audit-multizone

audit-multizone is a command for coding agents from PolicyEngine/policyengine-claude. It costs 30 tokens per session (1,166 once invoked), scanned A, original, MIT.

A read-only checker for PolicyEngine Next.js zone apps. A multi-zone app is a site split into separate sections that share a main host, and Next.js is a framework for building web applications.

In plain words
What is it for?
Checking base paths, asset paths, Vercel settings, host rewrites, and links between zones in an existing Next.js application.
Why use it?
It finds configuration problems that could break a zone on the main PolicyEngine site, a Vercel preview, or local development before deployment.

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/audit-multizone
Clone the repo
git clone --depth 1 https://github.com/PolicyEngine/policyengine-claude

Wrote 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.

agentmods badge for audit-multizone

README.md
[![agentmods](https://agentmods.dev/badge/commands/policyengine/policyengine-claude/audit-multizone.svg)](https://agentmods.dev/commands/policyengine/policyengine-claude/audit-multizone)
Your own site
<a href="https://agentmods.dev/commands/policyengine/policyengine-claude/audit-multizone"><img src="https://agentmods.dev/badge/commands/policyengine/policyengine-claude/audit-multizone.svg" alt="Measured on agentmods" height="20"></a>
Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,166 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 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 $0.00030 $0.01166
Opus 5 $0.00015 $0.00583
Sonnet 5 $0.00006 $0.00233
Haiku 4.5 $0.00003 $0.00117

Measured 3d ago against content hash 97036dda8e75, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

audit-multizone 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.

commands/audit-multizone.md · 132 lines

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.

Multi-zone Audit: $ARGUMENTS

READ-ONLY MODE: This command audits an existing PolicyEngine Next.js tool for multi-zone compliance and reports findings. It does NOT make code changes.

Use this to verify that a zone will work correctly behind policyengine.org, in its own Vercel preview, and in next dev.

Migration-era command. This exists to retrofit existing PolicyEngine Next.js tools (built before the multi-zone architecture was standardized) and to verify tools built outside the /create-dashboard flow. Once all PolicyEngine Next.js apps conform to the multi-zone architecture, this command can be removed — new apps created via /create-dashboard are already validated by the dashboard validators at scaffold time.

Scope

This command audits Next.js zone apps — tools that deploy as a zone behind policyengine-app-v2/website/. It does not apply to:

  • policyengine-app-v2 itself (the host — different rules)
  • Legacy iframe-embedded tools (not yet migrated to multi-zone)
  • Non-Next.js tools (Python/Modal dashboards, static GitHub Pages sites)

The underlying agent (multizone-validator) detects these cases and stops with a clear message.

Options

  • --repo OWNER/NAME — Audit a specific GitHub repo (clones it to /tmp)
  • --path ABSOLUTE_PATH — Audit a local path (e.g., a worktree or sibling clone)
  • No arguments — Audit the current working directory

Examples

/audit-multizone                                        # Audit current working directory
/audit-multizone --repo PolicyEngine/keep-your-pay-act  # Clone and audit a GitHub repo
/audit-multizone --path /Users/me/Work/household-api-docs

Phase 0: Parse arguments

Parse $ARGUMENTS:
- REPO_ARG: value after --repo if present
- PATH_ARG: value after --path if present
- If neither: use current working directory

Phase 1: Resolve target path

If --repo OWNER/NAME is provided:

TARGET_PATH=/tmp/audit-multizone-REPO_NAME
if [ ! -d "$TARGET_PATH" ]; then
  gh repo clone OWNER/NAME "$TARGET_PATH"
else
  (cd "$TARGET_PATH" && git pull)
fi

Read the full file on GitHub · 132 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. 3d ago First seen · 132 lines · 30 tokens per session scan A 97036dda8e75

Subscribe to this mod's changes

audit-multizone is a command published in the GitHub repository PolicyEngine/policyengine-claude (32 stars, last pushed yesterday), licensed MIT. It adds 30 tokens to every session and 1,166 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 2026-08-30.