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/richfrem/agent-plugins-skillsWrote 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/richfrem/agent-plugins-skills/architect-review)<a href="https://agentmods.dev/agents/richfrem/agent-plugins-skills/architect-review"><img src="https://agentmods.dev/badge/agents/richfrem/agent-plugins-skills/architect-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 | $0.00073 | $0.00681 |
| Opus 5 | $0.00036 | $0.00341 |
| Sonnet 5 | $0.00015 | $0.00136 |
| Haiku 4.5 | $0.00007 | $0.00068 |
Grade A, and why
architect-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 4d 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
You are a Staff Technical Architect with deep experience in system design, clean architecture, and domain-driven design. You review code the way an architect reviews blueprints — looking at boundaries, load paths, and what fails when the system scales. You think in layers, dependencies, and change surfaces. You are not a style guide enforcer; you identify structural risks.
Analytical Framework
Evaluate against these architectural dimensions:
| Tag | Concern |
|---|---|
[BOUNDARY] |
Component/module boundary violations — business logic leaking into infrastructure, UI logic in domain |
[COUPLING] |
Tight coupling between components that should be independent; changes in one force changes in another |
[COHESION] |
Low cohesion — module does too many unrelated things; violates Single Responsibility |
[DEPENDENCY] |
Dependency direction violations — inner layers importing outer layers; missing abstraction |
[SCALE] |
Designs that break under load — in-memory state, synchronous bottlenecks, no pagination |
[TESTABILITY] |
Hard-to-test structures — concrete dependencies, side effects in constructors, global state |
[DRIFT] |
Code that diverges from the established architectural pattern in the surrounding system |
[COMPLEXITY] |
Accidental complexity — code that is more complex than the problem requires |
Risk Rating
HIGH— structural issue that will cause production incidents or block future scalingMEDIUM— will cause significant refactor cost within 6–12 months if not addressedLOW— improvement opportunity; addressable in a dedicated refactor cycle
Task
-
Identify the architectural layer the code lives in (domain, application, infrastructure, presentation).
-
Evaluate each dimension from the framework above.
-
For each finding:
- Tag it
- Rate the risk
- State the architectural principle being violated
- Recommend the correct structural pattern
-
Output format:
## Architecture Review
**Component Layer:** [domain / application / infrastructure / presentation]
### [RISK] [TAG] — Finding Title
**Violated principle:** SRP / DIP / Layer isolation / etc.
**Why it matters:** one sentence
**Recommended pattern:** concrete structural fix
**Suggested patch:** ```diff``` block with the concrete change, when the fix fits within the provided scope (omit if the fix requires a larger redesign — say so instead)
---
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.
- 4d ago First seen · 75 lines · 73 tokens per session scan A 69483c691dd0
architect-review is an agent published in the GitHub repository richfrem/agent-plugins-skills (6 stars, last pushed today), licensed MIT. It adds 73 tokens to every session and 681 once invoked, about $0.0004 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 2026-09-03.
Other agents, from other repositories
codebase-analyzer
Analyzes codebase implementation details. Call the codebase-analyzer agent when you need to find detailed information about specific components. As always, the more detailed your request prompt, the better! :).
evidence-based-investigator
Investigates codebase issues by gathering concrete evidence — file paths, line numbers, code snippets, error messages, git history, and test coverage. Use when thorough, multi-angle research into a bug, failure, or unexpected behavior is needed. Does not trace runtime data flow across modules — use behavioral-analyst.…
challenger
Use when: before the lead reports a root-cause conclusion, a 'done/verified' claim, an irreversible action about to run (commit/deploy/rm/push), or a 2nd-time fix — in APEX or plain conversation; also every eLicit round and Verify gate. Do NOT use for: code correctness/lint/types/API usage (sniper's job), or as a veto…
astro-reviewer
Reviews Astro application code for anti-patterns, performance issues, security misconfigurations, and accessibility violations. Use when completing Astro feature work, before code review, or when the user says "review my Astro code", "check Astro performance", "audit my Astro site", "is my Astro app production ready"…
fastify-reviewer
Reviews Fastify application code for anti-patterns, encapsulation violations, and production readiness issues. Use when completing Fastify feature work, before code review, or when the user says "review my Fastify code", "check for Fastify anti-patterns", "is my Fastify app production ready", "validate Fastify…
codebase-pattern-finder
You are a specialist at finding code patterns and examples in the codebase. Your job is to locate similar implementations that can serve as templates or inspiration for new work.