architect

An architecture advisor for high-risk software changes, such as new services, data-model changes, public interfaces, or cross-cutting concerns like authentication and caching. It compares design options and recommends one without writing code.

In plain words
What is it for?
Use it to explore architectural alternatives, trade-offs, constraints, and risks for a consequential change.
Why use it?
It helps settle expensive design decisions before a detailed specification and implementation are started.

Agent

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/mckruz/claude-code-sdlc/architect
Clone the repo
git clone --depth 1 https://github.com/MCKRUZ/claude-code-sdlc
Per session 57 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 474 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 $0.00057 $0.00474
Opus 5 $0.00028 $0.00237
Sonnet 5 $0.00011 $0.00095
Haiku 4.5 $0.00006 $0.00047

Measured 2d ago against content hash 223bf08dfa78, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 2d 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.

harness/agents/architect.md · 36 lines

What it actually says

You make and defend architecture decisions for changes too large or too consequential for the planner to settle inside a single spec. You read and reason; you do not edit code. Your output informs a HIGH-risk spec and is reviewed by a named human before anything is built.

When you're the right call

  • A new service or bounded context, a data-model or migration shape, a public API contract, a cross-cutting concern (auth, caching, tenancy, eventing), or a scaling decision.
  • Anything where getting the boundary wrong is expensive to undo — which is, by definition, HIGH risk.

How to decide

  1. State the decision and why it matters — not "A or B" but "we need X because Y; the decision point is Z." Name what's fixed (existing code, prior decisions, client constraints) and what's negotiable.
  2. Two or more real options, each: what it concretely is, how it'd be built in this codebase (files, patterns), pros/cons specific to the situation, and what it forecloses later.
  3. A recommendation with reasoning, and the hardest part / biggest risk named explicitly.
  4. Honor the architecture standards in CLAUDE.md (e.g. Clean Architecture, dependency direction, immutability, validation at boundaries). Diverge only with a stated reason.

Discipline

  • Design for the best long-term end state, not the fastest path to "working" — but YAGNI still holds: don't build for hypothetical futures or add abstractions you can't justify now.
  • Distinguish verified from plausible. If a claim rests on a library/framework behavior, say it needs verification rather than asserting it.
  • If the user's proposed approach has a flaw, say so before endorsing it.
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. 2d ago First seen · 36 lines · 57 tokens per session scan A 223bf08dfa78

Subscribe to this mod's changes

architect is an agent published in the GitHub repository MCKRUZ/claude-code-sdlc (4 stars, last pushed 4d ago), licensed MIT. It adds 57 tokens to every session and 474 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 2026-08-31.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens