arch

arch is a command for Claude Code from ngocsangyem/MeowKit. It costs 0 tokens per session (463 once invoked), scanned A, original, MIT.

A command set for Architecture Decision Records, or short documents that record important technical choices and why they were made. It also examines the architectural effect of proposed changes.

In plain words
What is it for?
Use it to create, list, and review decision records, or assess the architectural impact of a planned change.
Why use it?
It keeps design decisions discoverable instead of leaving them in conversations or personal notes. Reviewing old records helps reveal when a decision no longer fits the system.

Command for Claude Code

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 commands/ngocsangyem/meowkit/arch
Clone the repo
git clone --depth 1 https://github.com/ngocsangyem/MeowKit

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 arch

README.md
[![agentmods](https://agentmods.dev/badge/commands/ngocsangyem/meowkit/arch.svg)](https://agentmods.dev/commands/ngocsangyem/meowkit/arch)
Your own site
<a href="https://agentmods.dev/commands/ngocsangyem/meowkit/arch"><img src="https://agentmods.dev/badge/commands/ngocsangyem/meowkit/arch.svg" alt="Measured on agentmods" 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 463 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 $0.00463
Opus 5 $0.00000 $0.00231
Sonnet 5 $0.00000 $0.00093
Haiku 4.5 $0.00000 $0.00046

Measured 3d ago against content hash 07e047aba717, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 3d 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/mk/arch.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/arch — Architecture Decision Records

Usage

/arch new [title]
/arch list
/arch review [number]
/arch impact [change description]

Behavior

Architecture as a first-class concern. Manages Architecture Decision Records (ADRs) and analyzes architectural impact of proposed changes.

Modes

/arch new [title]

Generate a new ADR using the architect agent.

  1. Assign the next sequential ADR number.
  2. Gather context: What decision needs to be made? What are the constraints? What options exist?
  3. Generate ADR with sections: Title, Status (Proposed), Context, Decision, Consequences, Alternatives Considered.
  4. Write to docs/architecture/adr/YYMMDD-title.md.
  5. Print summary and ask for review.
/arch list

List all ADRs with their current status.

  1. Scan docs/architecture/adr/ directory.
  2. Print table:
    # | Title                        | Status
    1 | Use PostgreSQL for persistence | Accepted
    2 | Event-driven architecture     | Proposed
    3 | Monorepo structure            | Superseded by #5
    
/arch review [number]

Review and update an existing ADR.

  1. Read the specified ADR.
  2. Evaluate: Is the decision still valid? Has context changed? Are there new alternatives?
  3. Update status if needed: Proposed → Accepted, Accepted → Deprecated, Accepted → Superseded by #N.
  4. Add review notes with date.
/arch impact [change description]

Analyze the architectural impact of a proposed change.

  1. Parse the change description.
  2. Identify which architectural decisions (ADRs) are affected.
  3. Identify which system boundaries are crossed.
  4. Assess: Does this change align with existing ADRs or conflict with them?
  5. Print impact assessment: affected components, affected ADRs, risk level, recommendation.

Output

  • For new: ADR file at docs/architecture/adr/YYMMDD-title.md
  • For list: table of all ADRs
  • For review: updated ADR file
  • For impact: printed impact assessment with affected components and recommendations

Read the full file on GitHub · 66 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. 3d ago First seen · 66 lines · 0 tokens per session scan A 07e047aba717

Subscribe to this mod's changes

arch is a command published in the GitHub repository ngocsangyem/MeowKit (14 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 463 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.