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/oxygen-fragment/claude-modularWrote 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/commands/oxygen-fragment/claude-modular/architecture-review)<a href="https://agentmods.dev/commands/oxygen-fragment/claude-modular/architecture-review"><img src="https://agentmods.dev/badge/commands/oxygen-fragment/claude-modular/architecture-review/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/commands/oxygen-fragment/claude-modular/architecture-review"><img src="https://agentmods.dev/badge/commands/oxygen-fragment/claude-modular/architecture-review.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 | $0.00000 | $0.00600 |
| Opus 5.5 | $0.00000 | $0.00240 |
| Sonnet 5.5 | $0.00000 | $0.00120 |
| Haiku 4.5 | $0.00000 | $0.00060 |
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 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
Architecture Review Command
2. **Component Documentation**
- Document individual component responsibilities
- Map component dependencies and interfaces
- Analyze coupling and cohesion patterns
- Identify reusable components and libraries
3. **Technical Debt Assessment**
- Identify architectural inconsistencies
- Analyze code quality and maintainability
- Document technical debt and improvement opportunities
- Assess scalability and performance bottlenecks
4. **Documentation Generation**
- Create architecture diagrams and visualizations
- Generate component interaction diagrams
- Document API contracts and interfaces
- Create deployment and infrastructure diagrams
5. **Review and Recommendations**
- Assess architecture against industry best practices
- Identify improvement opportunities
- Document architectural decisions and rationale
- Create roadmap for architectural evolution
6. **Knowledge Sharing**
- Create architecture overview presentations
- Document onboarding materials for new developers
- Establish architecture review processes
- Create decision logs and ADRs
# Generated documentation:
# - System overview diagrams
# - Component documentation
# - Technical debt analysis
# - Improvement recommendations
```
```bash
# Review specific architecture layer
/docs:architecture-review --layer=data-layer
# Layer-specific review:
# - Data architecture analysis
# - Database design review
# - Data flow documentation
# - Performance optimization
```
```bash
# Architecture review for scaling
/docs:architecture-review --focus=scalability
# Scalability-focused review:
# - Performance bottlenecks
# - Scaling strategies
# - Load balancing options
# - Infrastructure requirements
```
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 · 98 lines · 0 tokens per session scan A 2b00082f23b0
architecture-review is a command published in the GitHub repository oxygen-fragment/claude-modular (285 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 600 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.
Other commands, from other repositories
review-pr
PR review using parallel specialized agents for code quality, security, testing, architecture, and performance analysis. Synthesizes findings into a review report with conventional comments (praise/issue/suggestion/nitpick) and approve or request-changes verdict. Use when reviewing pull requests, conducting security…
iterate-plan
Revises a plan written by create-plan from its review comments or new instructions: rewrites the plan body, leaves each comment intact and bumps the revision. Use when a plan file got feedback or its scope changed; never to start a new plan.
review-artifact-comments
Works through the review comments written into a task artifact (plan or research under .ork/tasks/TASK/): lists the open ones, asks how to proceed, then replies, resolves or hands off to iterate-plan or iterate-research, and approves the artifact once nothing is open. Use when a reviewer has commented on an artifact…
paul:audit
Run enterprise-grade architectural audit on current plan.
deep-audit.skeleton
Description: This section is populated by Bootstrap with manifest data. Required manifest fields: project.description, stack.primary, project.structure, project.subprojects, stack.orm, stack.authmethod Example output.
task-hunter.skeleton
The user's input is resolved according to the following rules.