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.
curl -O https://raw.githubusercontent.com/noizu-labs-ml/NoizuPromptLingo/main/.claude/commands/update-arch-v2.mdgit clone --depth 1 https://github.com/noizu-labs-ml/NoizuPromptLingoWrote 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.
[](https://agentmods.dev/commands/noizu-labs-ml/noizupromptlingo/update-arch-v2)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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 |
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.
- 6d ago First seen · 477 lines · 61 tokens per session scan A 12798097ec9a
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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.