permit0: Agent for Claude Code

.github/agents/reviewer-arch.md

reviewer-arch is an agent for Claude Code from permit0-ai/permit0. It costs 0 tokens per session (144 once invoked), scanned A, original, Apache-2.0.

A browser-automation command-line tool that lets an AI agent open websites, inspect their controls, enter information, click buttons, wait for pages, take screenshots, and extract data.

In plain words
What is it for?
Use it to test web apps, complete forms, navigate sites, collect information, and automate browser-based tasks.
Why use it?
It handles repetitive website interactions that are difficult to perform through ordinary code alone, especially when pages change after each action.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

This is permit0-ai/permit0's own configuration. It tells Claude Code how to work on permit0 itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything permit0 configures →

Reuse

Borrowing it

Nothing to install: this file belongs to permit0-ai/permit0. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/permit0-ai/permit0/main/.github/agents/reviewer-arch.md
Clone the repo
git clone --depth 1 https://github.com/permit0-ai/permit0

Made for: Claude Code.

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 reviewer-arch

README.md
[![agentmods](https://agentmods.dev/badge/agents/permit0-ai/permit0/reviewer-arch.svg)](https://agentmods.dev/agents/permit0-ai/permit0/reviewer-arch)
Your own site
<a href="https://agentmods.dev/agents/permit0-ai/permit0/reviewer-arch"><img src="https://agentmods.dev/badge/agents/permit0-ai/permit0/reviewer-arch.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 144 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 5.1 $0.00000 $0.00144
Opus 5 $0.00000 $0.00072
Sonnet 5 $0.00000 $0.00029
Haiku 4.5 $0.00000 $0.00014

Measured 6d ago against content hash 811ebab6e92b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

reviewer-arch 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 6d 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.

.github/agents/reviewer-arch.md · 15 lines

What it actually says

You are the architecture reviewer in the Polis automated pipeline.

Inspect the architecture document named in your task prompt (read it on the current branch). Assess ONLY: soundness of the approach, phasing, major risks, and whether the ## Work breakdown is coherent and buildable. Use "block" for genuine architectural problems that should be fixed before decomposition.

Submit a GitHub PR review using gh with comments where you find issues.

Then write ONLY a JSON object to the output file you are told, with this exact shape: {"verdict": "approve", "summary": "..."} or {"verdict": "block", "summary": "..."} Keep the summary to one paragraph.

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. 6d ago First seen · 15 lines · 0 tokens per session scan A 811ebab6e92b

Subscribe to this mod's changes

reviewer-arch is an agent published in the GitHub repository permit0-ai/permit0 (185 stars, last pushed 2mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 144 tokens. 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.