update-architecture

A command that updates architecture documentation after a software change. Architecture documentation describes the system's main parts, connections, technical choices, and patterns.

In plain words
What is it for?
Use it after implementing a feature or structural change to refresh the affected architecture files and decide whether any larger design issue needs separate discussion.
Why use it?
It helps keep project documentation aligned with code that has already shipped, including APIs, frontend and backend patterns, services, constraints, and domain terms. It also identifies deeper design questions raised by the change.

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/ayoubben18/ab-method/update-architecture
Clone the repo
git clone --depth 1 https://github.com/ayoubben18/ab-method

Made for: Claude Code.

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 394 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 $0.00394
Opus 5 $0.00000 $0.00197
Sonnet 5 $0.00000 $0.00079
Haiku 4.5 $0.00000 $0.00039

Measured 3d ago against content hash 32698592cc4f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

update-architecture 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/update-architecture.md · 41 lines

What it actually says

Update Architecture

Description

Update and maintain architecture documentation to keep technical documentation current with project changes.

Usage

/update-architecture

Behavior

Loads and executes the update-architecture workflow from .ab-method/core/update-architecture.md

This workflow will:

  1. Identify what shipped (from the latest progress-tracker.md summaries, git diff, or user description)
  2. Refresh the architecture docs that the change touches:
    • APIs/endpoints in tech-stack.md (Entry Points) — checked every run, even if the user didn't mention APIs
    • Patterns in frontend-patterns.md / backend-patterns.md
    • Stack / external services / constraints / testing in tech-stack.md
    • Domain terms in UBIQUITOUS_LANGUAGE.md / CONTEXT.md
  3. Invoke the improve-codebase-architecture skill scoped to the changed files — surfaces deepening opportunities the change just created or revealed, drops into a grilling loop on the candidate the user picks
  4. Defer hard-to-reverse / domain-reshape decisions to /domain-model (which captures ADRs properly)

Workflow Details

  • Always checks APIs — Entry Points drift is the most common stale-doc issue
  • Always runs improve-codebase-architecture scoped to the change — docs catch the what; the skill catches the architectural debt the change just introduced
  • Incremental — adds new content; deprecates with [DEPRECATED <date>] instead of deleting

Examples

/update-architecture
# Reviews and updates architecture documentation
# Ensures technical docs reflect current project state
# Maintains consistency for accurate task planning

Alternative Usage

You can also use the traditional AB Method master controller:

/ab-master update-architecture
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 · 41 lines · 0 tokens per session scan A 32698592cc4f

Subscribe to this mod's changes

update-architecture is a command published in the GitHub repository ayoubben18/ab-method (187 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 394 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.