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.
npx skills add omergocmen/vibe-coder-kit --skill architecture-reviewgit clone --depth 1 https://github.com/omergocmen/vibe-coder-kitWrote 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/skills/omergocmen/vibe-coder-kit/architecture-review)<a href="https://agentmods.dev/skills/omergocmen/vibe-coder-kit/architecture-review"><img src="https://agentmods.dev/badge/skills/omergocmen/vibe-coder-kit/architecture-review.svg" alt="Measured on agentmods" 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 | $0.00057 | $0.01451 |
| Opus 5 | $0.00028 | $0.00726 |
| Sonnet 5 | $0.00011 | $0.00290 |
| Haiku 4.5 | $0.00006 | $0.00145 |
Grade A, and why
architecture-review 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 7d 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.
How it starts
The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architecture Review Skill
When to Trigger
- After
writing-plansproduces an implementation plan, beforeexecuting-plans - When a significant refactor is proposed
- When adding a new external service or integration
- When the team is debating between two approaches
- When something "feels off" about a design but you can't articulate why
Step-by-Step Process
1. Load the Plan
Read the implementation plan (typically implementation_plan.md or the artifact from writing-plans).
Extract:
- Components being built
- Data flow between components
- External dependencies
- Assumptions the plan makes
2. Run the Checklists
Work through each checklist section. For every "No" or "Unclear" answer, flag it as a finding.
A. Complexity Check
- Is this the simplest solution that could work?
- Are there off-the-shelf solutions (libraries, services) that cover 80%+ of this?
- Does each component have a single, clear responsibility?
- Would a junior developer understand this in 30 minutes?
B. Coupling & Cohesion
- Can each module be tested in isolation?
- Are there circular dependencies? (A needs B needs A)
- Is data ownership clear? (only one place writes to each piece of state)
- Is the public API surface minimal? (don't expose what doesn't need to be exposed)
C. Data & State
- Is the source of truth for each piece of data clearly defined?
- What happens if the datastore goes down?
- Is there any global mutable state? If so, is it justified?
- Are database migrations planned for any schema 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.
- 7d ago First seen · 157 lines · 57 tokens per session scan A 73ed9d3c5f74
architecture-review is a skill published in the GitHub repository omergocmen/vibe-coder-kit (91 stars, last pushed 3mo ago), licensed MIT. It adds 57 tokens to every session and 1,451 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.
Other skills, from other repositories
code-review-ai-ai-review
You are an expert AI-powered code review specialist combining automated static analysis, intelligent pattern recognition, and modern DevOps practices. Leverage AI tools (GitHub Copilot, Qodo, GPT-5, C.
code-refactoring-tech-debt
You are a technical debt expert specializing in identifying, quantifying, and prioritizing technical debt in software projects. Analyze the codebase to uncover debt, assess its impact, and create acti.
error-debugging-multi-agent-review
Use when working with error debugging multi agent review.
code-reviewer
Elite code review expert specializing in modern AI-powered code analysis, security vulnerabilities, performance optimization, and production reliability. Masters static analysis tools, security scanning, and configuration review with 2024/2025 best practices. Use PROACTIVELY for code quality assurance.
comprehensive-review-full-review
Use when working with comprehensive review full review.
git-pr-workflows-git-workflow
Orchestrate a comprehensive git workflow from code review through PR creation, leveraging specialized agents for quality assurance, testing, and deployment readiness. This workflow implements modern g.