
- 「看看我的进度」→ 走
learning-progress，不是重新建档。 - 目标代码默认只读；不读
.env、凭据、构建产物。 - 不知道的就记
unknown，别猜对方水平、时间。 - 写失败就说失败，别假装保存了。
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 51 lines · 36 tokens per session scan A 0167a71ab6ea
learner-onboarding is a skill published in the GitHub repository yyz666ai/Learning-Agent (0 stars, last pushed 1mo ago), licensed MIT. It adds 36 tokens to every session and 899 once invoked, about $0.0001 per session on Opus 5.5. 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 skills, from other repositories
skillpack-creator
Create a reusable SkillPack from a successful completed task. Use when the user wants to convert a one-off research, coding, analysis, or content workflow into a distributable local SkillPack with skillpack.json, local skills under skills/, starter prompts, start scripts, and an optional zip package.
skill-creator
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
goga-discover
Interview the user relentlessly about a decision until every branch of the design tree is resolved, then record the result as a short ADR.
commit
Atomic git commit with conventional message. Use when the user says "commit", "save my changes", "commit this", or wants to create a git commit. Stages specific files, writes a conventional commit message with body explaining non-obvious decisions. Never uses git add -A.
python-run
Run and debug Python scripts in the project. Use when the user says "run python", "execute this script", "debug this py file", or wants to run/modify a .py file. Handles dependency checks, linting, execution, and error analysis.
akirule
Aki's contextual rule router — route EVERY task turn before acting, by what the task means (the domain it touches and the kind of act — write, decide, audit, ship), with listed signals as evidence, never as the test. Domains: code quality and structure (any code file), docs and any .md, UI copy and i18n, frontend…