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-skill-programnpx skills add PostHog/wizard --skill adding-skill-programgit 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 | $0.00073 | $0.01776 |
| Opus 5 | $0.00036 | $0.00888 |
| Sonnet 5 | $0.00015 | $0.00355 |
| Haiku 4.5 | $0.00007 | $0.00178 |
Grade A, and why
adding-skill-program 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 — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Adding a Skill-Based Program
A skill-based program installs a context-mill skill and runs the agent against it. Examples in the codebase: the audit program (clean factory call), the revenue-analytics program (factory + custom intro screen + detect step).
Before reading this, read wizard-development/SKILL.md for the architectural context — particularly principle 4 ("New capability is a new program, not a new branch").
Architecture
The wizard's runner pipeline is fixed. What varies between programs is a ProgramRun configuration object that controls the skill ID, prompt, success message, abort cases, and post-run hooks. A ProgramConfig ties together: the CLI command, the step list, and the ProgramRun. The program registry derives all downstream wiring — CLI subcommands, TUI programs, the router — from a single array. Adding a program is configuration, not code.
The common case: createSkillProgram
For programs that just install a skill and let the agent run it (most programs), use the factory in agent-skill/index.ts:
// src/lib/programs/error-tracking/index.ts
import { createSkillProgram } from '../agent-skill/index.js';
export const errorTrackingConfig = createSkillProgram({
skillId: 'error-tracking-setup',
command: 'errors',
flowKey: 'error-tracking',
description: 'Set up PostHog error tracking',
integrationLabel: 'error-tracking',
successMessage: 'Error tracking configured!',
reportFile: 'posthog-error-tracking-report.md',
docsUrl: 'https://posthog.com/docs/error-tracking',
spinnerMessage: 'Setting up error tracking...',
estimatedDurationMinutes: 5,
requires: ['posthog-integration'], // optional: prior programs that must run first
});
Then register it in one place:
src/lib/programs/program-registry.ts— add toPROGRAM_REGISTRYarray
That's the entire program. bin.ts, the store, the agent runner, the router, and the screen sequences (src/ui/tui/screen-sequences.ts) all derive their wiring from the registry automatically. Don't add a yargs command. Don't add a runner function. Don't touch bin.ts. The ProgramId union type updates itself from the registry contents.
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 · 160 lines · 73 tokens per session scan A 88b8e7557520
adding-skill-program is a skill published in the GitHub repository PostHog/wizard (190 stars, last pushed 2d ago), licensed MIT. It adds 73 tokens to every session and 1,776 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.