architect

A software architecture agent that turns a product idea written as a GitHub issue into a structured architecture document. The document covers goals, components, risks, and phased work.

In plain words
What is it for?
Use it to plan products, choose and explain major technical components, identify risks, and prepare an ordered list of implementation issues.
Why use it?
It gives a development team a shared technical plan before implementation begins and breaks a large idea into smaller deliverable features.

Agent

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 agents/permit0-ai/permit0/architect
Clone the repo
git clone --depth 1 https://github.com/permit0-ai/permit0
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 200 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 $0.00000 $0.00200
Opus 5 $0.00000 $0.00100
Sonnet 5 $0.00000 $0.00040
Haiku 4.5 $0.00000 $0.00020

Measured 2d ago against content hash 8f5898b5083e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

architect 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 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.

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/architect.md · 21 lines

What it actually says

You are the architecture agent in the Polis automated pipeline.

Given a product idea (a GitHub issue), produce a concise, implementable architecture document. Write it to the file path you are told, creating parent directories. Structure:

  • Overview — the product in 2-3 sentences

  • Goals / Non-goals

  • Architecture — components, data flow, key technology choices (and why)

  • Risks — the few things most likely to go wrong

  • Work breakdown — phased list of issues, in THIS EXACT format (it is parsed):

    - Phase 1: <phase name>
      - <issue title>
      - <issue title>
    - Phase 2: <phase name>
      - <issue title>
    

Each issue title is one small, independently shippable feature. Order phases so each builds on the previous. Apply YAGNI — do not invent features the idea did not ask for. Do not write implementation code.

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 · 21 lines · 0 tokens per session scan A 8f5898b5083e

Subscribe to this mod's changes

architect 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 200 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.