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/adding-framework-supportnpx skills add PostHog/wizard --skill adding-framework-supportgit 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 | $0.00056 | $0.01394 |
| Opus 5 | $0.00028 | $0.00697 |
| Sonnet 5 | $0.00011 | $0.00279 |
| Haiku 4.5 | $0.00006 | $0.00139 |
Grade A, and why
adding-framework-support 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Adding Framework Support
Architecture Overview
Every framework integration is a single FrameworkConfig object. The wizard has no switch statements or per-framework routing — everything is data-driven through:
FrameworkConfig(src/lib/framework-config.ts) — the interface each framework implementsFRAMEWORK_REGISTRY(src/lib/registry.ts) — mapsIntegrationenum values to configsIntegrationenum (src/lib/constants.ts) — enum order determines detection priority and menu display order
The universal runner (src/lib/agent-runner.ts) handles all shared behavior: debug logging, version checking, welcome message, beta notices, AI consent, credential flow, agent execution, error handling, and outro messaging.
Steps to Add a New Framework
1. Add to the Integration enum and labels
In src/lib/constants.ts, add the new value to Integration. Enum order matters — it controls both the detection priority (first match wins) and the display order in the CLI select menu. The display label comes from metadata.name in your FrameworkConfig.
export enum Integration {
// ... existing entries
rails = 'rails', // insert at the desired detection/display position
}
2. Create the agent config file
Create src/<framework>/<framework>-wizard-agent.ts. This file exports:
- A context type for framework-specific data
- A
FrameworkConfig<TContext>object (the full integration definition) - A thin runner function that just calls
runAgentWizard(CONFIG, options)
Define a context type for any data gathered before the agent runs, then pass it as the generic parameter. Use type (not interface) so it satisfies the Record<string, unknown> constraint:
type RailsContext = {
projectType?: RailsProjectType;
gemfilePath?: string;
};
export const RAILS_AGENT_CONFIG: FrameworkConfig<RailsContext> = {
// All context-consuming callbacks (getTags, getOutroChanges, etc.)
// are now fully typed — no `any` casts needed.
};
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 · 135 lines · 56 tokens per session scan A 9e2588c278fd
adding-framework-support is a skill published in the GitHub repository PostHog/wizard (190 stars, last pushed 2d ago), licensed MIT. It adds 56 tokens to every session and 1,394 once invoked, about $0.0003 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.