codemeridian-architecture-review

codemeridian-architecture-review is an agent for Claude Code from Driftya/code-meridian. It costs 34 tokens per session (2,250 once invoked), scanned A, original, MIT.

A specialist code-review agent for checking software architecture and the safety of code changes. It uses repository evidence and CodeMeridian graph context to examine how code is connected.

In plain words
What is it for?
Use it to review changes or pull requests, check architecture and layering, assess async and logging concerns, inspect nullability and analyzer risks, and find test gaps.
Why use it?
It helps reveal changes that cross design boundaries, introduce maintenance risks, weaken tests, or affect more code than expected.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

Install

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.

agentmods
npx agentmods add agents/driftya/code-meridian/codemeridian-architecture-review-agent
Clone the repo
git clone --depth 1 https://github.com/Driftya/code-meridian

Made for: Claude Code.

Wrote 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.

agentmods badge for codemeridian-architecture-review

README.md
[![agentmods](https://agentmods.dev/badge/agents/driftya/code-meridian/codemeridian-architecture-review-agent.svg)](https://agentmods.dev/agents/driftya/code-meridian/codemeridian-architecture-review-agent)
Your own site
<a href="https://agentmods.dev/agents/driftya/code-meridian/codemeridian-architecture-review-agent"><img src="https://agentmods.dev/badge/agents/driftya/code-meridian/codemeridian-architecture-review-agent.svg" alt="Measured on agentmods" height="20"></a>
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,250 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00034 $0.02250
Opus 5 $0.00017 $0.01125
Sonnet 5 $0.00007 $0.00450
Haiku 4.5 $0.00003 $0.00225

Measured 5d ago against content hash 1a6c81ca6478, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

codemeridian-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 5d 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.

docs/agent-capabilities/agents/codemeridian-architecture-review-agent.md · 417 lines

How it starts

The opening of the file, as written. The whole thing — 417 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CodeMeridian Architecture Review Agent

You are a CodeMeridian architecture review specialist.

Your role is to review planned or completed code changes using CodeMeridian graph context and repository evidence.

You do not gather context for its own sake. You review whether the change is safe, well-structured, testable, and aligned with the repository architecture.

projectContext can be found in meridian.json in field project. Not found then assume the projectContext is the name of *.slx/.sln or *.code-workspace without the extension, in last case use the root project folder name. Then we can assume we are using the global meridian.json in *\AppData\Local\CodeMeridian

Mission

Review code changes for:

  1. architecture boundary violations
  2. dependency direction problems
  3. SOLID and maintainability risks
  4. async and cancellation issues
  5. logging and observability issues
  6. nullability and analyzer risks
  7. test coverage gaps
  8. stale or incomplete graph context
  9. risky impact or blast radius

When To Use

Use this agent when the user asks:

  • review this change
  • review this PR
  • check architecture
  • check if this is safe
  • check layering
  • does this break anything
  • is this refactor okay
  • what tests are missing
  • what is the impact
  • check quality risks
  • check if this follows the repo rules

Also use this agent after a non-trivial implementation or refactor.

Use installed CodeMeridian skills when they fit the task:

  • codemeridian-context for graph-grounded context before review
  • codemeridian-frontend when the review touches HTML/CSS/SCSS relationships, selector impact, cascade risk, or style duplication
  • codemeridian-refactor for refactor impact, blast radius, and route planning
  • codemeridian-test-planning for test shield and coverage gaps

First Pass: Architecture And Design

Start by checking architecture, design, and dependency direction.

1. Check Graph Freshness

When exact relationships matter, check whether the graph is fresh.

Read the full file on GitHub · 417 lines

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.

  1. 5d ago First seen · 417 lines · 34 tokens per session scan A 1a6c81ca6478

Subscribe to this mod's changes

codemeridian-architecture-review is an agent published in the GitHub repository Driftya/code-meridian (4 stars, last pushed 7d ago), licensed MIT. It adds 34 tokens to every session and 2,250 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 2026-08-31.

Related

Other agents, from other repositories

sverklo-explore

Drop-in replacement for Claude Code's built-in Explore subagent. Uses sverklo's hybrid-retrieval MCP tools (BM25 + ONNX embeddings + PageRank, 36 tools) to answer file-discovery and code-search questions with 60% fewer tokens than naive grep. Use this when you need to locate definitions, trace references, understand…

sverklo/sverklo · 96 tokens

codesage-feature-reviewer

Review one CodeSage feature slice and return strict JSON findings.

iliaal/codesage · 19 tokens

codesage-finding-verifier

Adversarially verify a bounded array of new findings from one feature.

iliaal/codesage · 22 tokens

dotnet-explore

Locates the C# symbols, references, and files a task touches, and reports the blast radius — before any code is written. Use when about to modify code, when assessing how a new feature lands in the existing codebase, or when navigating dependencies to find what a change would break. Returns symbolIds and file:line…

Attemainio/dotnet-toolkit · 105 tokens

dotnet-guard-redteam

Audit-only instrument for dotnet-guard-audit. Attempts a battery of known and improvised bypasses against this repo's own guard-cs-edit, guard-cs-read, guard-cs-bash-read and guard-cs-bash-write PreToolUse hooks — unusual quoting, spaced paths, symlinks, copies, variable expansion, and writing to a .cs file through…

Attemainio/dotnet-toolkit · 212 tokens

reviewer

Independent semantic review of a Cartograph Rust/PostgreSQL diff before merge or release. Read-only; checks correctness, bounds, concurrency, migration safety, agent evidence quality, and gate alignment.

adder-factory/cartograph · 41 tokens