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.
git clone --depth 1 https://github.com/yonatangross/orchestkitWrote 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/rules/yonatangross/orchestkit/playground-visual-standard)<a href="https://agentmods.dev/rules/yonatangross/orchestkit/playground-visual-standard"><img src="https://agentmods.dev/badge/rules/yonatangross/orchestkit/playground-visual-standard/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/rules/yonatangross/orchestkit/playground-visual-standard"><img src="https://agentmods.dev/badge/rules/yonatangross/orchestkit/playground-visual-standard.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00038 | $0.04043 |
| Opus 5 | $0.00019 | $0.02021 |
| Sonnet 5 | $0.00008 | $0.00809 |
| Haiku 4.5 | $0.00004 | $0.00404 |
Grade A, and why
playground-visual-standard 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 3d 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 — 257 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Playground Visual Standard
Load when: generating any single-file HTML artifact — a playground that demonstrates a feature, user story, flow, or decision, or a plan/config/data/architecture dashboard. Skip for: the ASCII floor (no pixels, nothing here applies).
Dashboards used to be exempt here ("their current card layout is fine"). They are not exempt any more, and the exemption is why they drifted: across 191 shipped artifacts, ~93% were dashboards, and only 39% carried
--pg-tokens, 29% a reduced-motion gate, 24% a copy-prompt. The format that governs almost all output had no template to copy and no self-audit. §0 now routes DASHBOARD to a first-class archetype withplan-dashboard.template.htmland its own §10 rows.
A playground is not a slide. It is a thing the viewer can operate: play a user story, or make a decision by dragging. This standard makes that quality reproducible. Every rule carries a concrete, falsifiable value — a rule without a measurable threshold is not shippable.
Reference exemplars (read the one matching your archetype before building):
shared/assets/playground-exemplars/
homeos-arieh.html— canonical gold standard (user-story player, RTL Hebrew). Study the bar.user-story-player.template.html— generalized player scaffold (device mockup + transport + flow).decision-board.template.html— drag-and-drop prioritization toolkit (the decision archetype).release-notes-player.template.html— player recipe for release / changelog notes (release-feed chrome + per-step impact card). A specialization of the player archetype, not a new one: route release / "what's new" notes here; route adoption / triage / verdict views to a dashboard (§0).decision-router.template.html— execution-router variant of the decision board: triage (Now/Next/Later) plus routing each card to an ork strategy (single/workflow/nested/teams/swarm) + a plan-only invocation. Used byvisualize-planfor backlogs the user must prioritize and dispatch.plan-dashboard.template.html— dashboard (the volume archetype, ~93% of output). Sticky tier-1 header, anchored<details>sections[0]–[5], every chart paired with a table twin, 1-click copy-prompt, state in aplan-stateJSON island. Both palettes are defined side by side so the chrome↔marks seam is visible in the file. Used byvisualize-planfor plan/config/data views. Copy it; swapSTATE.living-plan.template.html— living plan (dashboard family): a plan that executes over multiple sessions/waves. Carries an embeddedlpp-stateJSON block; the visual layer renders FROM state. Sessions update the SAME file in place (flip item statuses, append changelog) — one plan = one file, never fork a second file for the same slug. Every item has anevidence("done when") check; done without evidence is a contract violation. Used byvisualize-planupdate mode andbrainstormPhase 6.
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.
- 3d ago First seen · 257 lines · 38 tokens per session scan A 026f197876f5
playground-visual-standard is a cursor rule published in the GitHub repository yonatangross/orchestkit (264 stars, last pushed today), licensed MIT. It adds 38 tokens to every session and 4,043 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 2026-09-09.
Other cursor rules, from other repositories
pn-design-system
Design system rule: enforces token usage when editing CSS, SCSS, or styled components. Use tokens for color, spacing, typography; avoid one-off values. For establishing or auditing a design system, use the pn-design-system skill.
pn-figma
Figma design-to-code conventions: token extraction, component mapping, naming alignment. Use when implementing designs from Figma or maintaining design-code sync.
components
Rules for component usage - which component libraries are allowed (shadcn/ui, Aceternity, Kibo, Magic UI, etc.), reuse over recreation, table implementation standards, and component modularization for both new features and existing components.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.