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 skills add PolicyEngine/policyengine-claude --skill policyengine-toolsgit clone --depth 1 https://github.com/PolicyEngine/policyengine-claudeWrote 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/skills/policyengine/policyengine-claude/policyengine-tools)<a href="https://agentmods.dev/skills/policyengine/policyengine-claude/policyengine-tools"><img src="https://agentmods.dev/badge/skills/policyengine/policyengine-claude/policyengine-tools/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/skills/policyengine/policyengine-claude/policyengine-tools"><img src="https://agentmods.dev/badge/skills/policyengine/policyengine-claude/policyengine-tools.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Rogue Agent · line 92 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
- medium Excessive Agency · line 202 Skill allows unbounded resource consumption (API calls, storage, compute). Without rate limits or quotas, a compromised or misbehaving agent can cause denial-of-service or cost overruns.Fix: Set explicit rate limits, timeouts, and resource quotas for API calls, file operations, and compute. Implement circuit breakers for runaway loops.
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 | $0.00179 | $0.03839 |
| Opus 5.5 | $0.00072 | $0.01536 |
| Sonnet 5.5 | $0.00036 | $0.00768 |
| Haiku 4.5 | $0.00018 | $0.00384 |
Grade A, and why
policyengine-tools scanned grade A with 1 finding 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 1mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Vercel. Modal apps can silently disappear — if the frontend gets network errors, `curl` the How it starts
The opening of the file, as written. The whole thing — 266 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PolicyEngine standalone tools
How to build calculators, dashboards, and visualizations that deploy independently to Vercel
and slot into policyengine.org as Next.js multizones. New tools are their own repos; the
host (policyengine-app-v2/website/) proxies a URL path to each tool's Vercel deployment.
Required stack
- Next.js (App Router) — not Pages Router, not Vite as the app bundler (Vite only backs
Vitest).
next.config.ts+app/withlayout.tsx+page.tsx, TypeScript. - Tailwind v4, CSS-first — no
tailwind.config.{ts,js}.globals.cssis exactly:@import "tailwindcss"; @import "@policyengine/ui-kit/theme.css"; /* both required; Tailwind must come first */ - PostCSS is required for Next — create
postcss.config.mjswith{ plugins: { "@tailwindcss/postcss": {} } }and install@tailwindcss/postcss+postcssas devDeps. (A Vite tool uses the@tailwindcss/viteplugin instead and needs no PostCSS config.) The theme.css header itself states@tailwindcss/postcssis mandatory — the older "no postcss.config" guidance was wrong. @policyengine/ui-kit(bun add @policyengine/ui-kit) — use its components before building your own. See policyengine-design for the full 0.4.0 export list.- bun for everything (
bun install,bun run build,bunx;bun.lockcommitted). - Vercel deploy under the
policy-enginescope. Static-only tools may useoutput: 'export'; tools with a Modal backend stay server-rendered.
Scaffold: bunx create-next-app@latest my-tool --ts --app --tailwind --eslint --import-alias "@/*",
then bun add @policyengine/ui-kit and set up globals.css as above.
ui-kit components (verified 0.4.0)
Prefer these over hand-rolled equivalents; import from @policyengine/ui-kit:
| Need | Component |
|---|---|
| Page shell / layout | DashboardShell, SidebarLayout, SingleColumnLayout, InputPanel, ResultsPanel, Stack, Group, Container |
| Header + footer | Header, Footer (Header props: navItems, logoSrc, linkComponent, countries — not variant/navLinks) |
| Inputs | CurrencyInput, NumberInput, SelectInput, CheckboxInput, SliderInput, InputGroup |
| Primitives | Button, Card, Badge, Tabs, Dialog, Select, Tooltip, Alert, Switch, SegmentedControl, … |
| Display | MetricCard, SummaryText, DataTable, PolicyEngineWatermark |
| Charts | ChartContainer, PEBarChart, PELineChart, PEAreaChart, PEWaterfallChart |
| Maps | USDistrictChoroplethMap, UKConstituencyChoroplethMap, HexagonalMap, HouseholdGraph |
| Utils | formatCurrency, formatPercent, formatNumber, cn, logos |
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.
- 1mo ago First seen · 266 lines · 179 tokens per session scan A 069a757b4937
policyengine-tools is a skill published in the GitHub repository PolicyEngine/policyengine-claude (32 stars, last pushed 2d ago), licensed MIT. It adds 179 tokens to every session and 3,839 once invoked, about $0.0007 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
anti-slop-design
Autonomous Principal Design Technologist. Cures vibe-coded software from AI frontend slop using curated token archetypes and 7-axis quality gating.
chakra-ui-builder
Build responsive, accessible UI components and layouts using Chakra UI v3, install or configure Chakra UI in new and existing projects, and design scalable themes using tokens, semantic tokens, recipes, and slot recipes. Use this skill whenever a user asks to build, create, or generate any UI component, page, form…
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
prototype-web
A clickable, high-fidelity web product prototype with navigation, a hero section, feature cards, steps, social proof, and optional pricing. It is designed to resemble a finished landing page while remaining a prototype.
frontend-visual-qa
Audits rendered UI and specific task/object-link handoffs; excludes ordinary source citations alone. Audits already-rendered UI and Markdown/Obsidian image layout — web app, deck/slide, dashboard, design-system, or Electron/native app — via real-browser/native-app journeys and a Playwright sweep. Use after UI…
waitlist-page
A simple waitlist page for collecting email addresses from people interested in a new product or early-access release.