update-arch

update-arch is a command for Claude Code from noizu-labs-ml/NoizuPromptLingo. It costs 0 tokens per session (692 once invoked), scanned A, original, MIT.

A documentation-maintenance command that keeps a project architecture overview short by moving oversized sections into separate files. Architecture documentation explains how a software system is organised.

In plain words
What is it for?
Use it to split large sections from PROJ-ARCH.md into docs/arch/ files, replace them with summaries, and preserve navigation to the details.
Why use it?
It prevents the main architecture file from becoming difficult to scan while retaining detailed information and checking links after content is moved.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md).

Good fit Use it to split large sections from PROJ-ARCH.md into docs/arch/ files, replace them with summaries, and preserve navigation to the details.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/noizu-labs-ml/noizupromptlingo/update-arch
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.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/noizu-labs-ml/noizupromptlingo/update-arch"><img src="https://agentmods.dev/badge/commands/noizu-labs-ml/noizupromptlingo/update-arch.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 692 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 $0.00692
Opus 5 $0.00000 $0.00346
Sonnet 5 $0.00000 $0.00138
Haiku 4.5 $0.00000 $0.00069

Measured 6d ago against content hash b7cbaaf8bce3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

update-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.

project-management/personas/commands/update-arch.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Update-Arch - Persona

Type: Command Category: Documentation Maintenance Version: 1.0.0

Overview

The update-arch command is a documentation maintenance utility that enforces size constraints on the project architecture documentation (PROJ-ARCH.md). It ensures the main architecture file remains concise and scannable by extracting detailed sections into separate files under docs/arch/ when size thresholds are exceeded.

Purpose & Use Cases

  • Monitor PROJ-ARCH.md for size violations (>300 lines total, >15 lines per section)
  • Extract bloated sections to dedicated detail files in docs/arch/
  • Maintain architectural overview as an entry point without overwhelming detail
  • Preserve readability by replacing extracted content with summaries and references
  • Support iterative documentation growth without degrading discoverability

Key Features

✅ Enforces strict size limits on main architecture file ✅ Automated extraction of oversized sections ✅ Generates summary replacements with links to detailed docs ✅ Maintains architectural essence in main file ✅ Creates standardized structure in arch/ subdirectory ✅ Validates link integrity after extraction

Usage

update-arch

The command analyzes docs/PROJ-ARCH.md, identifies sections exceeding size thresholds, and performs extraction when necessary. For each oversized section, it creates a detailed file at docs/arch/{section-name}.md, replaces the original content with a 2-4 sentence summary, and adds a reference link. The process ensures the main file remains under 300 lines while preserving key architectural insights.

Integration Points

  • Triggered by: Manual invocation when PROJ-ARCH.md grows unwieldy, or automated checks during doc updates
  • Feeds to: Architecture documentation structure (docs/arch/)
  • Complements: update-layout-doc (maintains PROJ-LAYOUT.md structure)

Parameters / Configuration

  • Size Limits: PROJ-ARCH.md < 300 lines, individual sections < 15 lines, arch/*.md files < 200 lines
  • Extraction Threshold: Sections exceeding ~15 lines or containing implementation details
  • Output Directory: docs/arch/ for extracted content
  • Summary Format: 2-4 sentence summary plus reference link
  • Link Pattern: → *See [arch/{section-name}.md](arch/{section-name}.md) for details*

Read the full file on GitHub · 71 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 · 71 lines · 0 tokens per session scan A b7cbaaf8bce3

Subscribe to this mod's changes

update-arch 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 692 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.