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/forefy/.context/training-guidenpx skills add forefy/.context --skill training-guidegit clone --depth 1 https://github.com/forefy/.contextWrote 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/forefy/.context/training-guide)<a href="https://agentmods.dev/skills/forefy/.context/training-guide"><img src="https://agentmods.dev/badge/skills/forefy/.context/training-guide.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 | $0.00033 | $0.01193 |
| Opus 5 | $0.00016 | $0.00596 |
| Sonnet 5 | $0.00007 | $0.00239 |
| Haiku 4.5 | $0.00003 | $0.00119 |
Grade A, and why
training-guide 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.
How it starts
The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Training Guide - interactive visual primer
Turn a subject into a self-paced, click-through course: a full-bleed two-column page where a hand-built diagram sits on the left and one idea's explanation sits on the right, advanced with Next / Back / arrow keys. It teaches the way a good tutor does - build the machine one piece at a time, name each term the first time it appears, drop in a trick question to check understanding, and reveal an analogy on demand.
The engine (design system, stepper, diagram helpers, quiz mechanics) already exists in
assets/template.html. Your whole job is content: infer the subject, design the teaching
order, and write the steps array plus one small diagram function per screen. Do not rebuild the
engine.
Workflow
-
Pin the subject and the audience. Pull it from the conversation - the report, code, or topic in play. If genuinely ambiguous, ask one sentence's worth of clarification (subject + who's learning + how deep). Otherwise infer and proceed; the user can redirect.
-
Design the concept ladder before writing any code. This is the craft. List the ideas in dependency order and check the golden rule: every term a later screen uses must be taught on an earlier screen. If a "gotcha" or finding screen will say
DeploymentVerifierorECDH, there must be an earlier plain screen that introduces it. A good arc is usually: mechanics (the core moving parts) → the build (what it's for / the features) → the machinery (supporting infrastructure the gotchas will reference) → where it gets tricky (pitfalls, findings, edge cases). Put a quiz after each act. -
Copy the template and fill it in. Copy
assets/template.htmlto a working file (the user's Desktop or the scratchpad). Then:- Set
CONFIG(brand, title, legend meanings). - Optionally reskin the palette: change the ONE accent colour (
--accent/--accent-ink/--accent-soft) and the neutrals in the CSS:rootblocks to suit the subject's world. Keep--warnand--dangersemantic-only. Design both light and dark. - Replace the example diagram functions with one per concept, built from the
box / wire / lbl / seal / svghelpers (640×300 viewBox). ReusedQuiz()for quiz screens. - Replace the
stepsarray with your ladder. Readreferences/authoring.mdfor the full helper API, the screen-object schema, layout math, and worked examples - read it before writing diagrams so they don't overlap.
- Set
What ships with it
2 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.
- 5d ago First seen · 81 lines · 33 tokens per session scan A ec8a4e9178b6
training-guide is a skill published in the GitHub repository forefy/.context (141 stars, last pushed yesterday), licensed MIT. It adds 33 tokens to every session and 1,193 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 2026-08-30.
Other skills, from other repositories
onboarding-guide
Guides new users through a friendly onboarding experience.
cangjie-skill
Distill a book, long-video transcript, podcast, course, or interview into a coherent set of executable skills. Use when the user asks to "拆书" / "蒸馏一本书" / "把 XX 书做成 skill" / "把这个视频/播客/课程蒸馏成 skill" / "turn a book or video into skills" — i.e. wants the frameworks, principles, and methodologies in long-form content…
coding-tutor
Personalized coding tutorials that build on your existing knowledge and use your actual codebase for examples. Creates a persistent learning trail that compounds over time using the power of AI, spaced repetition and quizes.
reading-metaskill
当用户想养成阅读习惯、问「读什么书/怎么读」「如何学习新领域/怎么入门某学科」时调用。 核心理念: 阅读是终极元技能; 读你所爱直到爱上阅读, 没有读完义务; 读原著与经典优先; 以教促学; 每天1-2小时即可进入极少数人行列。 不适用于: 具体某本书的书评、考试备考资料选择。 Triggers: 阅读/读书/怎么学习/入门/原著/书单/reading/how to learn.
life-meaning
当用户问「活着的意义是什么/找不到方向/虚无感/该为什么努力」时调用。 核心理念: 生命没有外在赋予的意义(宇宙尺度一切会消失); 意义=个人创造+愿意为之受苦; 拥抱死亡是意义的入口。 不适用于: 急性自杀风险(先紧急求助)。 Triggers: 生命的意义/虚无/找不到意义/为什么活着/meaning/purpose/nihilism.
principal-agent
当用户选择职业/组织/合作方式、困惑「为什么大公司磨洋工/小公司拼命」「该不该自己干」时调用。 核心理念: 委托人(主人)会把事做好, 代理人会为自己利益优化; 收益与创造价值绑得越紧, 越像委托人; 别让媒体洗脑你需要代理人。 不适用于: 具体薪酬谈判数字、组织架构设计细节。 Triggers: 激励/代理/主人/打工 vs 创业/利益绑定/principal/agent/incentive.