new-tool

A project starter for building a standalone PolicyEngine calculator or widget. It sets up a Next.js web app, styling, user-interface components, and code for embedding the result in policyengine.org.

In plain words
What is it for?
Use it to start tools such as salary, health-care, or marriage-penalty calculators. It supports projects that use prepared data, the PolicyEngine calculation service, or a custom model service.
Why use it?
It removes the repetitive setup work needed before writing the calculator’s specific logic. It also helps distinguish a one-purpose tool from a multi-page policy analysis dashboard.

Command

Install

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.

agentmods
npx agentmods add commands/policyengine/policyengine-claude/new-tool
Clone the repo
git clone --depth 1 https://github.com/PolicyEngine/policyengine-claude
Per session 44 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,435 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00044 $0.03435
Opus 5 $0.00022 $0.01717
Sonnet 5 $0.00009 $0.00687
Haiku 4.5 $0.00004 $0.00344

Measured 2d ago against content hash aea4c6ae9688, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

new-tool scanned grade C with 2 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 2d 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

curl -fsSL https://raw.githubusercontent.com/PolicyEngine/policyengine-skills/main/scripts/audit_next_migration.py | python3 - --root .

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -fsSL https://raw.githubusercontent.com/PolicyEngine/policyengine-skills/main/scripts/audit_next_migration.py -o /tmp/audit_next_migration.py
commands/new-tool.md · 418 lines

How it starts

The opening of the file, as written. The whole thing — 418 lines — stays where its author put it; the contents beside it link to each section on GitHub.

New interactive tool scaffold

Creates a complete project for a standalone PolicyEngine interactive tool that embeds in policyengine.org.

When to use vs /create-dashboard

  • /new-tool (this command) — one-purpose calculator or widget. Ships with design tokens + embedding boilerplate; you write the specific tool logic. Examples: salternative, aca-calc, marriage-penalty-calculator.
  • /create-dashboard — multi-page policy analysis app with multi-agent plan/scaffold/implement/validate. Use when there are multiple views, comparison modes, filters, or the dashboard is answering a research question rather than performing a calculation.

Step 1: Gather requirements

Ask the user for:

  1. Tool name (kebab-case, e.g., marriage, aca-calc, salary-sacrifice-tool)
  2. Countries (us, uk, or both)
  3. Data pattern — how the tool gets model results:
    • A) Precomputed — Static JSON or CSV shipped with the app (best for finite parameter spaces)
    • B) PolicyEngine API — Direct calls to api.policyengine.org/us/calculate (best for household calculators)
    • C) Custom Modal API — Python serverless function with the top-level policyengine[us] / policyengine[uk] package (best when main API doesn't support needed variables/reforms)
  4. Brief description of what the tool calculates

Step 2: Create the project

# Create Next.js 14 + Tailwind project
bunx create-next-app@14 TOOL_NAME --js --app --tailwind --eslint --no-src-dir --import-alias "@/*"
cd TOOL_NAME

# Install dependencies
bun add @policyengine/ui-kit recharts
bun add -D vitest

Copy the favicon:

mkdir -p public
cp node_modules/@policyengine/ui-kit/src/assets/logos/policyengine/teal-square.svg public/favicon.svg

If using code highlighting:

bun add prism-react-renderer

Step 3: Generate project files

Create the following files with the content specified below. Replace TOOL_NAME, TOOL_TITLE, DESCRIPTION, and COUNTRY_ID with actual values.

Read the full file on GitHub · 418 lines

Changes

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.

  1. 2d ago First seen · 418 lines · 44 tokens per session scan C aea4c6ae9688

Subscribe to this mod's changes

new-tool is a command published in the GitHub repository PolicyEngine/policyengine-claude (31 stars, last pushed 7d ago), licensed MIT. It adds 44 tokens to every session and 3,435 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.