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/posthog-foss/building-product-empty-statesnpx skills add PostHog/posthog-foss --skill building-product-empty-statesgit clone --depth 1 https://github.com/PostHog/posthog-fossWhat 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 | $0.00124 | $0.03587 |
| Opus 5 | $0.00062 | $0.01793 |
| Sonnet 5 | $0.00025 | $0.00717 |
| Haiku 4.5 | $0.00012 | $0.00359 |
Grade A, and why
building-product-empty-states 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 today.
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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Building product empty states
Before a user has set a product up, its scene should show a setup empty state: the product pitch and install command on the left, an animated preview of the product filled with realistic example data on the right. The shared component lives in frontend/src/lib/components/ProductEmptyState/; MCP analytics (products/mcp_analytics/frontend/emptyState/) is the reference adoption.
ProductIntroduction is deprecated — don't add new call sites. Both of its jobs fold into this system: "product not installed" (data-existence detection) and "no entities yet" (entity-count detection with a primaryAction create CTA).
How it works
- A scene declares
emptyStateon itsSceneExport. The app shell (frontend/src/scenes/App.tsx) wraps the scene inProductEmptyStateGate— the scene component itself contains no empty-state branching. - The gate mounts the product's detection logic, which pushes a normalized status into
productSetupStatusLogic({ productKey })— the app-wide single read point for "is product X set up?". - The gate renders the setup empty state for
needs-setup/waiting-for-data, and the scene untouched forhas-data. Whileloadingit shows the standard scene-level spinner — the one shared loading treatment. Never add a product-specific loading fallback. - Statuses are preloaded at app boot:
productSetupPreloadLogic(mounted inApp.tsx) answers every manifest-declared probe (each product'ssetupProbe, aggregated intoproductSetupProbes) with one combined event-count query on idle, so by the time a user opens the scene the status is usually already known and the spinner never shows. The product's in-scene detection stays the fresher source of truth. - Users can skip by default. Skip is local-only (localStorage, keyed team + product, never backend-persisted); detection keeps polling, and a slim "Set up" banner stays visible until data lands. Creation-first products whose gated scene is just an empty list can set
skippable: falseon the config to drop the escape hatch — the primary action is the only next step anyway.
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.
- today Changed · +1 lines 436d0abda7f6
- yesterday First seen · 131 lines · 124 tokens per session scan A ce79837ae35d
building-product-empty-states is a skill published in the GitHub repository PostHog/posthog-foss (713 stars, last pushed today), licensed MIT. It adds 124 tokens to every session and 3,587 once invoked, about $0.0006 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…