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 skills/li-evan/bloom/learn-occamnpx skills add Li-Evan/Bloom --skill learn-occamgit clone --depth 1 https://github.com/Li-Evan/BloomWrote 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/li-evan/bloom/learn-occam)<a href="https://agentmods.dev/skills/li-evan/bloom/learn-occam"><img src="https://agentmods.dev/badge/skills/li-evan/bloom/learn-occam.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 | $0.00155 | $0.00824 |
| Opus 5 | $0.00077 | $0.00412 |
| Sonnet 5 | $0.00031 | $0.00165 |
| Haiku 4.5 | $0.00015 | $0.00082 |
Grade A, and why
learn-occam 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.
What it actually says
简易策略（learn-occam）
核心信条：这世界最有价值的不是知识，是你的时间。 能用现有知识解决的就别学新的；以后要用的，以后再学。
何时用
用户在纠结"要不要学 X / 学到什么程度 / 精力往哪放"。这是"广度优先、兴趣队列过长"倾向的刹车。
流程
第一步：先找"既定问题"
逼问一句：你要解决的具体问题是什么？ 没有具体问题、纯"感觉该学 / 别人都在学"→ 直接进"以后再学"队列，不占当下精力。理解知识的作用，重于知识本身。
第二步：现有知识能不能搞定
问清用户已经会什么——能解决就别学新的。拿不准"是不是其实已经会了"就配合 learn-crossover。
第三步：贬值速度 + ROI
这知识多久会贬值？（技术栈 / 工具往往 6–12 个月就明显更新）相对有限的时间值不值？贬值快 + 可外包给 AI / 随时查 → 只需"知道它存在、管什么"，不必真学。
第四步：探索 vs 应用（N 臂老虎机）
现在该"探索"（学新）还是"应用"（用现有）？探索成本越高 → 越该偏应用。只有目标够难、现有知识确实够不着时，简易策略才督促你学。
第五步：给结论
明确三选一：① 学（值得且现有搞不定）/ ② 不学（入"以后再学"队列）/ ③ 只学最小够用的那一块（点明是哪一小块）。要深挖就转 learn-graph 建路径。
注意
⚠️ 铁律·只用确证的已会知识：判断用户「已经会什么」只能用他确证学过的知识（亲口确认或可靠背景）；严禁把「正在讲的材料 / 文章作者背景 / 对话里别人的知识」当成用户会的。拿不准 → 直接问「⚠️ 你学过 ___ 吗？」，绝不替他假设。
- 简易策略不是"少学"，是"让问题决定你学什么"。
- 它的缺点是易陷局部最优——拿不准"是不是缺前置知识"时转
learn-graph。 - 同族 skill：
learn-crossover(已会什么)learn-graph(系统建图)learn-prototype(动手迭代)learn-feynman(自查)。
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.
- 5d ago First seen · 43 lines · 155 tokens per session scan A cdccde274c6a
learn-occam is a skill published in the GitHub repository Li-Evan/Bloom (250 stars, last pushed 2mo ago), licensed MIT. It adds 155 tokens to every session and 824 once invoked, about $0.0008 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 2026-08-30.
Other skills, from other repositories
liu-xiaoyan-english
模拟刘晓燕老师的英语教学风格和方法论，用于四六级/考研英语辅导（已用2026年6月CET-6真题校准）。触发场景：用户提到刘晓燕、晓燕老师、四六级英语、CET-4、CET-6、2026六级、考研英语、英语阅读理解、英语写作模板、长难句分析、英语备考规划、英语翻译技巧、选词填空、背单词方法，或要求用刘晓燕的方式讲课/解题/做规划/对答案。也适用于：用户发来英语阅读/听力/翻译/写作/选词填空题要求讲解。常见触发语：'用刘晓燕的方式'、'燕姐教我'、'像晓燕老师那样讲'、'四六级怎么准备'、'帮我分析这道阅读题'、'这个长难句怎么拆'、'保命班'、'考前急救'、'今年六级'。Use when coaching CET-4/6 or…
ai-pm-atom-lesson
输入一个"原子知识点"(AI 产品经理知识体系里的最小单元概念,如「文本切分」「演绎推理」「思维链 CoT」「向量化」「LLM-as-Judge」),自动展开成一份讲解思路并产出一个单文件、离线可用的交互式 HTML 原子课件——含权威定义+真实出处、通俗解释、贯穿项目案例、实操判断题、以及一个可视交互 Demo。当用户说"做一个 X 的原子课""把这个知识点做成原子课件""按原子课 SOP 做 X""给 X 配一页能点着玩的讲解""atom lesson"时,一定要使用本技能。也适用于:把知识体系/能力地图里的某个词条单点成课、要一系列同构的知识点小课件、批量把能力地图节点做成课。即使用户只说"把 X…
deeptutor-cli
Configure, manage, and use DeepTutor through its CLI, including capabilities, knowledge bases, partners, memory, sessions, notebooks, providers, skills, and the server or Web app.
check-understanding
AI Engineering from Scratch 的阶段测验。用于“给我测验一下”、“测试阶段”、“检查我的理解”、“我掌握第 3 阶段了吗”，也支持 "quiz me", "test phase", "check my understanding", "do I know phase 3" 或 /check-understanding 。.
learn-mcp
AI Engineering from Scratch 中 Model Context Protocol (MCP) 路线的专注交互 tutor。 学习者想构建、保护、调试、验证或运行 MCP clients、servers、transports、gateways、 registries 或 conformance gates 时，开始或续学此路线。每次调用教学一课，并将 wire evidence 记录到 MCP-LEARNING.md。Start or resume this route when a learner wants to build, secure, debug, verify, or operate MCP…
learn
AI Engineering from Scratch 课程的交互式课程 tutor。读取 LEARNING.md，获取下一课， 在终端按章节教学，结尾测验并记录进度。可在克隆仓库中或完全通过 raw.githubusercontent.com 工作—— 无需设置。触发短语：“下一课”、“教我”、“继续课程”、“我们来学习”、“继续学习”，或 "next lesson", "teach me", "continue the course", "let's learn", "resume learning".