architect-review-spike

architect-review-spike is a command for Claude Code from SteveGJones/ai-first-sdlc-practices. It costs 0 tokens per session (1,555 once invoked), scanned A, original, MIT.

A command that reviews an architectural decomposition proposal for an open-source software-development framework. The proposal divides the repository into programs, sub-programs, and modules using domain-driven design boundaries and Bazel-style visibility rules.

In plain words
What is it for?
Use it to critique the decomposition spike, assess its module boundaries and dependency visibility rules, and report concrete issues in the proposed design.
Why use it?
It gives a structured way to find problems in the proposed architecture without redesigning it. The review is based on the full spike document and delegated architectural reasoning.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md).

Good fit Use it to critique the decomposition spike, assess its module boundaries and dependency visibility rules, and report concrete issues in the proposed design.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/stevegjones/ai-first-sdlc-practices/architect-review-spike
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.

Clone the repo
git clone --depth 1 https://github.com/SteveGJones/ai-first-sdlc-practices

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 architect-review-spike

README.md
[![agentmods](https://agentmods.dev/badge/commands/stevegjones/ai-first-sdlc-practices/architect-review-spike/github.svg)](https://agentmods.dev/commands/stevegjones/ai-first-sdlc-practices/architect-review-spike)
Your own site
<a href="https://agentmods.dev/commands/stevegjones/ai-first-sdlc-practices/architect-review-spike"><img src="https://agentmods.dev/badge/commands/stevegjones/ai-first-sdlc-practices/architect-review-spike/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.

agentmods 80×15 button for architect-review-spike

Your own site · 80×15
<a href="https://agentmods.dev/commands/stevegjones/ai-first-sdlc-practices/architect-review-spike"><img src="https://agentmods.dev/badge/commands/stevegjones/ai-first-sdlc-practices/architect-review-spike.svg" alt="Reviewed on agentmods" width="80" 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 1,555 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.01555
Opus 5 $0.00000 $0.00777
Sonnet 5 $0.00000 $0.00311
Haiku 4.5 $0.00000 $0.00155

Measured 11d ago against content hash b275fafe099e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

architect-review-spike 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 11d 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.

.archon/commands/architect-review-spike.md · 138 lines

How it starts

The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Architect Review — Decomposition Spike

Your Role

You are a senior solution architect reviewing an architectural decomposition spike for the ai-first-sdlc-practices repository (an open-source SDLC framework). The spike proposes a candidate programs / sub-programs / modules decomposition under DDD bounded-context discipline + Bazel visibility-rule philosophy.

You operate in a fresh container with SDLC plugins installed. Use the sdlc-team-common:solution-architect agent (via the Agent tool with subagent_type="sdlc-team-common:solution-architect") for the actual architectural reasoning — this command file briefs the agent and captures their output as your structured review.

Your task is review and critique, not redesign. Do not propose alternative decompositions. Surface concrete issues with the one proposed.

What you're reviewing

Primary input: research/sdlc-bundles/decomposition-spike.md (in the worktree).

Read the WHOLE document before reviewing. It has 9 sections:

  • 0: executive verdict
  • 1: repo character analysis
  • 2: candidate programs block (YAML)
  • 3: per-module DDD analysis
  • 4: visibility rules / DAG
  • 5: granularity targets
  • 6: worked example using kb-query cross-library synthesis (PR #177 code)
  • 7: failure-mode honest assessment
  • 8: verdict and what it means for Phase D-E
  • 9: critical review by sdlc-team-common:solution-architect and response

Important: Section 9 is a previous review by the same agent type that you are now invoking. Your dispatch must:

  1. Independently produce findings — read the spike Sections 0-8 first, form your own judgement, then read Section 9 to compare
  2. Confirm whether the previous review's verdicts hold under independent dispatch (would you have surfaced the same 8 issues? would you have surfaced different ones?)
  3. Surface any issues NOT covered by the previous review

Do not rubber-stamp the previous review. Do not just re-paraphrase it.

Required context

Before reviewing, also read:

Read the full file on GitHub · 138 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. 11d ago First seen · 138 lines · 0 tokens per session scan A b275fafe099e

Subscribe to this mod's changes

architect-review-spike is a command published in the GitHub repository SteveGJones/ai-first-sdlc-practices (41 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,555 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.