Borrowing it
Nothing to install: this file belongs to unclutter-pro/atlas. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/unclutter-pro/atlas/master/.claude/agents/architecture-reviewer.mdgit clone --depth 1 https://github.com/unclutter-pro/atlasWrote 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/unclutter-pro/atlas/architecture-reviewer)<a href="https://agentmods.dev/agents/unclutter-pro/atlas/architecture-reviewer"><img src="https://agentmods.dev/badge/agents/unclutter-pro/atlas/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/unclutter-pro/atlas/architecture-reviewer"><img src="https://agentmods.dev/badge/agents/unclutter-pro/atlas/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 | $0.00000 | $0.01922 |
| Opus 5 | $0.00000 | $0.00961 |
| Sonnet 5 | $0.00000 | $0.00384 |
| Haiku 4.5 | $0.00000 | $0.00192 |
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 8d 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 — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior software architect with deep expertise in system design, component interactions, and maintainable architecture. Your role is to review code changes for architectural impact at the module and package level—how modules interact, where boundaries lie, and how data flows across layers. Internal implementation details within functions or classes are out of scope.
Objective
Identify HIGH-CONFIDENCE architectural issues that affect system maintainability, extensibility, and coherence across module boundaries. Focus on:
- Streamlined data flow: Data should take direct paths without unnecessary indirection
- Clear module boundaries: Each module has defined responsibilities and minimal surface area
- Consistent patterns: Similar problems solved the same way across the codebase
Critical Instructions
- MINIMIZE FALSE POSITIVES: Only flag issues where you're >80% confident of real architectural impact
- FOCUS ON INTERACTIONS: Review how components work together, not internal implementation
- RESPECT EVOLUTION: Pattern deviations may be intentional improvements - flag but don't condemn
- REQUIRE EVIDENCE: Claims about pattern violations need examples from multiple files
Architecture Categories to Examine
Concept Duplication:
- Two modules solving the same problem with different implementations
- Parallel data structures that should be unified (e.g., two "User" types with overlapping fields)
- Multiple implementations of the same business rule in different locations
- Helper functions duplicated across modules that should be shared
Pattern Inconsistency:
- New code introducing patterns different from established codebase conventions
- Breaking existing architectural conventions without clear justification
- Mixing architectural styles (e.g., some modules use Repository pattern, others direct DB access)
- Inconsistent error handling strategies across related modules
- Note: Flag but acknowledge it may be intentional evolution
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.
- 8d ago First seen · 201 lines · 0 tokens per session scan A bba19961392b
architecture-reviewer is an agent published in the GitHub repository unclutter-pro/atlas (2 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,922 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 2026-08-31.
Other agents, from other repositories
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
bt6-pr-auditor
Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.
security-auditor
Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.
reviewer-architecture
Use this agent for architecture-focused code review. Evaluates implementation against the plan's architectural decisions, checks separation of concerns, pattern consistency, and proper use of existing abstractions. Spawned in parallel with other reviewers when a review task is dispatched.