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/posthog/wizard/wizard-developmentnpx skills add PostHog/wizard --skill wizard-developmentgit clone --depth 1 https://github.com/PostHog/wizardWhat 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 | $0.00085 | $0.04142 |
| Opus 5 | $0.00043 | $0.02071 |
| Sonnet 5 | $0.00017 | $0.00828 |
| Haiku 4.5 | $0.00009 | $0.00414 |
Grade A, and why
wizard-development 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 yesterday.
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 — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wizard Development
This skill teaches the design discipline behind the wizard's architecture. The procedural skills tell you how to add things. This skill tells you why the system is shaped the way it is, so you can make good decisions when extending into territory no existing skill covers.
Read this first. Then any procedural skill that's relevant for what you're building.
The core discipline
Every architectural decision in this codebase is guided by one question:
Who will need to change this next, and what's the smallest thing they should have to understand?
This question produces a specific, testable commitment: product knowledge never enters infrastructure code. The runner pipeline, the TUI store, the detection loop, the prompt assembler — these are machinery. They don't know what PostHog is. They don't know what a framework is. They execute a pipeline driven by configuration.
The knowledge — what PostHog needs from a Next.js project, how to detect SvelteKit, what security rules to enforce — lives in configuration surfaces with typed boundaries:
| Which domain has leverage | Where it lives | What they need to understand |
|---|---|---|
| Frameworks | FrameworkConfig (~70-120 lines) |
Detection, env vars, prompts |
| Docs | Skill markdown in context-mill | Workflow steps, example code |
| Security | YARA-X rules in the warlock sibling repo | Rule content (patterns, severity, category). Wizard wires the engine via hooks. |
| Context | Step array in programs/ |
Gates, screens, predicates |
| UI | Screen component + primitives | Ink, store getters, layout |
| Agent development | Runner, store, detection loop, tools | The machinery itself |
These tight boundaries increase the scope of who is able to contribute to the wizard, while lowering the costs of those contributions. PostHog has a variety of skillsets across many kinds of teams. The wizard should be as accessible to contributions as possible to as many contributor skill sets as possible.
What ships with it
3 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.
- yesterday First seen · 190 lines · 85 tokens per session scan A 5c88c9ace9ee
wizard-development is a skill published in the GitHub repository PostHog/wizard (190 stars, last pushed 2d ago), licensed MIT. It adds 85 tokens to every session and 4,142 once invoked, about $0.0004 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
cep-wizard
Launch a local, localhost-only browser wizard with two journeys — layout onboarding for a project with ult-repo-layout installed, initialized or not — guides an uninitialized or not-yet-discovered repo through Run Discover, then shows resolved layer/slot state through four labeled boxes and a directory picker, and…
suanfish-design-system
算鱼设计系统(Suanfish)——多智能体界面设计系统。当用户要设计、制作、优化、重构或评审网页前端界面与交互体验时调用。常见说法包括：做个页面、做个登录页或注册页、搞个落地页或首屏、做个后台管理界面、加个弹窗或二次确认、做个多步表单或向导、画个图表或做数据看板/仪表盘、整个聊天或智能体对话界面、做个新手引导、加个动效动画、调个样式或配色、美化一下界面、优化交互体验、改改界面布局、做个空状态或图标、写界面文案、做响应式或移动端适配、做无障碍优化，以及需要多视角设计评审与辩证式批判体检时。由一支虚拟设计工作室的数十位专科匠人协作，保证品牌语言、设计令牌、动效、无障碍全程统一。技术栈以 React 与 Tailwind…
find-your-level
Interactive quiz that maps your AI/ML knowledge to a starting point in the 523-lesson, 20-phase AI Engineering from Scratch curriculum. Trigger phrases: "where should I start", "find my level", "what do I know", "which phase", "assess my knowledge", "placement test", "skip ahead".
start-learning
One-time onboarding for the AI Engineering from Scratch curriculum (523 lessons, 20 phases). Interviews the learner, runs the placement quiz, and writes LEARNING.md, a persistent study plan the learn skill drives. Trigger phrases: "start learning", "set up the course", "begin the curriculum", "onboard me", "create my…
cudaq-guide
CUDA-Q onboarding guide for installation, test programs, GPU simulation, QPU hardware, and quantum applications.
hr-onboarding
首周日程 + buddy + 学习路径 + 设备 + 完成标准.