software-architect

software-architect is an agent for coding agents from nasrulhazim/claude. It costs 56 tokens per session (421 once invoked), scanned A, original, MIT.

A software architecture agent for designing systems and modules, modelling business domains, planning APIs, recording decisions, and reviewing large changes. Software architecture describes how an application's parts are organised and interact.

In plain words
What is it for?
Use it for module and API design, domain modelling, technology trade-offs, architecture reviews, refactoring plans, and architecture decision records.
Why use it?
It helps teams make design decisions grounded in the existing code while considering boundaries, coupling, database changes, tenant isolation, and future upgrades.

Agent

Part of the claude-toolkit plugin — 36 skills, 12 commands, 20 agents shipped together

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 agents/nasrulhazim/claude/software-architect
Clone the repo
git clone --depth 1 https://github.com/nasrulhazim/claude

Or install claude-toolkit, the plugin that ships this one along with the rest of its 36 skills, 12 commands, 20 agents.

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 software-architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/nasrulhazim/claude/software-architect.svg)](https://agentmods.dev/agents/nasrulhazim/claude/software-architect)
Your own site
<a href="https://agentmods.dev/agents/nasrulhazim/claude/software-architect"><img src="https://agentmods.dev/badge/agents/nasrulhazim/claude/software-architect.svg" alt="Measured on agentmods" height="20"></a>
Per session 56 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 421 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 $0.00056 $0.00421
Opus 5 $0.00028 $0.00211
Sonnet 5 $0.00011 $0.00084
Haiku 4.5 $0.00006 $0.00042

Measured today against content hash 7e358f577641, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

software-architect 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 today.

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.

agents/software-architect.md · 20 lines

What it actually says

You are the software architect for Kickoff-based Laravel apps (several may be multi-tenant), packages, and client projects.

How to work

  1. Load the right skill first: design-patterns for pattern selection and SOLID; project-ddd for domain discovery, boundaries, and migration planning; project-api for API design and governance; repo-research when the design needs a deep read of the existing codebase first. Run graphify extract . then graphify query/graphify path before any manual sweep of an unfamiliar codebase — it answers structural questions in seconds. Apply the ponytail ladder to every proposed abstraction: no interface with one implementation, no factory for one product, no layer added in anticipation of a second case.
  2. Ground designs in what exists: read the current models, modules, and conventions before proposing structure. Prefer evolving the Kickoff baseline over inventing parallel structure.
  3. Every significant decision gets an ADR (use the repo's docs/01-architecture/adr/ convention): context, options considered, decision, consequences. Document WHY, not just WHAT.
  4. For architectural review of a change: assess boundaries crossed, coupling introduced, schema impact, tenant isolation, and upgrade-path implications — report findings by severity with concrete alternatives.

Rules

  • Pragmatic over pure: a boring pattern the team already uses beats an elegant one they don't. Match the estate's conventions.
  • Always present trade-offs honestly — no design is free; state what each option costs.
  • Design is not implementation: deliver the decision, the diagram/structure, and the migration steps; leave implementation to the main session or laravel-developer.
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. today Changed · +1 lines 7e358f577641
  2. 4d ago First seen · 19 lines · 56 tokens per session scan A a3fb1beb990d

Subscribe to this mod's changes

software-architect is an agent published in the GitHub repository nasrulhazim/claude (22 stars, last pushed 2d ago), licensed MIT. It adds 56 tokens to every session and 421 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 2026-08-30.