NoizuPromptLingo: Command for Claude Code

.claude/commands/update-arch-v2.md

update-arch is a command for Claude Code from noizu-labs-ml/NoizuPromptLingo. It costs 61 tokens per session (2,810 once invoked), scanned A, original, MIT.

A command that refreshes architecture documentation in a project’s docs/PROJECT-ARCH.md file and related sub-files. It compares the documents with the code, expands unfinished files, and keeps human-written edits and decisions.

In plain words
What is it for?
Use it to expand initial architecture stubs, find differences between documentation and code, and regenerate stale sections of project architecture docs.
Why use it?
Architecture documents become outdated or remain as incomplete stubs as a codebase changes. This reduces that drift without regenerating sections that are still current or overwriting manual notes.

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-v2.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

README.md
[![agentmods](https://agentmods.dev/badge/commands/noizu-labs-ml/noizupromptlingo/update-arch-v2/github.svg)](https://agentmods.dev/commands/noizu-labs-ml/noizupromptlingo/update-arch-v2)
Your own site
<a href="https://agentmods.dev/commands/noizu-labs-ml/noizupromptlingo/update-arch-v2"><img src="https://agentmods.dev/badge/commands/noizu-labs-ml/noizupromptlingo/update-arch-v2/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-v2"><img src="https://agentmods.dev/badge/commands/noizu-labs-ml/noizupromptlingo/update-arch-v2.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 61 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,810 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 $0.00061 $0.02810
Opus 5 $0.00030 $0.01405
Sonnet 5 $0.00012 $0.00562
Haiku 4.5 $0.00006 $0.00281

Measured 6d ago against content hash 12798097ec9a, 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 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.

.claude/commands/update-arch-v2.md · 477 lines

How it starts

The opening of the file, as written. The whole thing — 477 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Update Architecture Documentation

Refresh and expand architecture documentation, updating stale content and expanding stub files with detailed analysis.

Inputs: Existing docs/PROJECT-ARCH.md and stub files Outputs: Updated docs/PROJECT-ARCH.md and expanded docs/PROJECT-ARCH/*.md sub-files

NPL Dependencies

Load NPL definitions before proceeding using the NPLLoad MCP tool:

NPLLoad(expression="syntax fences directives pumps")

See Also

  • Fence type reference (diagram, example, format)
  • Directive patterns (📐, 🗺️, 🔧, 📂)
  • Reasoning pump documentation
  • Agent declaration syntax

Design Philosophy

incremental : Only regenerate sections that are stale or incomplete — preserve manual edits

expand-stubs : Transform stub files from /init-project-fast into full detailed documentation

drift-detection : Identify discrepancies between documentation and current codebase

preserve-intent : Maintain architectural decisions and rationale added by humans


Phase 1: Analyze Current State

1.1 Inventory Existing Documentation

Check current documentation state:

inventory = {
    main_file: check_exists("docs/PROJECT-ARCH.md"),
    sub_files: glob("docs/PROJECT-ARCH/*.md"),
    stubs: [],
    detailed: [],
    missing: []
}

for file in inventory.sub_files:
    if contains(file, "Stub generated by init-project"):
        inventory.stubs.append(file)
    else:
        inventory.detailed.append(file)

# Expected sub-files per spec
expected = ["layers.md", "domain.md", "patterns.md", "infrastructure.md"]
for expected_file in expected:
    if expected_file not in inventory.sub_files:
        inventory.missing.append(expected_file)

1.2 Determine Update Mode

Condition Mode Action
No PROJECT-ARCH.md exists full-init Run /init-project instead
Stubs exist expand Expand stubs to detailed files
All detailed, possible drift refresh Validate and update stale sections
User requests specific section targeted Update only requested sections

Read the full file on GitHub · 477 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 · 477 lines · 61 tokens per session scan A 12798097ec9a

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 adds 61 tokens to every session and 2,810 once invoked, about $0.0003 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 2026-09-04.