What is architecture-methodology?

A guided method for designing software architecture through four phases: requirements, overall structure, individual components, and final review. It controls which decisions can be made at each phase.

Use it to analyse a product requirements document, choose an architecture pattern, map components, decide shared concerns such as security and monitoring, and produce a final design.

It prevents technology and component choices from being made before the requirements and overall design are understood. It also requires earlier decisions to be accepted before later work proceeds.

architecture-methodology — Skill for Claude Code by AhmedHabiba

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.

Any agent

npx skills add AhmedHabiba/architor --skill architecture-methodology

Clone the repo

git clone --depth 1 https://github.com/AhmedHabiba/architor

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/ahmedhabiba/architor/architecture-methodology/github.svg)](https://agentmods.dev/skills/ahmedhabiba/architor/architecture-methodology)

Your own site

<a href="https://agentmods.dev/skills/ahmedhabiba/architor/architecture-methodology"><img src="https://agentmods.dev/badge/skills/ahmedhabiba/architor/architecture-methodology/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/ahmedhabiba/architor/architecture-methodology"><img src="https://agentmods.dev/badge/skills/ahmedhabiba/architor/architecture-methodology.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 118 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,315 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.

Model	Per session	Once invoked
Fable 5.1	$0.00118	$0.01315
Opus 5.5	$0.00047	$0.00526
Sonnet 5.5	$0.00024	$0.00263
Haiku 4.5	$0.00012	$0.00131

Measured 2mo ago against content hash d946c79c44fb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

architecture-methodology 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 2mo 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/skills/architecture-methodology/SKILL.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Architecture Methodology Orchestrator

When This Skill Activates

Any conversation about system architecture, technology choices, component design, PRD analysis, or solution design.

Phase Definitions

Phase	Name	Purpose
1	Evaluation	Analyse PRDs, extract functional and non-functional requirements, identify constraints and risks. No technology or component decisions yet.
2A	Pattern	Select the architecture pattern (e.g. event-driven, microservices, monolith) and justify the choice.
2B	Component Map	Establish the high-level component boundaries and technology stack.
2C	Cross-Cutting	Decide cross-cutting concerns (auth, observability, data consistency, security). These become constraints for all Phase 3 component designs.
3	Components	Design individual components sequentially. Each component must be explicitly accepted before the next begins.
4	Finalisation	Consolidate all accepted components into a solution document, validate against Phase 1 requirements, produce deliverables.

State File: `.arch/state.json`

ALWAYS read this file before every architecture-related response. It tracks the current phase and the acceptance status of each component. NEVER rely on conversation memory for phase state.

Example structure:

{
  "current_phase": "methodology",
  "phases": {
    "evaluation": { "status": "accepted" },
    "methodology": {
      "status": "in_progress",
      "sub_phase": "cross_cutting",
      "pattern_accepted": true,
      "components_overview_accepted": true,
      "cross_cutting_accepted": false
    }
  },
  "components": {
    "api-gateway": { "status": "accepted" },
    "auth-service": { "status": "in_progress" },
    "data-layer": { "status": "pending" }
  },
  "decision_count": 7,
  "reopens": { "count": 0, "max": 2 }
}

A component is accepted only when the user types the explicit command /accept or the single word ACCEPT in uppercase. Paraphrases such as "looks good", "fine", or "approved" are NOT acceptance — respond by asking the user to confirm with /accept.

Read the full file on GitHub · 114 lines

Files

What ships with it

19 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

2mo ago First seen · 114 lines · 118 tokens per session scan A d946c79c44fb

Subscribe to this mod's changes

architecture-methodology is a skill published in the GitHub repository AhmedHabiba/architor (6 stars, last pushed 8mo ago), licensed MIT. It adds 118 tokens to every session and 1,315 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-08-31.

Claude Code Planning ai ai-agents architecture-automation claude claude-code-plugin

architecture-methodology next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
architecture-methodologyAhmedHabiba/architor	Skill	6	8mo ago	MIT	A	118	Claude Code
reviewSethGammon/Citadel	Skill	930	yesterday	MIT	A	17	Claude Code
system-upgradealivecontext/alive	Skill	132	3d ago	MIT	A	55	Claude Code
wenlan-handoffwenlan-app/wenlan	Skill	133	today	Apache-2.0	A	43	Claude Code, Codex
read-literaturefirecrawl/firecrawl-claude-plugin	Skill	259	2d ago	MIT	A	101	Claude Code
pr-reviewnitinjain999/platform-skills	Skill	72	5d ago	Apache-2.0	A	81	Claude Code
apex-skillifytonone-ai/tonone	Skill	77	3d ago	MIT	A	41	Claude Code