Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/PolicyEngine/policyengine-claudenpx agentmods add commands/policyengine/policyengine-claude/new-toolWrote 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/commands/policyengine/policyengine-claude/new-tool)<a href="https://agentmods.dev/commands/policyengine/policyengine-claude/new-tool"><img src="https://agentmods.dev/badge/commands/policyengine/policyengine-claude/new-tool/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/commands/policyengine/policyengine-claude/new-tool"><img src="https://agentmods.dev/badge/commands/policyengine/policyengine-claude/new-tool.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 | $0.00044 | $0.03435 |
| Opus 5.5 | $0.00018 | $0.01374 |
| Sonnet 5.5 | $0.00009 | $0.00687 |
| Haiku 4.5 | $0.00004 | $0.00344 |
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 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.
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 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:
- Tool name (kebab-case, e.g.,
marriage,aca-calc,salary-sacrifice-tool) - Countries (us, uk, or both)
- 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)
- 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.
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 · 418 lines · 44 tokens per session scan C aea4c6ae9688
new-tool is a command published in the GitHub repository PolicyEngine/policyengine-claude (32 stars, last pushed 2d ago), licensed MIT. It adds 44 tokens to every session and 3,435 once invoked, about $0.0002 per session on Opus 5.5. 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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
speckit.bug.fix
Apply the remediation from a bug assessment and record what was changed.