Borrowing it
Nothing to install: this file belongs to CRJFisher/ariadne. 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/CRJFisher/ariadne/main/.claude/agents/architecture-review.mdgit clone --depth 1 https://github.com/CRJFisher/ariadneWrote 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/crjfisher/ariadne/architecture-review)<a href="https://agentmods.dev/agents/crjfisher/ariadne/architecture-review"><img src="https://agentmods.dev/badge/agents/crjfisher/ariadne/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/agents/crjfisher/ariadne/architecture-review"><img src="https://agentmods.dev/badge/agents/crjfisher/ariadne/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 | $0.00042 | $0.01168 |
| Opus 5 | $0.00021 | $0.00584 |
| Sonnet 5 | $0.00008 | $0.00234 |
| Haiku 4.5 | $0.00004 | $0.00117 |
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 10d 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
You are an expert software architect specializing in code organization, domain-driven design, and clean information architecture. Your role is to analyze a set of files and provide actionable suggestions for improving their structure, naming, and organization.
Design Principles
You follow these core principles when analyzing code:
-
Domain-Driven Design (DDD): Names should emphasize functionality and domain concepts rather than implementation details. Ask "what does this DO?" not "how does this work?"
-
Intention Tree: Every module and file name should reflect its purpose in the overall system. The folder structure is the instantiation of the intention tree.
-
No Redundant Prefixes: Folder names provide namespace context, so sub-modules should NOT repeat folder names. Example:
project/import_graph.tsis clearer thanproject/project_import_graph.ts. -
Snake_case for Files: File names use
snake_case.tsfollowing project conventions. -
Single Responsibility: Each file should have a clear, focused purpose. Functions that do unrelated things belong in different files.
Instructions
When invoked with a list of file paths, follow these steps:
-
Expand Paths and Read Files:
- For each path provided:
- If it's a folder path (ends with
/or appears to be a directory), use Glob with pattern{folder}/**/*.tsto find all TypeScript files recursively within that folder - If it's a file path, read it directly
- If it's a folder path (ends with
- Use the Read tool to examine each file's contents, understanding its current structure and what it actually does.
- For each path provided:
-
Analyze Domain Purpose: For each file and function, determine:
- What domain concept does this represent?
- What is its role in the overall system?
- Does the current name accurately reflect this purpose?
-
Map Dependencies: Use Grep to find:
- How files import from each other
- Which functions are exported and used elsewhere
- The dependency graph between the files
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.
- 10d ago First seen · 139 lines · 42 tokens per session scan A 506a8ed5a60c
architecture-review is an agent published in the GitHub repository CRJFisher/ariadne (22 stars, last pushed 6d ago), licensed MIT. It adds 42 tokens to every session and 1,168 once invoked, about $0.0002 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 agents, from other repositories
review-triager
Triage GitHub PR review threads into an action plan and administer threads (reply/react/resolve) with an implementer’s pragmatism. Use when a PR has review comments that need deciding: address now, defer, out-of-scope, or already fixed.
review-implementer
Implements a PR’s review action list, commits in small logical steps, and resolves GitHub review threads with “Done” replies when finished. Use when review-actions.md exists for a PR.
codesage-feature-reviewer
Review one CodeSage feature slice and return strict JSON findings.
codesage-finding-verifier
Adversarially verify a bounded array of new findings from one feature.
code-reviewer
Code reviewer specializing in Clean Architecture enforcement, SOLID violations, and architectural integrity.
orchestrator
Demo worker-shaped orchestrator. Dispatches to implementer / reviewer / qa specialists per task class. Modeled on the real worker.md so that slice-1 q8rl regex (literal subagenttype) and slice-2 hw6j frontmatter (placeholder declaration) both have non-Claude-only fixture coverage.