NoizuPromptLingo: Command for Claude Code

.claude/commands/update-arch-doc.md

update-arch-doc is a command for Claude Code from noizu-labs-ml/NoizuPromptLingo. It costs 0 tokens per session (996 once invoked), scanned A, original, MIT.

A command for maintaining a concise project architecture document, with detailed topics kept in linked files. Architecture documentation explains a system's main parts and how they fit together.

In plain words
What is it for?
Use it to update docs/PROJ-ARCH.md and organize detailed architecture notes under docs/arch/.
Why use it?
It keeps the main overview readable while providing a clear structure for deeper material such as data flow, API design, and infrastructure.

Command for Claude Code

Written for Claude Code: installed under .claude/.

This is noizu-labs-ml/NoizuPromptLingo's own configuration. It tells Claude Code how to work on NoizuPromptLingo 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 NoizuPromptLingo configures →

Reuse

Borrowing it

Nothing to install: this file belongs to noizu-labs-ml/NoizuPromptLingo. 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/noizu-labs-ml/NoizuPromptLingo/main/.claude/commands/update-arch-doc.md
Clone the repo
git clone --depth 1 https://github.com/noizu-labs-ml/NoizuPromptLingo

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 update-arch-doc

README.md
[![agentmods](https://agentmods.dev/badge/commands/noizu-labs-ml/noizupromptlingo/update-arch-doc/github.svg)](https://agentmods.dev/commands/noizu-labs-ml/noizupromptlingo/update-arch-doc)
Your own site
<a href="https://agentmods.dev/commands/noizu-labs-ml/noizupromptlingo/update-arch-doc"><img src="https://agentmods.dev/badge/commands/noizu-labs-ml/noizupromptlingo/update-arch-doc/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.

agentmods 80×15 button for update-arch-doc

Your own site · 80×15
<a href="https://agentmods.dev/commands/noizu-labs-ml/noizupromptlingo/update-arch-doc"><img src="https://agentmods.dev/badge/commands/noizu-labs-ml/noizupromptlingo/update-arch-doc.svg" alt="Reviewed on agentmods" width="80" 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 996 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00996
Opus 5 $0.00000 $0.00498
Sonnet 5 $0.00000 $0.00199
Haiku 4.5 $0.00000 $0.00100

Measured 6d ago against content hash aed7c1cf4c8c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

update-arch-doc 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.claude/commands/update-arch-doc.md · 139 lines

How it starts

The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PROJ-ARCH.md — Maintenance Guide

Purpose

docs/PROJ-ARCH.md provides a high-level architectural overview of the project. It should remain concise and scannable, serving as an entry point for understanding system design.

Structure

docs/
├── PROJ-ARCH.md          # Main architecture overview (keep small)
└── arch/
    ├── data-flow.md      # Detailed section documents
    ├── api-design.md
    ├── infrastructure.md
    └── ...

Content Guidelines

What to Include in PROJ-ARCH.md

  • System overview (2-3 paragraphs max)
  • Core components list with one-line descriptions
  • High-level diagrams (mermaid preferred)
  • Key design decisions and rationale (brief)
  • Technology stack summary
  • References to detailed arch/*.md files

Section Template

## [Section Name]

[2-4 sentence summary of this architectural concern]

→ *See [arch/section-name.md](arch/section-name.md) for details*

Size Limits

Location Target Size Action When Exceeded
PROJ-ARCH.md < 300 lines Extract sections to arch/
Individual sections < 15 lines Move to arch/{section}.md
arch/*.md files < 200 lines Consider further decomposition

When to Extract

Move content to arch/{section}.md when:

  1. A section exceeds ~15 lines
  2. The section contains implementation details beyond "what" into "how"
  3. The section includes extensive code examples
  4. Multiple subsections emerge within a section

Extraction Process

  1. Create docs/arch/{section-name}.md with full content
  2. Replace section in PROJ-ARCH.md with:
    • 2-4 sentence summary
    • Link to detailed document
  3. Ensure the summary captures the essence without requiring the reader to click through for basic understanding

Example PROJ-ARCH.md

# Project Architecture

## Overview

Brief description of what the system does and its primary architectural style
(e.g., microservices, monolith, event-driven).

## System Diagram

\`\`\`mermaid
graph TB
    A[Client] --> B[API Gateway]
    B --> C[Service A]
    B --> D[Service B]
    C --> E[(Database)]
\`\`\`

## Core Components

| Component | Purpose |
|-----------|---------|
| API Gateway | Request routing, auth |
| Service A | Handles X domain |
| Service B | Handles Y domain |

## Data Flow

Requests enter through the gateway, authenticate via JWT, and route to
appropriate services. Events propagate via message queue.

→ *See [arch/data-flow.md](arch/data-flow.md) for details*

## Infrastructure

Deployed on Kubernetes with Postgres and Redis backing stores.

→ *See [arch/infrastructure.md](arch/infrastructure.md) for details*

## Key Decisions

- **Why microservices**: Scaling requirements for component X
- **Why Postgres**: ACID compliance needed for financial data

→ *See [arch/decisions.md](arch/decisions.md) for ADRs*

Read the full file on GitHub · 139 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. 6d ago First seen · 139 lines · 0 tokens per session scan A aed7c1cf4c8c

Subscribe to this mod's changes

update-arch-doc is a command published in the GitHub repository noizu-labs-ml/NoizuPromptLingo (13 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 996 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 2026-09-04.