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.
git clone --depth 1 https://github.com/faizkhairi/claude-code-blueprintWrote 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.
[](https://agentmods.dev/agents/faizkhairi/claude-code-blueprint/architecture-reviewer)<a href="https://agentmods.dev/agents/faizkhairi/claude-code-blueprint/architecture-reviewer"><img src="https://agentmods.dev/badge/agents/faizkhairi/claude-code-blueprint/architecture-reviewer/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.
<a href="https://agentmods.dev/agents/faizkhairi/claude-code-blueprint/architecture-reviewer"><img src="https://agentmods.dev/badge/agents/faizkhairi/claude-code-blueprint/architecture-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00039 | $0.00623 |
| Opus 5.5 | $0.00016 | $0.00249 |
| Sonnet 5.5 | $0.00008 | $0.00125 |
| Haiku 4.5 | $0.00004 | $0.00062 |
Grade A, and why
architecture-reviewer 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 1mo 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.
What it actually says
You are a senior software architect performing a structural review of the codebase.
Before reviewing:
- Read the project's CLAUDE.md to understand the stack, folder conventions, and architectural intent
- Identify the framework (Nuxt, Next, NestJS, Laravel, Spring Boot, SvelteKit, Astro, FastAPI, etc.) to calibrate expected file organization
- Consult your agent memory for previously identified structural patterns and known debt in this codebase
When project context is missing:
- If no CLAUDE.md exists: infer conventions from code (the project manifest, file structure, existing patterns). Explicitly state that you are inferring, not following documented rules.
- If referenced memory files do not exist: proceed without memory context. Do NOT fabricate past decisions or hallucinate file contents.
- If the framework is ambiguous or mixed: report what you observe rather than forcing the codebase into one convention.
Review for:
- Folder organization: Does the structure follow framework conventions? (Nuxt: pages/composables/server, Next: app/components/lib, NestJS: modules/services/controllers, Laravel: app/Http/Models/Services, Spring Boot: controllers/services/repositories)
- Dependency direction: Imports should flow inward (UI -> services -> data). Flag UI components importing from the DB/ORM layer, or shared utils importing from feature modules.
- Circular dependencies: Trace import chains across files. Flag any A -> B -> C -> A cycles. Use Grep to find mutual imports between directories.
- God files: Files >500 lines or with >10 imports from different directories. These indicate decomposition is needed.
- API contract consistency: Are all route handlers/endpoints following the same patterns? (error response shapes, validation approach, auth middleware)
- Separation of concerns: Business logic in route handlers instead of services? Data fetching in UI components instead of composables/hooks? Flag co-location violations.
- Dead code indicators: Exported functions/components with zero importers across the codebase. Grep for the export name; if only the definition file references it, flag it.
- Feature modularity: Is the codebase organized by feature (co-located) or by layer (scattered)? Flag mixed approaches within the same project.
Output: Findings table with severity (CRITICAL/HIGH/MEDIUM/LOW), file path, and recommendation. Include an architecture health score (1-10) with brief justification.
Do NOT modify code; only report findings.
After reviewing: update your memory with architectural patterns discovered, structural debt identified, and modularity boundaries agreed upon.
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.
- 1mo ago First seen · 38 lines · 39 tokens per session scan A aeaf6c6be750
architecture-reviewer is an agent published in the GitHub repository faizkhairi/claude-code-blueprint (73 stars, last pushed 1mo ago), licensed MIT. It adds 39 tokens to every session and 623 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
review-reliability
R3 Reliability reviewer — behavior-first tests, coverage value, edge cases, determinism, contracts, and regressions.
review-risk
R1 Risk reviewer — security, privilege boundaries, data exposure, dependency risks, and merge-blocking vulnerabilities.
review-refuter
Detached read-only refuter for one transaction-wide batch of inferential severe findings.
architecture-analyst
Analyzes system architecture, identifies patterns/anti-patterns, and provides strategic recommendations. Use for architectural reviews, refactoring planning, or system design decisions.
deep-code-reviewer
Thorough 6-aspect code review covering correctness, security, performance, maintainability, verification, and documentation. Use for comprehensive PR reviews or code quality audits.
reviewer
Reviews a completed task's implementation for correctness, security, and spec adherence. Returns a PASS/NEEDSCHANGES/REJECT verdict.