learning-intent-router

learning-intent-router is a skill for Claude Code, Codex from yyz666ai/Learning-Agent. It costs 35 tokens per session (1,709 once invoked), scanned A, original, MIT.

A learning-intent router that interprets a learner’s goals, materials, corrections, and questions, then chooses the appropriate next interaction.

In plain words
What is it for?
Use it to route questions, learning goals, interview materials, and requests for study plans to the right response type.
Why use it?
Learners often provide partial or changing information. This router preserves known details, asks only for missing information that affects the plan, and avoids assuming a subject or skill level.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/yyz666ai/learning-agent/learning-intent-router
Any agent
npx skills add yyz666ai/Learning-Agent --skill learning-intent-router
Clone the repo
git clone --depth 1 https://github.com/yyz666ai/Learning-Agent

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for learning-intent-router

README.md
[![agentmods](https://agentmods.dev/badge/skills/yyz666ai/learning-agent/learning-intent-router.svg)](https://agentmods.dev/skills/yyz666ai/learning-agent/learning-intent-router)
Your own site
<a href="https://agentmods.dev/skills/yyz666ai/learning-agent/learning-intent-router"><img src="https://agentmods.dev/badge/skills/yyz666ai/learning-agent/learning-intent-router.svg" alt="Measured on agentmods" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,709 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00035 $0.01709
Opus 5 $0.00017 $0.00855
Sonnet 5 $0.00007 $0.00342
Haiku 4.5 $0.00003 $0.00171

Measured 5d ago against content hash 3f11e9881043, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

learning-intent-router 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 5d 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.

workspace/dev/.codex/skills/learning-intent-router/SKILL.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

学习意图与条件追问

理解用户想达成的结果,而不是让用户填完问卷。结合用户原话、服务端恢复的同项目历史、当前槽位与页面上下文,输出接口要求的一个 JSON 对象。

每轮决策

先记录已知事实,再判断缺口。保留原有准确槽位;新原话中的明确纠正覆盖旧事实。保留“不写代码”“不从头学”等约束到 constraints。用户同时回答多件事就一起记录,不按固定顺序重新问一遍。

当前需求 动作
当前页答疑、报错、改讲法、追加练习、假设性咨询 answer_in_context,不创建新课程
用户真的贴出面试题正文 interview_bank_intake,material_text仅复制题目原文的连续片段
已知主题、目标和适当起点,能提出有明确结果的计划 ready_for_plan,随后界面展示草稿并等用户确认
确实缺会改变方案的信息 clarify,一次一个问题

只有“你好”时开放问想学什么。只有主题时问想用它做到什么,不自动认定后端、面试或工程师方向。不固定生成“初学/精进/面试”三项;快捷回答必须对应当前问题的同一维度。

追问与输入

  • question.slot指向真正尚未确定的字段;该字段保持null/空/unknown,不一边填满一边追问。细化交付用learning_scope;已有经历但需了解目标领域用target_context,不泛问基础。
  • reason_to_ask用一句话说明缺口为什么影响方案,不输出思维链。
  • prompt只能询问question.slot对应的一件事。例如问岗位专业方向时,不在句尾再问“有没有面试题”;下一轮只在资料来源仍unknown时再开放索取。已给领域就直接保留,不问用户是否还要编程框架。
  • interaction=choices:仅当快捷回答有帮助时提供2–3个动态短选项;detail供详情气泡。界面自动追加末行输入,直接打字发送。不得生成“其他/都不符合”占位答案,不替用户选答案。
  • interaction=text:开放问题,options=[]。interaction=material:请发材料,options=[]。面试题、JD、仓库/代码、大纲不用有/没有选择卡。
  • “不知道”“暂时没有”“先通用”是可接受的回答,不无限追问,不强行填默认技术栈。
  • “零基础、系统学Python、直到独立开发项目”信息已够,直接生成方案,不再问学习程度。具体项目目标已明确,也不回问是否想完成项目。

基础证据

level_evidence引用用户描述能力的原文。“初学/零基础”通常zero,“学过一些/有基础”some,“熟练/资深”experienced。经历也是证据,不要求重复标签。三年某语言经历不能证明熟练另一框架。

仅有年限或做过项目,level_claim先记some,具体能力交后续诊断;不擅自标experienced或高级工程师。若目标是新框架且经验是否可迁移会明显改变课程,可用target_context追问相关实践,不让用户重复报整体基础。

区分否定、领域和目标:“不是零基础”不是zero,也不单凭这句就算高级;“Go写了四年,但没学过Rust”保留两种事实,按Rust起点与可迁移经验组织。尚不知基础且持续课程确实需要时才追问;不突然技术测验。有基础诊断由后续界面说明目的后开始,初学跳过。

路线与范围

  • 单个概念:concept_clarity;只问含义用meaning_only,同时要求代码/实现用code_walkthrough,不抹掉实现需求。当前页“这里的state是什么意思”留在answer_in_context。
  • 全面从零到工程能力:foundation_engineer;高级工程能力:senior_engineer。
  • 具体项目:project_delivery;只读语法:syntax_reading;紧急读某项目:urgent_codebase;补缺:gap_upgrade。
  • 本科跟课:academic_course;考试/期末:exam_review。保留course_scope、exam_format、deadline,不强制毕业项目。范围/题型已给不再问;无大纲可明确按通用范围,不假装看过老师材料。
  • 跟课却未给课程范围时,开放邀请发章节/教学大纲,允许回答“没有,按通用范围”;每周等节奏原样记录constraints,不换算成臆造的每日时长。已明确范围的考试不强求上传文件。
  • 两个目标已给先后就照做,顺序保存priority;冲突且无优先级才问一次,question.slot=priority,priority=null,goal仍保留全部目标。不要用goal追问优先级,因为目标本身已知。期限已知不重复问。
  • 读同事的具体仓库却无内容时,请发链接/目录/关键代码;拿不到可提供通用阅读方案,不能声称分析过实际代码。

Read the full file on GitHub · 73 lines

Files

What ships with it

1 file 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.

Changes

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.

  1. 5d ago First seen · 73 lines · 35 tokens per session scan A 3f11e9881043

Subscribe to this mod's changes

learning-intent-router is a skill published in the GitHub repository yyz666ai/Learning-Agent (1 stars, last pushed 5d ago), licensed MIT. It adds 35 tokens to every session and 1,709 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.

Related

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.

CreminiAI/skillpack · 67 tokens

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.

CreminiAI/skillpack · 64 tokens

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.

congchuanling-dot/Cohort · 59 tokens

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.

congchuanling-dot/Cohort · 56 tokens

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.

qarium/goga · 31 tokens

akirule

Aki's contextual rule router — invoke BEFORE acting whenever the task touches any of - .md/.vue/.css/.tsx/.rs/.sql files; docs, plan, README, CHANGELOG; UI, component, CSS, tailwind; SEO, schema, sitemap; release, version, commit, push, deploy; DB schema, migration; Tauri; i18n, UI copy; pricing, biz; UX review…

lacvietanh/akidevrule · 137 tokens